A novel fuzzy C-means algorithm for unsupervised heterogeneous tumor quantification in PET

Purpose: Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C-means (FCM) clustering algorith...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Medical physics (Lancaster) Ročník 37; číslo 3; s. 1309 - 1324
Hlavní autoři: Belhassen, Saoussen, Zaidi, Habib
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States American Association of Physicists in Medicine 01.03.2010
Témata:
Algorithms
anisotropic diffusion filtering
Artificial Intelligence
cancer
Carcinoma, Non-Small-Cell Lung - diagnostic imaging
cellular biophysics
Computed tomography
Diffusion
discrete wavelet transforms
FCM segmentation
Fuzzy Logic
Humans
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
image segmentation
Integral transforms
intensity heterogeneity
lung
Lung Neoplasms - diagnostic imaging
Medical image noise
medical image processing
Medical image segmentation
Medical image spatial resolution
Medical imaging
Neural networks, fuzzy logic, artificial intelligence
Pattern Recognition, Automated - methods
phantoms
Phantoms, Imaging
positron emission tomography
positron emission tomography (PET)
Positron-Emission Tomography - instrumentation
Positron-Emission Tomography - methods
Reproducibility of Results
Segmentation
Sensitivity and Specificity
tumours
Wavelet transform
Wavelets
à trous wavelet transform
intensity heterogeneity
à trous wavelet transform
FCM segmentation
positron emission tomography (PET)
anisotropic diffusion filtering
ISSN:0094-2405, 2473-4209
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Purpose: Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C-means (FCM) clustering algorithm was largely used in various medical image segmentation approaches. However, the algorithm is sensitive to both noise and intensity heterogeneity since it does not take into account spatial contextual information. Methods: To overcome this limitation, a new fuzzy segmentation technique adapted to typical noisy and low resolution oncological PET data is proposed. PET images smoothed using a nonlinear anisotropic diffusion filter are added as a second input to the proposed FCM algorithm to incorporate spatial information (FCM-S). In addition, a methodology was developed to integrate theà trous wavelet transform in the standard FCM algorithm (FCM-SW) to allow handling of heterogeneous lesions’ uptake. The algorithm was applied to the simulated data of the NCAT phantom, incorporating heterogeneous lesions in the lung and clinical PET/CT images of 21 patients presenting with histologically proven nonsmall-cell lung cancer (NSCLC) and 7 patients presenting with laryngeal squamous cell carcinoma (LSCC) to assess its performance for segmenting tumors with arbitrary size, shape, and tracer uptake. For NSCLC patients, the maximal tumor diameters measured from the macroscopic examination of the surgical specimen served as the ground truth for comparison with the maximum diameter estimated by the segmentation technique, whereas for LSCC patients, the 3D macroscopic tumor volume was considered as the ground truth for comparison with the corresponding PET-based volume. The proposed algorithm was also compared to the classical FCM segmentation technique. Results: There is a good correlation ( R 2 = 0.942 ) between the actual maximal diameter of primary NSCLC tumors estimated using the proposed PET segmentation procedure and those measured from the macroscopic examination, and the regression line agreed well with the line of identity ( slope = 1.08 ) for the group analysis of the clinical data. The standard FCM algorithm seems to underestimate actual maximal diameters of the clinical data, resulting in a mean error of −4.6 mm (relative error of − 10.8 ± 23.1 % ) for all data sets. The mean error of maximal diameter estimation was reduced to 0.1 mm ( 0.9 ± 14.4 % ) using the proposed FCM-SW algorithm. Likewise, the mean relative error on the estimated volume for LSCC patients was reduced from 21.7 ± 22.0 % for FCM to 8.6 ± 28.3 % using the proposed FCM-SW technique. Conclusions: A novel unsupervised PET image segmentation technique that allows the quantification of lesions in the presence of heterogeneity of tracer uptake was developed and evaluated. The technique is being further refined and assessed in clinical setting to delineate treatment volumes for the purpose of PET-guided radiation therapy treatment planning but could find other applications in clinical oncology such as the assessment of response to treatment.
AbstractList Purpose: Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C‐means (FCM) clustering algorithm was largely used in various medical image segmentation approaches. However, the algorithm is sensitive to both noise and intensity heterogeneity since it does not take into account spatial contextual information. Methods: To overcome this limitation, a new fuzzy segmentation technique adapted to typical noisy and low resolution oncological PET data is proposed. PET images smoothed using a nonlinear anisotropic diffusion filter are added as a second input to the proposed FCM algorithm to incorporate spatial information (FCM‐S). In addition, a methodology was developed to integrate theà trous wavelet transform in the standard FCM algorithm (FCM‐SW) to allow handling of heterogeneous lesions’ uptake. The algorithm was applied to the simulated data of the NCAT phantom, incorporating heterogeneous lesions in the lung and clinical PET/CT images of 21 patients presenting with histologically proven nonsmall‐cell lung cancer (NSCLC) and 7 patients presenting with laryngeal squamous cell carcinoma (LSCC) to assess its performance for segmenting tumors with arbitrary size, shape, and tracer uptake. For NSCLC patients, the maximal tumor diameters measured from the macroscopic examination of the surgical specimen served as the ground truth for comparison with the maximum diameter estimated by the segmentation technique, whereas for LSCC patients, the 3D macroscopic tumor volume was considered as the ground truth for comparison with the corresponding PET‐based volume. The proposed algorithm was also compared to the classical FCM segmentation technique. Results: There is a good correlation (R2=0.942) between the actual maximal diameter of primary NSCLC tumors estimated using the proposed PET segmentation procedure and those measured from the macroscopic examination, and the regression line agreed well with the line of identity (slope=1.08) for the group analysis of the clinical data. The standard FCM algorithm seems to underestimate actual maximal diameters of the clinical data, resulting in a mean error of −4.6 mm (relative error of −10.8±23.1%) for all data sets. The mean error of maximal diameter estimation was reduced to 0.1 mm (0.9±14.4%) using the proposed FCM‐SW algorithm. Likewise, the mean relative error on the estimated volume for LSCC patients was reduced from 21.7±22.0% for FCM to 8.6±28.3% using the proposed FCM‐SW technique. Conclusions: A novel unsupervised PET image segmentation technique that allows the quantification of lesions in the presence of heterogeneity of tracer uptake was developed and evaluated. The technique is being further refined and assessed in clinical setting to delineate treatment volumes for the purpose of PET‐guided radiation therapy treatment planning but could find other applications in clinical oncology such as the assessment of response to treatment.
Purpose: Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C-means (FCM) clustering algorithm was largely used in various medical image segmentation approaches. However, the algorithm is sensitive to both noise and intensity heterogeneity since it does not take into account spatial contextual information. Methods: To overcome this limitation, a new fuzzy segmentation technique adapted to typical noisy and low resolution oncological PET data is proposed. PET images smoothed using a nonlinear anisotropic diffusion filter are added as a second input to the proposed FCM algorithm to incorporate spatial information (FCM-S). In addition, a methodology was developed to integrate the à trous wavelet transform in the standard FCM algorithm (FCM-SW) to allow handling of heterogeneous lesions' uptake. The algorithm was applied to the simulated data of the NCAT phantom, incorporating heterogeneous lesions in the lung and clinical PET/CT images of 21 patients presenting with histologically proven nonsmall-cell lung cancer (NSCLC) and 7 patients presenting with laryngeal squamous cell carcinoma (LSCC) to assess its performance for segmenting tumors with arbitrary size, shape, and tracer uptake. For NSCLC patients, the maximal tumor diameters measured from the macroscopic examination of the surgical specimen served as the ground truth for comparison with the maximum diameter estimated by the segmentation technique, whereas for LSCC patients, the 3D macroscopic tumor volume was considered as the ground truth for comparison with the corresponding PET-based volume. The proposed algorithm was also compared to the classical FCM segmentation technique. Results: There is a good correlation ( R 2 = 0.942 ) between the actual maximal diameter of primary NSCLC tumors estimated using the proposed PET segmentation procedure and those measured from the macroscopic examination, and the regression line agreed well with the line of identity ( slope = 1.08 ) for the group analysis of the clinical data. The standard FCM algorithm seems to underestimate actual maximal diameters of the clinical data, resulting in a mean error of −4.6 mm (relative error of − 10.8 ± 23.1 % ) for all data sets. The mean error of maximal diameter estimation was reduced to 0.1 mm ( 0.9 ± 14.4 % ) using the proposed FCM-SW algorithm. Likewise, the mean relative error on the estimated volume for LSCC patients was reduced from 21.7 ± 22.0 % for FCM to 8.6 ± 28.3 % using the proposed FCM-SW technique. Conclusions: A novel unsupervised PET image segmentation technique that allows the quantification of lesions in the presence of heterogeneity of tracer uptake was developed and evaluated. The technique is being further refined and assessed in clinical setting to delineate treatment volumes for the purpose of PET-guided radiation therapy treatment planning but could find other applications in clinical oncology such as the assessment of response to treatment.
Purpose: Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C-means (FCM) clustering algorithm was largely used in various medical image segmentation approaches. However, the algorithm is sensitive to both noise and intensity heterogeneity since it does not take into account spatial contextual information. Methods: To overcome this limitation, a new fuzzy segmentation technique adapted to typical noisy and low resolution oncological PET data is proposed. PET images smoothed using a nonlinear anisotropic diffusion filter are added as a second input to the proposed FCM algorithm to incorporate spatial information (FCM-S). In addition, a methodology was developed to integrate theà trous wavelet transform in the standard FCM algorithm (FCM-SW) to allow handling of heterogeneous lesions’ uptake. The algorithm was applied to the simulated data of the NCAT phantom, incorporating heterogeneous lesions in the lung and clinical PET/CT images of 21 patients presenting with histologically proven nonsmall-cell lung cancer (NSCLC) and 7 patients presenting with laryngeal squamous cell carcinoma (LSCC) to assess its performance for segmenting tumors with arbitrary size, shape, and tracer uptake. For NSCLC patients, the maximal tumor diameters measured from the macroscopic examination of the surgical specimen served as the ground truth for comparison with the maximum diameter estimated by the segmentation technique, whereas for LSCC patients, the 3D macroscopic tumor volume was considered as the ground truth for comparison with the corresponding PET-based volume. The proposed algorithm was also compared to the classical FCM segmentation technique. Results: There is a good correlation ( R 2 = 0.942 ) between the actual maximal diameter of primary NSCLC tumors estimated using the proposed PET segmentation procedure and those measured from the macroscopic examination, and the regression line agreed well with the line of identity ( slope = 1.08 ) for the group analysis of the clinical data. The standard FCM algorithm seems to underestimate actual maximal diameters of the clinical data, resulting in a mean error of −4.6 mm (relative error of − 10.8 ± 23.1 % ) for all data sets. The mean error of maximal diameter estimation was reduced to 0.1 mm ( 0.9 ± 14.4 % ) using the proposed FCM-SW algorithm. Likewise, the mean relative error on the estimated volume for LSCC patients was reduced from 21.7 ± 22.0 % for FCM to 8.6 ± 28.3 % using the proposed FCM-SW technique. Conclusions: A novel unsupervised PET image segmentation technique that allows the quantification of lesions in the presence of heterogeneity of tracer uptake was developed and evaluated. The technique is being further refined and assessed in clinical setting to delineate treatment volumes for the purpose of PET-guided radiation therapy treatment planning but could find other applications in clinical oncology such as the assessment of response to treatment.
Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C-means (FCM) clustering algorithm was largely used in various medical image segmentation approaches. However, the algorithm is sensitive to both noise and intensity heterogeneity since it does not take into account spatial contextual information.PURPOSEAccurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C-means (FCM) clustering algorithm was largely used in various medical image segmentation approaches. However, the algorithm is sensitive to both noise and intensity heterogeneity since it does not take into account spatial contextual information.To overcome this limitation, a new fuzzy segmentation technique adapted to typical noisy and low resolution oncological PET data is proposed. PET images smoothed using a nonlinear anisotropic diffusion filter are added as a second input to the proposed FCM algorithm to incorporate spatial information (FCM-S). In addition, a methodology was developed to integrate the a trous wavelet transform in the standard FCM algorithm (FCM-SW) to allow handling of heterogeneous lesions' uptake. The algorithm was applied to the simulated data of the NCAT phantom, incorporating heterogeneous lesions in the lung and clinical PET/CT images of 21 patients presenting with histologically proven nonsmall-cell lung cancer (NSCLC) and 7 patients presenting with laryngeal squamous cell carcinoma (LSCC) to assess its performance for segmenting tumors with arbitrary size, shape, and tracer uptake. For NSCLC patients, the maximal tumor diameters measured from the macroscopic examination of the surgical specimen served as the ground truth for comparison with the maximum diameter estimated by the segmentation technique, whereas for LSCC patients, the 3D macroscopic tumor volume was considered as the ground truth for comparison with the corresponding PET-based volume. The proposed algorithm was also compared to the classical FCM segmentation technique.METHODSTo overcome this limitation, a new fuzzy segmentation technique adapted to typical noisy and low resolution oncological PET data is proposed. PET images smoothed using a nonlinear anisotropic diffusion filter are added as a second input to the proposed FCM algorithm to incorporate spatial information (FCM-S). In addition, a methodology was developed to integrate the a trous wavelet transform in the standard FCM algorithm (FCM-SW) to allow handling of heterogeneous lesions' uptake. The algorithm was applied to the simulated data of the NCAT phantom, incorporating heterogeneous lesions in the lung and clinical PET/CT images of 21 patients presenting with histologically proven nonsmall-cell lung cancer (NSCLC) and 7 patients presenting with laryngeal squamous cell carcinoma (LSCC) to assess its performance for segmenting tumors with arbitrary size, shape, and tracer uptake. For NSCLC patients, the maximal tumor diameters measured from the macroscopic examination of the surgical specimen served as the ground truth for comparison with the maximum diameter estimated by the segmentation technique, whereas for LSCC patients, the 3D macroscopic tumor volume was considered as the ground truth for comparison with the corresponding PET-based volume. The proposed algorithm was also compared to the classical FCM segmentation technique.There is a good correlation (R2 = 0.942) between the actual maximal diameter of primary NSCLC tumors estimated using the proposed PET segmentation procedure and those measured from the macroscopic examination, and the regression line agreed well with the line of identity (slope = 1.08) for the group analysis of the clinical data. The standard FCM algorithm seems to underestimate actual maximal diameters of the clinical data, resulting in a mean error of -4.6 mm (relative error of -10.8 +/- 23.1%) for all data sets. The mean error of maximal diameter estimation was reduced to 0.1 mm (0.9 +/- 14.4%) using the proposed FCM-SW algorithm. Likewise, the mean relative error on the estimated volume for LSCC patients was reduced from 21.7 +/- 22.0% for FCM to 8.6 +/- 28.3% using the proposed FCM-SW technique.RESULTSThere is a good correlation (R2 = 0.942) between the actual maximal diameter of primary NSCLC tumors estimated using the proposed PET segmentation procedure and those measured from the macroscopic examination, and the regression line agreed well with the line of identity (slope = 1.08) for the group analysis of the clinical data. The standard FCM algorithm seems to underestimate actual maximal diameters of the clinical data, resulting in a mean error of -4.6 mm (relative error of -10.8 +/- 23.1%) for all data sets. The mean error of maximal diameter estimation was reduced to 0.1 mm (0.9 +/- 14.4%) using the proposed FCM-SW algorithm. Likewise, the mean relative error on the estimated volume for LSCC patients was reduced from 21.7 +/- 22.0% for FCM to 8.6 +/- 28.3% using the proposed FCM-SW technique.A novel unsupervised PET image segmentation technique that allows the quantification of lesions in the presence of heterogeneity of tracer uptake was developed and evaluated. The technique is being further refined and assessed in clinical setting to delineate treatment volumes for the purpose of PET-guided radiation therapy treatment planning but could find other applications in clinical oncology such as the assessment of response to treatment.CONCLUSIONSA novel unsupervised PET image segmentation technique that allows the quantification of lesions in the presence of heterogeneity of tracer uptake was developed and evaluated. The technique is being further refined and assessed in clinical setting to delineate treatment volumes for the purpose of PET-guided radiation therapy treatment planning but could find other applications in clinical oncology such as the assessment of response to treatment.
Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C-means (FCM) clustering algorithm was largely used in various medical image segmentation approaches. However, the algorithm is sensitive to both noise and intensity heterogeneity since it does not take into account spatial contextual information. To overcome this limitation, a new fuzzy segmentation technique adapted to typical noisy and low resolution oncological PET data is proposed. PET images smoothed using a nonlinear anisotropic diffusion filter are added as a second input to the proposed FCM algorithm to incorporate spatial information (FCM-S). In addition, a methodology was developed to integrate the a trous wavelet transform in the standard FCM algorithm (FCM-SW) to allow handling of heterogeneous lesions' uptake. The algorithm was applied to the simulated data of the NCAT phantom, incorporating heterogeneous lesions in the lung and clinical PET/CT images of 21 patients presenting with histologically proven nonsmall-cell lung cancer (NSCLC) and 7 patients presenting with laryngeal squamous cell carcinoma (LSCC) to assess its performance for segmenting tumors with arbitrary size, shape, and tracer uptake. For NSCLC patients, the maximal tumor diameters measured from the macroscopic examination of the surgical specimen served as the ground truth for comparison with the maximum diameter estimated by the segmentation technique, whereas for LSCC patients, the 3D macroscopic tumor volume was considered as the ground truth for comparison with the corresponding PET-based volume. The proposed algorithm was also compared to the classical FCM segmentation technique. There is a good correlation (R2 = 0.942) between the actual maximal diameter of primary NSCLC tumors estimated using the proposed PET segmentation procedure and those measured from the macroscopic examination, and the regression line agreed well with the line of identity (slope = 1.08) for the group analysis of the clinical data. The standard FCM algorithm seems to underestimate actual maximal diameters of the clinical data, resulting in a mean error of -4.6 mm (relative error of -10.8 +/- 23.1%) for all data sets. The mean error of maximal diameter estimation was reduced to 0.1 mm (0.9 +/- 14.4%) using the proposed FCM-SW algorithm. Likewise, the mean relative error on the estimated volume for LSCC patients was reduced from 21.7 +/- 22.0% for FCM to 8.6 +/- 28.3% using the proposed FCM-SW technique. A novel unsupervised PET image segmentation technique that allows the quantification of lesions in the presence of heterogeneity of tracer uptake was developed and evaluated. The technique is being further refined and assessed in clinical setting to delineate treatment volumes for the purpose of PET-guided radiation therapy treatment planning but could find other applications in clinical oncology such as the assessment of response to treatment.
Author Zaidi, Habib
Belhassen, Saoussen
Author_xml – sequence: 1
  givenname: Saoussen
  surname: Belhassen
  fullname: Belhassen, Saoussen
  organization: Division of Nuclear Medicine, Geneva University Hospital, CH-1211 Geneva, Switzerland
– sequence: 2
  givenname: Habib
  surname: Zaidi
  fullname: Zaidi, Habib
  email: habib.zaidi@hcuge.ch
  organization: Division of Nuclear Medicine, Geneva University Hospital, CH-1211 Geneva, Switzerland and Geneva Neuroscience Center, Geneva University, CH-1205 Geneva, Switzerland
BackLink https://www.ncbi.nlm.nih.gov/pubmed/20384268$$D View this record in MEDLINE/PubMed
BookMark eNqNkUtrHDEQhEVwiNdODvkDQbfgwNgtaR6aS2BZnAc4xAfnkovQSi1bYUZaSzMb1r8-431ACHHIqS9fFdVVJ-QoxICEvGZwzhiTF-xcCGA1g2dkxstGFCWH9ojMANqy4CVUx-Qk5x8AUIsKXpBjDkKWvJYz8n1OQ1xjR9348LChi6JHHTLV3W1MfrjrqYuJjiGPK0xrn9HSOxwwxVsMGMdMh7GfgPtRh8E7b_TgY6A-0OvLm5fkudNdxlf7e0q-fbi8WXwqrr5-_LyYXxWmYgIKZgQuHTTCGCOd4bKVlrVOaxTYspprqEvQAmUjJLfa6ZI3tmpsa5xhS2vFKXm7812leD9iHlTvs8Gu09uIqhFCSqjbaiLf7Mlx2aNVq-R7nTbqUMcEXOwAk2LOCZ0yftj-NCTtO8VAPRaumNoXPinO_lAcTP_GFjv2p-9w8zSovlzv-fc7Ph9SPK2Zq-2MajujWqjHGSeDd_9t8C94HdNv6VbWiV8dXb9b
CODEN MPHYA6
CitedBy_id crossref_primary_10_1007_s13246_017_0587_6
crossref_primary_10_1007_s00259_011_2053_0
crossref_primary_10_1097_RLU_0000000000003789
crossref_primary_10_1111_bjh_18016
crossref_primary_10_1118_1_4929561
crossref_primary_10_1016_j_cmpb_2017_07_006
crossref_primary_10_1186_2197_7364_1_12
crossref_primary_10_1007_s10044_014_0399_1
crossref_primary_10_1016_j_compbiomed_2013_07_027
crossref_primary_10_1118_1_4728219
crossref_primary_10_1109_TIM_2018_2884017
crossref_primary_10_1049_iet_ipr_2016_1024
crossref_primary_10_1016_j_ins_2015_02_015
crossref_primary_10_1088_1361_6560_ac994e
crossref_primary_10_1016_j_compbiomed_2017_05_034
crossref_primary_10_1118_1_4863480
crossref_primary_10_1016_j_ins_2022_11_010
crossref_primary_10_1088_0031_9155_57_15_5035
crossref_primary_10_1007_s00259_021_05624_5
crossref_primary_10_1016_j_semcancer_2023_03_005
crossref_primary_10_1097_MNM_0000000000000317
crossref_primary_10_1118_1_4928485
crossref_primary_10_1186_s13550_018_0379_3
crossref_primary_10_1007_s11517_016_1571_0
crossref_primary_10_1016_j_cpet_2019_03_002
crossref_primary_10_1118_1_4761952
crossref_primary_10_1186_s12917_025_04591_5
crossref_primary_10_1088_0031_9155_57_17_5381
crossref_primary_10_1038_s41598_019_51096_x
crossref_primary_10_3390_jimaging10010027
crossref_primary_10_1016_j_cviu_2016_10_002
crossref_primary_10_1118_1_4793721
crossref_primary_10_1088_0031_9155_61_1_227
crossref_primary_10_1109_TBME_2017_2688453
crossref_primary_10_1016_j_cmpb_2012_10_009
crossref_primary_10_1016_j_canrad_2011_07_243
crossref_primary_10_1016_j_radonc_2012_05_002
crossref_primary_10_1007_s40336_014_0068_9
crossref_primary_10_1109_TBME_2023_3297249
crossref_primary_10_1007_s00530_017_0579_0
crossref_primary_10_1118_1_4813302
crossref_primary_10_1053_j_semnuclmed_2017_09_005
crossref_primary_10_1109_JBHI_2022_3230060
crossref_primary_10_1259_bjr_20140625
crossref_primary_10_1118_1_4947123
crossref_primary_10_1002_mp_12124
crossref_primary_10_1186_2191_219X_3_85
crossref_primary_10_1155_2013_980769
crossref_primary_10_1007_s11547_014_0446_4
crossref_primary_10_1109_TBME_2015_2433397
crossref_primary_10_1016_j_artmed_2019_01_002
crossref_primary_10_1016_j_cpet_2011_02_009
crossref_primary_10_1016_j_jrmge_2025_01_057
crossref_primary_10_1118_1_4954844
crossref_primary_10_1016_j_ejmp_2017_08_012
crossref_primary_10_1155_2020_5648206
crossref_primary_10_1016_j_semradonc_2017_08_003
crossref_primary_10_1016_j_ijrobp_2014_01_047
crossref_primary_10_1016_j_compbiomed_2014_04_014
crossref_primary_10_1109_TITB_2011_2159307
crossref_primary_10_1093_jrr_rrw082
crossref_primary_10_1007_s40336_015_0135_x
crossref_primary_10_1109_TMI_2012_2202322
crossref_primary_10_1118_1_4816296
crossref_primary_10_1155_2015_571473
crossref_primary_10_1371_journal_pone_0031724
crossref_primary_10_1007_s00259_015_3239_7
crossref_primary_10_1088_1361_6560_ac01f4
crossref_primary_10_1118_1_4812892
crossref_primary_10_1088_0031_9155_60_13_5123
crossref_primary_10_3390_app12104865
crossref_primary_10_1016_j_ejmp_2018_08_008
crossref_primary_10_1109_TIP_2015_2488902
crossref_primary_10_1155_2012_327861
crossref_primary_10_1088_0031_9155_61_13_4855
crossref_primary_10_1016_j_compbiomed_2018_09_002
crossref_primary_10_1109_TMI_2010_2083681
crossref_primary_10_1088_1361_6560_ab8535
crossref_primary_10_1002_ima_22154
crossref_primary_10_1109_TCBB_2023_3281638
crossref_primary_10_1007_s11307_016_1015_0
crossref_primary_10_1016_j_neucom_2016_08_042
crossref_primary_10_1109_TFUZZ_2023_3317779
crossref_primary_10_1016_j_compbiomed_2020_103701
crossref_primary_10_1109_ACCESS_2020_3003138
crossref_primary_10_1016_j_compmedimag_2021_101886
crossref_primary_10_3938_jkps_77_1049
crossref_primary_10_1016_j_engappai_2019_02_005
crossref_primary_10_1109_JBHI_2022_3186275
crossref_primary_10_1002_mp_14903
crossref_primary_10_1007_s00259_010_1688_6
crossref_primary_10_1002_widm_1474
crossref_primary_10_1109_TIP_2018_2872908
crossref_primary_10_1186_s13014_018_1163_2
crossref_primary_10_2310_7290_2014_00032
crossref_primary_10_1109_TMI_2013_2263388
crossref_primary_10_1109_JBHI_2020_3024563
crossref_primary_10_1118_1_4828836
crossref_primary_10_3389_fmed_2015_00018
crossref_primary_10_3390_cancers6041821
crossref_primary_10_1109_TNS_2013_2295975
crossref_primary_10_1016_j_media_2013_11_003
crossref_primary_10_1016_j_imu_2020_100481
crossref_primary_10_1016_j_media_2013_05_004
crossref_primary_10_1007_s00259_010_1423_3
crossref_primary_10_1016_j_ejmp_2019_04_020
crossref_primary_10_1016_j_cpet_2019_08_005
Cites_doi 10.1109/23.910837
10.1016/j.dsp.2007.11.005
10.1118/1.3160108
10.1148/radiol.2331030660
10.1109/34.56205
10.1016/j.acra.2009.02.014
10.1016/j.acra.2004.07.012
10.1016/j.compmedimag.2008.08.004
10.1016/0165-1684(94)90211-9
10.1049/ip-vis:20000218
10.1109/42.996338
10.1109/51.334636
10.1109/TPAMI.1980.4766964
10.1118/1.2791035
10.1007/s002590050425
10.1016/j.ijrobp.2007.04.065
10.1053/j.semnuclmed.2007.01.005
10.1016/S0167-8140(03)00270-6
10.1016/j.ijrobp.2008.04.019
10.1109/78.157290
10.1016/S0933-3657(98)00069-4
10.1016/j.ijrobp.2006.12.067
10.1016/j.ctrv.2006.02.002
10.1109/42.802752
10.1118/1.2799886
10.1080/01969727308546046
10.1016/j.compmedimag.2005.10.001
10.1007/s00259-008-0943-6
10.1118/1.2938518
10.1109/TSMCB.2004.831165
10.1109/TMI.2003.816956
10.1155/2007/25182
10.1016/0895-6111(96)00025-0
10.1016/S0360-3016(00)00467-3
10.1056/NEJMra050276
10.1109/JPROC.2003.817883
10.1109/TMI.2008.2012036
10.1016/j.acra.2005.08.035
10.1006/cviu.2001.0951
10.1007/s00259-006-0363-4
10.1109/TPAMI.1986.4767851
10.1016/j.lungcan.2007.03.020
10.2967/jnumed.106.035774
10.1088/0031-9155/53/16/001
10.1016/j.asoc.2007.10.025
10.1118/1.2432404
10.1088/0031-9155/47/7/310
10.1016/j.radonc.2003.10.009
10.47102/annals-acadmedsg.V33N2p183
10.1007/978-3-642-97177-8_28
10.1109/TSMC.1987.6499296
10.1017/CBO9780511564352
ContentType Journal Article
Copyright American Association of Physicists in Medicine
2010 American Association of Physicists in Medicine
Copyright_xml – notice: American Association of Physicists in Medicine
– notice: 2010 American Association of Physicists in Medicine
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1118/1.3301610
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList


MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Physics
EISSN 2473-4209
EndPage 1324
ExternalDocumentID 20384268
10_1118_1_3301610
MP1610
Genre article
Evaluation Studies
Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: NSF-CH
  grantid: SNSF 3152A0-102143
– fundername: Swiss National Science Foundation
  funderid: SNSF 3152A0‐102143
GroupedDBID ---
--Z
-DZ
.GJ
0R~
1OB
1OC
29M
2WC
33P
36B
3O-
4.4
476
53G
5GY
5RE
5VS
AAHHS
AANLZ
AAQQT
AASGY
AAXRX
AAZKR
ABCUV
ABEFU
ABFTF
ABJNI
ABLJU
ABQWH
ABTAH
ABXGK
ACAHQ
ACBEA
ACCFJ
ACCZN
ACGFO
ACGFS
ACGOF
ACPOU
ACSMX
ACXBN
ACXQS
ADBBV
ADBTR
ADKYN
ADOZA
ADXAS
ADZMN
AEEZP
AEGXH
AEIGN
AENEX
AEQDE
AEUYR
AFBPY
AFFPM
AHBTC
AIACR
AIAGR
AIURR
AIWBW
AJBDE
ALMA_UNASSIGNED_HOLDINGS
ALUQN
AMYDB
ASPBG
BFHJK
C45
CS3
DCZOG
DRFUL
DRMAN
DRSTM
DU5
EBD
EBS
EJD
EMB
EMOBN
F5P
G8K
HDBZQ
HGLYW
I-F
KBYEO
LATKE
LEEKS
LOXES
LUTES
LYRES
MEWTI
O9-
OVD
P2P
P2W
PALCI
PHY
RJQFR
RNS
ROL
SAMSI
SUPJJ
SV3
TEORI
TN5
TWZ
USG
WOHZO
WXSBR
XJT
ZGI
ZVN
ZXP
ZY4
ZZTAW
AAHQN
AAIPD
AAMNL
AAYCA
ABDPE
AFWVQ
AITYG
ALVPJ
AAMMB
AAYXX
ABUFD
ADMLS
AEFGJ
AEYWJ
AGHNM
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
LH4
CGR
CUY
CVF
ECM
EIF
NPM
7X8
ID FETCH-LOGICAL-c5130-1c3ebf073ccc8fc2898d19faae3e9162a0640a3e87382dafa427d57d9cfc1bdd3
IEDL.DBID DRFUL
ISICitedReferencesCount 146
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000275160300038&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0094-2405
IngestDate Fri Sep 05 14:02:17 EDT 2025
Thu Apr 03 07:04:56 EDT 2025
Tue Nov 18 21:38:34 EST 2025
Sat Nov 29 03:54:18 EST 2025
Wed Jan 22 16:38:45 EST 2025
Fri Jun 21 00:19:59 EDT 2024
Sun Jul 14 10:05:20 EDT 2019
Fri Jun 21 00:28:29 EDT 2024
IsPeerReviewed true
IsScholarly true
Issue 3
Keywords intensity heterogeneity
à trous wavelet transform
FCM segmentation
positron emission tomography (PET)
anisotropic diffusion filtering
Language English
License 0094-2405/2010/37(3)/1309/16/$30.00
http://onlinelibrary.wiley.com/termsAndConditions#vor
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c5130-1c3ebf073ccc8fc2898d19faae3e9162a0640a3e87382dafa427d57d9cfc1bdd3
Notes habib.zaidi@hcuge.ch
Telephone: +41 22 372 7258; Fax: +41 22 372 7169.
0094‐2405/2010/37(3)/1309/16/$30.00
Author to whom correspondence should be addressed. Electronic mail
ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Undefined-1
ObjectType-Feature-3
content type line 23
PMID 20384268
PQID 733880695
PQPubID 23479
PageCount 16
ParticipantIDs scitation_primary_10_1118_1_3301610A_novel_fuzzy_C_mean
crossref_citationtrail_10_1118_1_3301610
scitation_primary_10_1118_1_3301610
proquest_miscellaneous_733880695
wiley_primary_10_1118_1_3301610_MP1610
pubmed_primary_20384268
crossref_primary_10_1118_1_3301610
PublicationCentury 2000
PublicationDate March 2010
PublicationDateYYYYMMDD 2010-03-01
PublicationDate_xml – month: 03
  year: 2010
  text: March 2010
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Medical physics (Lancaster)
PublicationTitleAlternate Med Phys
PublicationYear 2010
Publisher American Association of Physicists in Medicine
Publisher_xml – name: American Association of Physicists in Medicine
References Juweid, Cheson (c5) 2006; 354
Pham, Prince (c15) 1999; 18
Clark (c23) 1994; 13
Aristophanous, Penney, Martel, Pelizzari (c61) 2007; 34
Bezdek, Hathaway, Sabin, Tucker (c36) 1987; 17
Bezdek (c37) 1980; PAMI-2
Pham (c28) 2001; 84
Liew, Hong (c17) 2003; 22
Tan, Ong (c50) 2004; 33
Ahmed, Yamany, Mohamed, Farag, Moriarty (c29) 2002; 21
Gregoire, Haustermans, Geets, Roels, Lonneux (c3) 2007; 48
van Baardwijk (c7) 2006; 32
Hatt, Cheze le Rest, Turzo, Roux, Visvikis (c11) 2009; 28
Masulli, Schenone (c14) 1999; 16
van Baardwijk (c51) 2007; 68
Boucek (c57) 2008; 53
Liew, Leung, Lau (c27) 2000; 147
Rahmim, Tang, Zaidi (c42) 2009; 36
Kang, Min, Luan, Li, Liu (c31) 2009; 19
Udupa, Saha (c59) 2003; 91
Soret, Bacharach, Buvat (c12) 2007; 48
Daisne (c54) 2003; 69
Montgomery, Amira, Zaidi (c9) 2007; 34
Geets, Lee, Bol, Lonneux, Gregoire (c53) 2007; 34
Dunn (c35) 1973; 3
Stroom (c63) 2007; 69
Chen, Zhang (c30) 2004; 34
Perona, Malik (c38) 1990; 12
Chen, Giger, Bick (c22) 2006; 13
El Naqa (c10) 2007; 34
Shensa (c43) 1992; 40
Kannan (c32) 2008; 8
Starck, Bijaoui (c44) 1994; 35
Aristophanous, Penney, Pelizzari (c62) 2008; 35
Czernin, Allen-Auerbach, Schelbert (c1) 2007; 48
Wang, Kong, Lu, Qi, Zhang (c20) 2008; 32
Yu, Wang (c19) 2007; 2007
Bijaoui, Starck, Murtagh (c47) 1994; 3
Canny (c40) 1986; PAMI-8
Chuang, Tzeng, Chen, Wu, Chen (c18) 2006; 30
Vees, Senthamizhchelvan, Miralbell, Weber, Ratib, Zaidi (c8) 2009; 36
Basu (c13) 2007; 37
Acton, Pilowsky, Kung, Ell (c21) 1999; 26
Zaidi, Diaz-Gomez, Boudraa, Slosman (c16) 2002; 47
Daisne (c58) 2003; 69
Zaidi, El Naqa (c4)
Janssen (c60) 2009; 73
Boudraa (c24) 1996; 20
Segars, Lalush, Tsui (c49) 2001; 48
Ling (c2) 2000; 47
Greco, Rosenzweig, Cascini, Tamburrini (c6) 2007; 57
Daisne (c52) 2004; 233
Belhassen (c55) 2009; 50
Demirkaya (c41) 2004; 11
Zaidi, Vees, Wissmeyer (c56) 2009; 16
Pham, D. 2001; 84
Bezdek, J.; Hathaway, R.; Sabin, M.; Tucker, W. 1987; 17
Aristophanous, M.; Penney, B.; Pelizzari, C. 2008; 35
Segars, W.; Lalush, D.; Tsui, B. 2001; 48
Kang, J.; Min, L.; Luan, Q.; Li, X.; Liu, J. 2009; 19
Demirkaya, O. 2004; 11
Starck, J.; Bijaoui, A. 1994; 35
Kannan, S. 2008; 8
El Naqa, I. 2007; 34
Chuang, K.; Tzeng, H.; Chen, S.; Wu, J.; Chen, T. 2006; 30
Boucek, J. 2008; 53
Bezdek, J. 1980; PAMI-2
Udupa, J.; Saha, P. 2003; 91
Vees, H.; Senthamizhchelvan, S.; Miralbell, R.; Weber, D.; Ratib, O.; Zaidi, H. 2009; 36
Wang, J.; Kong, J.; Lu, Y.; Qi, M.; Zhang, B. 2008; 32
van Baardwijk, A. 2007; 68
Czernin, J.; Allen-Auerbach, M.; Schelbert, H. 2007; 48
Liew, A.; Hong, Y. 2003; 22
Stroom, J. 2007; 69
Acton, P.; Pilowsky, L.; Kung, H.; Ell, P. 1999; 26
Liew, A.; Leung, S.; Lau, W. 2000; 147
Juweid, M.; Cheson, B. 2006; 354
Boudraa, A. 1996; 20
Soret, M.; Bacharach, S.; Buvat, I. 2007; 48
Zaidi, H.; Vees, H.; Wissmeyer, M. 2009; 16
Montgomery, D.; Amira, A.; Zaidi, H. 2007; 34
Gregoire, V.; Haustermans, K.; Geets, X.; Roels, S.; Lonneux, M. 2007; 48
Janssen, M. 2009; 73
Masulli, F.; Schenone, A. 1999; 16
Bijaoui, A.; Starck, J.; Murtagh, F. 1994; 3
Daisne, J. 2003; 69
Pham, D.; Prince, J. 1999; 18
Canny, J. 1986; PAMI-8
Perona, P.; Malik, J. 1990; 12
Zaidi, H.; Diaz-Gomez, M.; Boudraa, A.; Slosman, D. 2002; 47
Clark, M. 1994; 13
van Baardwijk, A. 2006; 32
Zaidi, H.; El Naqa, I.
Geets, X.; Lee, J.; Bol, A.; Lonneux, M.; Gregoire, V. 2007; 34
Basu, S. 2007; 37
Hatt, M.; Cheze le Rest, C.; Turzo, A.; Roux, C.; Visvikis, D. 2009; 28
Greco, C.; Rosenzweig, K.; Cascini, G.; Tamburrini, O. 2007; 57
Ling, C. 2000; 47
Ahmed, M.; Yamany, S.; Mohamed, N.; Farag, A.; Moriarty, T. 2002; 21
Belhassen, S. 2009; 50
Chen, S.; Zhang, D. 2004; 34
Rahmim, A.; Tang, J.; Zaidi, H. 2009; 36
Tan, L.; Ong, K. 2004; 33
Chen, W.; Giger, M.; Bick, U. 2006; 13
Dunn, J. 1973; 3
Shensa, M. 1992; 40
Yu, J.; Wang, Y. 2007; 2007
Daisne, J. 2004; 233
Aristophanous, M.; Penney, B.; Martel, M.; Pelizzari, C. 2007; 34
2006; 30
1990; 12
2000; 47
2006; 32
2008; 8
2008; 35
2008; 32
2001; 48
2007; 34
2001; 84
2007; 37
2004; 33
2002; 47
2003; 91
2009; 50
1999; 18
1999; 16
2004; 34
2003; 4
2007; 6
1994; 35
1986; PAMI‐8
2009; 19
2007; 68
2009; 16
1996; 20
2007; 69
1992; 40
1989
2006; 13
1999; 26
1998
2007
2008; 53
2006; 354
2007; 57
1987; 17
2009; 28
2004; 233
2004; 11
2009; 36
2009; 73
2000; 147
1980; PAMI‐2
2007; 2007
2002; 21
2005; 4
2003; 69
1994; 13
1998; 2
1994; 3
2007; 48
2003; 22
1973; 3
e_1_2_7_3_1
e_1_2_7_9_1
Czernin J. (e_1_2_7_2_1) 2007; 48
e_1_2_7_7_1
e_1_2_7_19_1
e_1_2_7_60_1
e_1_2_7_17_1
e_1_2_7_62_1
e_1_2_7_15_1
e_1_2_7_41_1
e_1_2_7_64_1
e_1_2_7_13_1
e_1_2_7_43_1
e_1_2_7_11_1
e_1_2_7_45_1
e_1_2_7_47_1
e_1_2_7_28_1
Zhu W. (e_1_2_7_26_1) 2003
e_1_2_7_50_1
e_1_2_7_25_1
e_1_2_7_31_1
e_1_2_7_52_1
e_1_2_7_23_1
e_1_2_7_33_1
e_1_2_7_54_1
e_1_2_7_21_1
Belhassen S. (e_1_2_7_56_1) 2009; 50
e_1_2_7_37_1
e_1_2_7_58_1
e_1_2_7_39_1
e_1_2_7_6_1
Tan L. (e_1_2_7_51_1) 2004; 33
Zaidi H. (e_1_2_7_5_1)
e_1_2_7_8_1
Congdon P. (e_1_2_7_34_1) 2007
e_1_2_7_18_1
e_1_2_7_16_1
e_1_2_7_61_1
Gregoire V. (e_1_2_7_4_1) 2007; 48
e_1_2_7_14_1
e_1_2_7_42_1
e_1_2_7_63_1
e_1_2_7_12_1
e_1_2_7_44_1
Kim J. (e_1_2_7_27_1) 2007
e_1_2_7_10_1
e_1_2_7_29_1
Montgomery D. W. G. (e_1_2_7_49_1) 2005
Holschneider M. (e_1_2_7_46_1) 1989
Weickert J. (e_1_2_7_40_1) 1998
e_1_2_7_30_1
e_1_2_7_53_1
e_1_2_7_24_1
e_1_2_7_32_1
e_1_2_7_55_1
e_1_2_7_22_1
e_1_2_7_57_1
e_1_2_7_20_1
e_1_2_7_59_1
Dunn J. C. (e_1_2_7_36_1) 1973; 3
e_1_2_7_38_1
Bijaoui A. (e_1_2_7_48_1) 1994; 3
Chen S. S. (e_1_2_7_35_1) 1998
References_xml – volume: 20
  start-page: 31
  issn: 0895-6111
  year: 1996
  ident: c24
  article-title: Delineation and quantitation of brain lesions by fuzzy clustering in positron emission tomography
  publication-title: Comput. Med. Imaging Graph.
– volume: 26
  start-page: 581
  issn: 0340-6997
  year: 1999
  ident: c21
  article-title: Automatic segmentation of dynamic neuroreceptor single-photon emission tomography images using fuzzy clustering
  publication-title: Eur. J. Nucl. Med.
– volume: 48
  start-page: 78S
  issn: 0161-5505
  year: 2007
  ident: c1
  article-title: Improvements in cancer staging with PET/CT: Literature-based evidence as of September 2006
  publication-title: J. Nucl. Med.
– volume: 16
  start-page: 1108
  issn: 1076-6332
  year: 2009
  ident: c56
  article-title: Molecular PET/CT imaging-guided radiation therapy treatment planning
  publication-title: Acad. Radiol.
– volume: PAMI-2
  start-page: 1
  issn: 0162-8828
  year: 1980
  ident: c37
  article-title: A convergence theorem for the fuzzy ISODATA clustering algorithms
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 35
  start-page: 195
  issn: 0165-1684
  year: 1994
  ident: c44
  article-title: Filtering and deconvolution by the wavelet transform
  publication-title: Signal Process.
– volume: 3
  start-page: 32
  issn: 0018-9472
  year: 1973
  ident: c35
  article-title: A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters
  publication-title: IEEE Trans. Syst. Man Cybern.
– volume: 34
  start-page: 722
  issn: 0094-2405
  year: 2007
  ident: c9
  article-title: Fully automated segmentation of oncological PET volumes using a combined multiscale and statistical model
  publication-title: Med. Phys.
– volume: 48
  start-page: 89
  issn: 0018-9499
  year: 2001
  ident: c49
  article-title: Modeling respiratory mechanics in the MCAT and spline-based MCAT phantoms
  publication-title: IEEE Trans. Nucl. Sci.
– volume: 36
  start-page: 3654
  issn: 0094-2405
  year: 2009
  ident: c42
  article-title: Four-dimensional (4D) image reconstruction strategies in dynamic PET: Beyond conventional independent frame reconstruction
  publication-title: Med. Phys.
– volume: 30
  start-page: 9
  issn: 0895-6111
  year: 2006
  ident: c18
  article-title: Fuzzy c-means clustering with spatial information for image segmentation
  publication-title: Comput. Med. Imaging Graph.
– volume: 69
  start-page: 267
  issn: 0360-3016
  year: 2007
  ident: c63
  article-title: Feasibility of pathology-correlated lung imaging for accurate target definition of lung tumors
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
– volume: 57
  start-page: 125
  issn: 0169-5002
  year: 2007
  ident: c6
  article-title: Current status of PET/CT for tumour volume definition in radiotherapy treatment planning for non-small cell lung cancer (NSCLC)
  publication-title: Lung Cancer
– volume: 16
  start-page: 129
  issn: 0933-3657
  year: 1999
  ident: c14
  article-title: A fuzzy clustering based segmentation system as support to diagnosis in medical imaging
  publication-title: Artif. Intell. Med.
– volume: 40
  start-page: 2464
  issn: 1053-587X
  year: 1992
  ident: c43
  article-title: The discrete wavelet transform: Wedding the a trous and Mallat algorithms
  publication-title: IEEE Trans. Signal Process.
– volume: 47
  start-page: 551
  issn: 0360-3016
  year: 2000
  ident: c2
  article-title: Towards multidimensional radiotherapy (MD-CRT): Biological imaging and biological conformality
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
– volume: 32
  start-page: 245
  issn: 0305-7372
  year: 2006
  ident: c7
  article-title: The current status of FDG-PET in tumour volume definition in radiotherapy treatment planning
  publication-title: Cancer Treat Rev.
– volume: 47
  start-page: 1143
  issn: 0031-9155
  year: 2002
  ident: c16
  article-title: Fuzzy clustering-based segmented attenuation correction in whole-body PET imaging
  publication-title: Phys. Med. Biol.
– volume: 32
  start-page: 685
  issn: 0895-6111
  year: 2008
  ident: c20
  article-title: A modified FCM algorithm for MRI brain image segmentation using both local and non-local spatial constraints
  publication-title: Comput. Med. Imaging Graph.
– volume: 68
  start-page: 771
  issn: 0360-3016
  year: 2007
  ident: c51
  article-title: PET-CT-based auto-contouring in non-small-cell lung cancer correlates with pathology and reduces interobserver variability in the delineation of the primary tumor and involved nodal volumes
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
– volume: 91
  start-page: 1649
  issn: 0018-9219
  year: 2003
  ident: c59
  article-title: Fuzzy connectedness and image segmentation
  publication-title: Proc. IEEE
– volume: 354
  start-page: 496
  issn: 0028-4793
  year: 2006
  ident: c5
  article-title: Positron-emission tomography and assessment of cancer therapy
  publication-title: N. Engl. J. Med.
– volume: 34
  start-page: 4738
  issn: 0094-2405
  year: 2007
  ident: c10
  article-title: Concurrent multimodality image segmentation by active contours for radiotherapy treatment planning
  publication-title: Med. Phys.
– volume: 50
  start-page: 27P
  issn: 0161-5505
  year: 2009
  ident: c55
  article-title: Comparative methods for 18F-FDG PET-based delineation of target volumes in non-small-cell lung cancer [abstract]
  publication-title: J. Nucl. Med.
– volume: 48
  start-page: 932
  issn: 0161-5505
  year: 2007
  ident: c12
  article-title: Partial-volume effect in PET tumor imaging
  publication-title: J. Nucl. Med.
– volume: 69
  start-page: 237
  issn: 0167-8140
  year: 2003
  ident: c54
  article-title: Evaluation of a multimodality image (CT, MRI and PET) coregistration procedure on phantom and head and neck cancer patients: Accuracy, reproducibility and consistency
  publication-title: Radiother. Oncol.
– volume: 73
  start-page: 456
  issn: 0360-3016
  year: 2009
  ident: c60
  article-title: Tumor delineation based on time-activity curve differences assessed with dynamic fluorodeoxyglucose positron emission tomography-computed tomography in rectal cancer patients
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
– volume: 33
  start-page: 183
  issn: 0304-4602
  year: 2004
  ident: c50
  article-title: Semi-quantitative measurements of normal organs with variable metabolic activity on FDG PET imaging
  publication-title: Ann. Acad. Med. Singapore
– issn: 1619-7070
  ident: c4
  article-title: PET-guided delineation of radiation therapy treatment volumes: A survey of image segmentation techniques
  publication-title: Eur. J. Nucl. Med. Mol. Imaging
– volume: 35
  start-page: 3331
  issn: 0094-2405
  year: 2008
  ident: c62
  article-title: The development and testing of a digital PET phantom for the evaluation of tumor volume segmentation techniques
  publication-title: Med. Phys.
– volume: 37
  start-page: 223
  issn: 0001-2998
  year: 2007
  ident: c13
  article-title: Novel quantitative techniques for assessing regional and global function and structure based on modern imaging modalities: Implications for normal variation, aging and diseased states
  publication-title: Semin Nucl. Med.
– volume: 18
  start-page: 737
  issn: 0278-0062
  year: 1999
  ident: c15
  article-title: Adaptive fuzzy segmentation of magnetic resonance images
  publication-title: IEEE Trans. Med. Imaging
– volume: 69
  start-page: 247
  issn: 0167-8140
  year: 2003
  ident: c58
  article-title: Tri-dimensional automatic segmentation of PET volumes based on measured source-to-background ratios: Influence of reconstruction algorithms
  publication-title: Radiother. Oncol.
– volume: 36
  start-page: 182
  issn: 1619-7070
  year: 2009
  ident: c8
  article-title: Assessment of various strategies for 18F-FET PET-guided delineation of target volumes in high-grade glioma patients
  publication-title: Eur. J. Nucl. Med. Mol. Imaging
– volume: 147
  start-page: 185
  issn: 1350-245X
  year: 2000
  ident: c27
  article-title: Fuzzy image clustering incorporating spatial continuity
  publication-title: IEEE Proc. Vision Image Signal Process
– volume: 34
  start-page: 4223
  issn: 0094-2405
  year: 2007
  ident: c61
  article-title: A Gaussian mixture model for definition of lung tumor volumes in positron emission tomography
  publication-title: Med. Phys.
– volume: 13
  start-page: 730
  issn: 0739-5175
  year: 1994
  ident: c23
  article-title: MRI segmentation using fuzzy clustering techniques
  publication-title: IEEE Eng. Med. Biol. Mag.
– volume: PAMI-8
  start-page: 679
  issn: 0162-8828
  year: 1986
  ident: c40
  article-title: A computational approach to edge detection
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 34
  start-page: 1427
  issn: 1619-7070
  year: 2007
  ident: c53
  article-title: A gradient-based method for segmenting FDG-PET images: Methodology and validation
  publication-title: Eur. J. Nucl. Med. Mol. Imaging
– volume: 84
  start-page: 285
  issn: 1077-3142
  year: 2001
  ident: c28
  article-title: “Spatial models for fuzzy clustering
  publication-title: Comput. Vis. Image Underst.
– volume: 21
  start-page: 193
  issn: 0278-0062
  year: 2002
  ident: c29
  article-title: A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data
  publication-title: IEEE Trans. Med. Imaging
– volume: 53
  start-page: 4213
  issn: 0031-9155
  year: 2008
  ident: c57
  article-title: Assessment of tumour response with 18F-fluorodeoxyglucose positron emission tomography using 3-dimensional measures compared to SUVmax—A phantom study
  publication-title: Phys. Med. Biol.
– volume: 13
  start-page: 63
  issn: 1076-6332
  year: 2006
  ident: c22
  article-title: A fuzzy C-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images
  publication-title: Acad. Radiol.
– volume: 28
  start-page: 881
  issn: 0278-0062
  year: 2009
  ident: c11
  article-title: A fuzzy locally adaptive Bayesian segmentation approach for volume determination in PET
  publication-title: IEEE Trans. Med. Imaging
– volume: 11
  start-page: 1105
  issn: 1076-6332
  year: 2004
  ident: c41
  article-title: Post-reconstruction filtering of positron emission tomography whole-body emission images and attenuation maps using nonlinear diffusion filtering
  publication-title: Acad. Radiol.
– volume: 19
  start-page: 309
  issn: 1051-2004
  year: 2009
  ident: c31
  article-title: Novel modified fuzzy c-means algorithm with applications
  publication-title: Digit. Signal Process.
– volume: 22
  start-page: 1063
  issn: 0278-0062
  year: 2003
  ident: c17
  article-title: An adaptive spatial fuzzy clustering algorithm for 3-D MR image segmentation
  publication-title: IEEE Trans. Med. Imaging
– volume: 8
  start-page: 1599
  issn: 1568-4946
  year: 2008
  ident: c32
  article-title: A new segmentation system for brain MR images based on fuzzy techniques
  publication-title: Appl. Soft Comput.
– volume: 233
  start-page: 93
  issn: 0033-8419
  year: 2004
  ident: c52
  article-title: Tumor volume in pharyngolaryngeal squamous cell carcinoma: Comparison at CT, MR imaging, and FDG PET and validation with surgical specimen
  publication-title: Radiology
– volume: 12
  start-page: 629
  issn: 0162-8828
  year: 1990
  ident: c38
  article-title: Scale-space and edge detection using anisotropic diffusion
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 34
  start-page: 1907
  issn: 1083-4419
  year: 2004
  ident: c30
  article-title: Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure
  publication-title: IEEE Trans. Syst., Man, Cybern., Part B: Cybern.
– volume: 17
  start-page: 873
  issn: 0018-9472
  year: 1987
  ident: c36
  article-title: Convergence theory for fuzzy c-means: Counterexamples and repairs
  publication-title: IEEE Trans. Syst. Man Cybern.
– volume: 2007
  issn: 1687-4188
  year: 2007
  ident: c19
  article-title: Molecular image segmentation based on improved fuzzy clustering
  publication-title: Int. J. Biomed. Imaging
– volume: 3
  start-page: 229
  issn: 0765-0019
  year: 1994
  ident: c47
  article-title: Restauration des images multi-échelles par l’algorithme à trous
  publication-title: Trait. Signal
– volume: 48
  start-page: 68S
  issn: 0161-5505
  year: 2007
  ident: c3
  article-title: PET-based treatment planning in radiotherapy: A new standard?
  publication-title: J. Nucl. Med.
– volume: 33
  start-page: 183-185
  year: 2004
  publication-title: Ann. Acad. Med. Singapore
– volume: 48
  start-page: 89-97
  year: 2001
  publication-title: IEEE Trans. Nucl. Sci.
  doi: 10.1109/23.910837
– volume: 19
  start-page: 309-319
  year: 2009
  publication-title: Digit. Signal Process.
  doi: 10.1016/j.dsp.2007.11.005
– volume: 36
  start-page: 3654-3670
  year: 2009
  publication-title: Med. Phys.
  doi: 10.1118/1.3160108
– volume: 233
  start-page: 93-100
  year: 2004
  publication-title: Radiology
  doi: 10.1148/radiol.2331030660
– volume: 12
  start-page: 629-639
  year: 1990
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/34.56205
– volume: 16
  start-page: 1108-1133
  year: 2009
  publication-title: Acad. Radiol.
  doi: 10.1016/j.acra.2009.02.014
– volume: 11
  start-page: 1105-1114
  year: 2004
  publication-title: Acad. Radiol.
  doi: 10.1016/j.acra.2004.07.012
– volume: 32
  start-page: 685-698
  year: 2008
  publication-title: Comput. Med. Imaging Graph.
  doi: 10.1016/j.compmedimag.2008.08.004
– volume: 35
  start-page: 195-211
  year: 1994
  publication-title: Signal Process.
  doi: 10.1016/0165-1684(94)90211-9
– volume: 147
  start-page: 185-192
  year: 2000
  publication-title: IEEE Proc. Vision Image Signal Process
  doi: 10.1049/ip-vis:20000218
– volume: 21
  start-page: 193-199
  year: 2002
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/42.996338
– volume: 17
  start-page: 873-877
  year: 1987
  publication-title: IEEE Trans. Syst. Man Cybern.
– volume: 13
  start-page: 730-742
  year: 1994
  publication-title: IEEE Eng. Med. Biol. Mag.
  doi: 10.1109/51.334636
– volume: PAMI-2
  start-page: 1-8
  year: 1980
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.1980.4766964
– volume: 34
  start-page: 4223-4235
  year: 2007
  publication-title: Med. Phys.
  doi: 10.1118/1.2791035
– volume: 26
  start-page: 581-590
  year: 1999
  publication-title: Eur. J. Nucl. Med.
  doi: 10.1007/s002590050425
– volume: 69
  start-page: 267-275
  year: 2007
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
  doi: 10.1016/j.ijrobp.2007.04.065
– volume: 37
  start-page: 223-239
  year: 2007
  publication-title: Semin Nucl. Med.
  doi: 10.1053/j.semnuclmed.2007.01.005
– volume: 69
  start-page: 247-250
  year: 2003
  publication-title: Radiother. Oncol.
  doi: 10.1016/S0167-8140(03)00270-6
– volume: 73
  start-page: 456-465
  year: 2009
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
  doi: 10.1016/j.ijrobp.2008.04.019
– volume: 40
  start-page: 2464-2482
  year: 1992
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/78.157290
– volume: 16
  start-page: 129-147
  year: 1999
  publication-title: Artif. Intell. Med.
  doi: 10.1016/S0933-3657(98)00069-4
– volume: 68
  start-page: 771-778
  year: 2007
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
  doi: 10.1016/j.ijrobp.2006.12.067
– volume: 32
  start-page: 245-260
  year: 2006
  publication-title: Cancer Treat Rev.
  doi: 10.1016/j.ctrv.2006.02.002
– volume: 18
  start-page: 737-752
  year: 1999
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/42.802752
– volume: 34
  start-page: 4738-4749
  year: 2007
  publication-title: Med. Phys.
  doi: 10.1118/1.2799886
– volume: 3
  start-page: 32-57
  year: 1973
  publication-title: IEEE Trans. Syst. Man Cybern.
  doi: 10.1080/01969727308546046
– volume: 30
  start-page: 9-15
  year: 2006
  publication-title: Comput. Med. Imaging Graph.
  doi: 10.1016/j.compmedimag.2005.10.001
– volume: 36
  start-page: 182-193
  year: 2009
  publication-title: Eur. J. Nucl. Med. Mol. Imaging
  doi: 10.1007/s00259-008-0943-6
– volume: 35
  start-page: 3331-3342
  year: 2008
  publication-title: Med. Phys.
  doi: 10.1118/1.2938518
– volume: 34
  start-page: 1907-1916
  year: 2004
  publication-title: IEEE Trans. Syst., Man, Cybern., Part B: Cybern.
  doi: 10.1109/TSMCB.2004.831165
– volume: 22
  start-page: 1063-1075
  year: 2003
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/TMI.2003.816956
– volume: 2007
  year: 2007
  publication-title: Int. J. Biomed. Imaging
  doi: 10.1155/2007/25182
– volume: 20
  start-page: 31-41
  year: 1996
  publication-title: Comput. Med. Imaging Graph.
  doi: 10.1016/0895-6111(96)00025-0
– volume: 47
  start-page: 551-560
  year: 2000
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
  doi: 10.1016/S0360-3016(00)00467-3
– volume: 48
  start-page: 68S-77S
  year: 2007
  publication-title: J. Nucl. Med.
– volume: 354
  start-page: 496-507
  year: 2006
  publication-title: N. Engl. J. Med.
  doi: 10.1056/NEJMra050276
– volume: 91
  start-page: 1649-1669
  year: 2003
  publication-title: Proc. IEEE
  doi: 10.1109/JPROC.2003.817883
– volume: 28
  start-page: 881-893
  year: 2009
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/TMI.2008.2012036
– volume: 13
  start-page: 63-72
  year: 2006
  publication-title: Acad. Radiol.
  doi: 10.1016/j.acra.2005.08.035
– volume: 3
  start-page: 229-243
  year: 1994
  publication-title: Trait. Signal
– volume: 84
  start-page: 285-297
  year: 2001
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1006/cviu.2001.0951
– volume: 34
  start-page: 1427-1438
  year: 2007
  publication-title: Eur. J. Nucl. Med. Mol. Imaging
  doi: 10.1007/s00259-006-0363-4
– volume: PAMI-8
  start-page: 679-698
  year: 1986
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.1986.4767851
– volume: 57
  start-page: 125-134
  year: 2007
  publication-title: Lung Cancer
  doi: 10.1016/j.lungcan.2007.03.020
– volume: 48
  start-page: 932-945
  year: 2007
  publication-title: J. Nucl. Med.
  doi: 10.2967/jnumed.106.035774
– volume: 53
  start-page: 4213-4230
  year: 2008
  publication-title: Phys. Med. Biol.
  doi: 10.1088/0031-9155/53/16/001
– volume: 48
  start-page: 78S-88S
  year: 2007
  publication-title: J. Nucl. Med.
– volume: 8
  start-page: 1599-1606
  year: 2008
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2007.10.025
– volume: 34
  start-page: 722-736
  year: 2007
  publication-title: Med. Phys.
  doi: 10.1118/1.2432404
– publication-title: Eur. J. Nucl. Med. Mol. Imaging
– volume: 47
  start-page: 1143-1160
  year: 2002
  publication-title: Phys. Med. Biol.
  doi: 10.1088/0031-9155/47/7/310
– volume: 50
  start-page: 27P
  year: 2009
  publication-title: J. Nucl. Med.
– volume: 69
  start-page: 237-245
  year: 2003
  publication-title: Radiother. Oncol.
  doi: 10.1016/j.radonc.2003.10.009
– volume: 34
  start-page: 4738
  year: 2007
  end-page: 4749
  article-title: Concurrent multimodality image segmentation by active contours for radiotherapy treatment planning
  publication-title: Med. Phys.
– volume: 2007
  year: 2007
  article-title: Molecular image segmentation based on improved fuzzy clustering
  publication-title: Int. J. Biomed. Imaging
– volume: 32
  start-page: 245
  year: 2006
  end-page: 260
  article-title: The current status of FDG‐PET in tumour volume definition in radiotherapy treatment planning
  publication-title: Cancer Treat Rev.
– volume: 16
  start-page: 1108
  year: 2009
  end-page: 1133
  article-title: Molecular PET/CT imaging‐guided radiation therapy treatment planning
  publication-title: Acad. Radiol.
– article-title: PET‐guided delineation of radiation therapy treatment volumes: A survey of image segmentation techniques
  publication-title: Eur. J. Nucl. Med. Mol. Imaging
– volume: 84
  start-page: 285
  year: 2001
  end-page: 297
  article-title: “Spatial models for fuzzy clustering
  publication-title: Comput. Vis. Image Underst.
– volume: 21
  start-page: 193
  year: 2002
  end-page: 199
  article-title: A modified fuzzy c‐means algorithm for bias field estimation and segmentation of MRI data
  publication-title: IEEE Trans. Med. Imaging
– volume: 34
  start-page: 1427
  year: 2007
  end-page: 1438
  article-title: A gradient‐based method for segmenting FDG‐PET images: Methodology and validation
  publication-title: Eur. J. Nucl. Med. Mol. Imaging
– volume: 16
  start-page: 129
  year: 1999
  end-page: 147
  article-title: A fuzzy clustering based segmentation system as support to diagnosis in medical imaging
  publication-title: Artif. Intell. Med.
– volume: 2
  start-page: 645
  year: 1998
  end-page: 648
  article-title: Clustering via the Bayesian information criterion with applications in speech recognition
– volume: 354
  start-page: 496
  year: 2006
  end-page: 507
  article-title: Positron‐emission tomography and assessment of cancer therapy
  publication-title: N. Engl. J. Med.
– year: 1998
– volume: 73
  start-page: 456
  year: 2009
  end-page: 465
  article-title: Tumor delineation based on time‐activity curve differences assessed with dynamic fluorodeoxyglucose positron emission tomography‐computed tomography in rectal cancer patients
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
– volume: 34
  start-page: 722
  year: 2007
  end-page: 736
  article-title: Fully automated segmentation of oncological PET volumes using a combined multiscale and statistical model
  publication-title: Med. Phys.
– volume: 40
  start-page: 2464
  year: 1992
  end-page: 2482
  article-title: The discrete wavelet transform: Wedding the a trous and Mallat algorithms
  publication-title: IEEE Trans. Signal Process.
– volume: 37
  start-page: 223
  year: 2007
  end-page: 239
  article-title: Novel quantitative techniques for assessing regional and global function and structure based on modern imaging modalities: Implications for normal variation, aging and diseased states
  publication-title: Semin Nucl. Med.
– volume: 233
  start-page: 93
  year: 2004
  end-page: 100
  article-title: Tumor volume in pharyngolaryngeal squamous cell carcinoma: Comparison at CT, MR imaging, and FDG PET and validation with surgical specimen
  publication-title: Radiology
– volume: 33
  start-page: 183
  year: 2004
  end-page: 185
  article-title: Semi‐quantitative measurements of normal organs with variable metabolic activity on FDG PET imaging
  publication-title: Ann. Acad. Med. Singapore
– volume: 20
  start-page: 31
  year: 1996
  end-page: 41
  article-title: Delineation and quantitation of brain lesions by fuzzy clustering in positron emission tomography
  publication-title: Comput. Med. Imaging Graph.
– volume: 69
  start-page: 267
  year: 2007
  end-page: 275
  article-title: Feasibility of pathology‐correlated lung imaging for accurate target definition of lung tumors
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
– volume: 36
  start-page: 3654
  year: 2009
  end-page: 3670
  article-title: Four‐dimensional (4D) image reconstruction strategies in dynamic PET: Beyond conventional independent frame reconstruction
  publication-title: Med. Phys.
– volume: 22
  start-page: 1063
  year: 2003
  end-page: 1075
  article-title: An adaptive spatial fuzzy clustering algorithm for 3‐D MR image segmentation
  publication-title: IEEE Trans. Med. Imaging
– volume: 3
  start-page: 32
  year: 1973
  end-page: 57
  article-title: A fuzzy relative of the ISODATA process and its use in detecting compact well‐separated clusters
  publication-title: IEEE Trans. Syst. Man Cybern.
– volume: 35
  start-page: 195
  year: 1994
  end-page: 211
  article-title: Filtering and deconvolution by the wavelet transform
  publication-title: Signal Process.
– volume: 53
  start-page: 4213
  year: 2008
  end-page: 4230
  article-title: Assessment of tumour response with 18F‐fluorodeoxyglucose positron emission tomography using 3‐dimensional measures compared to SUVmax—A phantom study
  publication-title: Phys. Med. Biol.
– volume: 19
  start-page: 309
  year: 2009
  end-page: 319
  article-title: Novel modified fuzzy c‐means algorithm with applications
  publication-title: Digit. Signal Process.
– start-page: 286
  year: 1989
  end-page: 297
– volume: 11
  start-page: 1105
  year: 2004
  end-page: 1114
  article-title: Post‐reconstruction filtering of positron emission tomography whole‐body emission images and attenuation maps using nonlinear diffusion filtering
  publication-title: Acad. Radiol.
– volume: PAMI‐2
  start-page: 1
  year: 1980
  end-page: 8
  article-title: A convergence theorem for the fuzzy ISODATA clustering algorithms
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 13
  start-page: 63
  year: 2006
  end-page: 72
  article-title: A fuzzy C‐means (FCM)‐based approach for computerized segmentation of breast lesions in dynamic contrast‐enhanced MR images
  publication-title: Acad. Radiol.
– volume: 28
  start-page: 881
  year: 2009
  end-page: 893
  article-title: A fuzzy locally adaptive Bayesian segmentation approach for volume determination in PET
  publication-title: IEEE Trans. Med. Imaging
– volume: 47
  start-page: 551
  year: 2000
  end-page: 560
  article-title: Towards multidimensional radiotherapy (MD‐CRT): Biological imaging and biological conformality
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
– volume: 34
  start-page: 1907
  year: 2004
  end-page: 1916
  article-title: Robust image segmentation using FCM with spatial constraints based on new kernel‐induced distance measure
  publication-title: IEEE Trans. Syst., Man, Cybern., Part B: Cybern.
– volume: 50
  start-page: 27P
  year: 2009
  article-title: Comparative methods for 18F‐FDG PET‐based delineation of target volumes in non‐small‐cell lung cancer [abstract]
  publication-title: J. Nucl. Med.
– volume: 4
  start-page: 2627
  year: 2003
  end-page: 2629
  article-title: Automation segmentation of PET image for brain tumors
– volume: 35
  start-page: 3331
  year: 2008
  end-page: 3342
  article-title: The development and testing of a digital PET phantom for the evaluation of tumor volume segmentation techniques
  publication-title: Med. Phys.
– volume: 47
  start-page: 1143
  year: 2002
  end-page: 1160
  article-title: Fuzzy clustering‐based segmented attenuation correction in whole‐body PET imaging
  publication-title: Phys. Med. Biol.
– year: 2007
– volume: 68
  start-page: 771
  year: 2007
  end-page: 778
  article-title: PET‐CT‐based auto‐contouring in non‐small‐cell lung cancer correlates with pathology and reduces interobserver variability in the delineation of the primary tumor and involved nodal volumes
  publication-title: Int. J. Radiat. Oncol., Biol., Phys.
– volume: 6
  start-page: 4242
  year: 2007
  end-page: 4245
  article-title: Use of anatomical priors in the segmentation of PET lung tumor images
– volume: 34
  start-page: 4223
  year: 2007
  end-page: 4235
  article-title: A Gaussian mixture model for definition of lung tumor volumes in positron emission tomography
  publication-title: Med. Phys.
– volume: 3
  start-page: 229
  year: 1994
  end-page: 243
  article-title: Restauration des images multi‐échelles par l'algorithme à trous
  publication-title: Trait. Signal
– volume: 4
  start-page: 3789
  year: 2005
  end-page: 3792
  article-title: An automated volumetric segmentation system combining multiscale and statistical reasoning
– volume: 13
  start-page: 730
  year: 1994
  end-page: 742
  article-title: MRI segmentation using fuzzy clustering techniques
  publication-title: IEEE Eng. Med. Biol. Mag.
– volume: 17
  start-page: 873
  year: 1987
  end-page: 877
  article-title: Convergence theory for fuzzy c‐means: Counterexamples and repairs
  publication-title: IEEE Trans. Syst. Man Cybern.
– volume: 48
  start-page: 89
  year: 2001
  end-page: 97
  article-title: Modeling respiratory mechanics in the MCAT and spline‐based MCAT phantoms
  publication-title: IEEE Trans. Nucl. Sci.
– volume: 69
  start-page: 247
  year: 2003
  end-page: 250
  article-title: Tri‐dimensional automatic segmentation of PET volumes based on measured source‐to‐background ratios: Influence of reconstruction algorithms
  publication-title: Radiother. Oncol.
– volume: 18
  start-page: 737
  year: 1999
  end-page: 752
  article-title: Adaptive fuzzy segmentation of magnetic resonance images
  publication-title: IEEE Trans. Med. Imaging
– volume: 147
  start-page: 185
  year: 2000
  end-page: 192
  article-title: Fuzzy image clustering incorporating spatial continuity
  publication-title: IEEE Proc. Vision Image Signal Process
– volume: 8
  start-page: 1599
  year: 2008
  end-page: 1606
  article-title: A new segmentation system for brain MR images based on fuzzy techniques
  publication-title: Appl. Soft Comput.
– volume: 48
  start-page: 78S
  year: 2007
  end-page: 88S
  article-title: Improvements in cancer staging with PET/CT: Literature‐based evidence as of September 2006
  publication-title: J. Nucl. Med.
– volume: 91
  start-page: 1649
  year: 2003
  end-page: 1669
  article-title: Fuzzy connectedness and image segmentation
  publication-title: Proc. IEEE
– volume: 30
  start-page: 9
  year: 2006
  end-page: 15
  article-title: Fuzzy c‐means clustering with spatial information for image segmentation
  publication-title: Comput. Med. Imaging Graph.
– volume: 69
  start-page: 237
  year: 2003
  end-page: 245
  article-title: Evaluation of a multimodality image (CT, MRI and PET) coregistration procedure on phantom and head and neck cancer patients: Accuracy, reproducibility and consistency
  publication-title: Radiother. Oncol.
– volume: 32
  start-page: 685
  year: 2008
  end-page: 698
  article-title: A modified FCM algorithm for MRI brain image segmentation using both local and non‐local spatial constraints
  publication-title: Comput. Med. Imaging Graph.
– volume: 48
  start-page: 68S
  year: 2007
  end-page: 77S
  article-title: PET‐based treatment planning in radiotherapy: A new standard?
  publication-title: J. Nucl. Med.
– volume: 12
  start-page: 629
  year: 1990
  end-page: 639
  article-title: Scale‐space and edge detection using anisotropic diffusion
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 57
  start-page: 125
  year: 2007
  end-page: 134
  article-title: Current status of PET/CT for tumour volume definition in radiotherapy treatment planning for non‐small cell lung cancer (NSCLC)
  publication-title: Lung Cancer
– volume: 48
  start-page: 932
  year: 2007
  end-page: 945
  article-title: Partial‐volume effect in PET tumor imaging
  publication-title: J. Nucl. Med.
– volume: 36
  start-page: 182
  year: 2009
  end-page: 193
  article-title: Assessment of various strategies for 18F‐FET PET‐guided delineation of target volumes in high‐grade glioma patients
  publication-title: Eur. J. Nucl. Med. Mol. Imaging
– volume: PAMI‐8
  start-page: 679
  year: 1986
  end-page: 698
  article-title: A computational approach to edge detection
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 26
  start-page: 581
  year: 1999
  end-page: 590
  article-title: Automatic segmentation of dynamic neuroreceptor single‐photon emission tomography images using fuzzy clustering
  publication-title: Eur. J. Nucl. Med.
– start-page: 2627
  year: 2003
  ident: e_1_2_7_26_1
– ident: e_1_2_7_17_1
  doi: 10.1088/0031-9155/47/7/310
– ident: e_1_2_7_38_1
  doi: 10.1109/TPAMI.1980.4766964
– ident: e_1_2_7_25_1
  doi: 10.1016/0895-6111(96)00025-0
– ident: e_1_2_7_61_1
  doi: 10.1016/j.ijrobp.2008.04.019
– volume: 3
  start-page: 229
  year: 1994
  ident: e_1_2_7_48_1
  article-title: Restauration des images multi‐échelles par l'algorithme à trous
  publication-title: Trait. Signal
– ident: e_1_2_7_20_1
  doi: 10.1155/2007/25182
– ident: e_1_2_7_58_1
  doi: 10.1088/0031-9155/53/16/001
– ident: e_1_2_7_33_1
  doi: 10.1016/j.asoc.2007.10.025
– start-page: 4242
  year: 2007
  ident: e_1_2_7_27_1
– ident: e_1_2_7_44_1
  doi: 10.1109/78.157290
– ident: e_1_2_7_53_1
  doi: 10.1148/radiol.2331030660
– ident: e_1_2_7_63_1
  doi: 10.1118/1.2938518
– ident: e_1_2_7_64_1
  doi: 10.1016/j.ijrobp.2007.04.065
– volume-title: Anisotropic Diffusion in Image Processing
  year: 1998
  ident: e_1_2_7_40_1
– start-page: 3789
  year: 2005
  ident: e_1_2_7_49_1
– volume: 48
  start-page: 78S
  year: 2007
  ident: e_1_2_7_2_1
  article-title: Improvements in cancer staging with PET/CT: Literature‐based evidence as of September 2006
  publication-title: J. Nucl. Med.
– ident: e_1_2_7_14_1
  doi: 10.1053/j.semnuclmed.2007.01.005
– volume-title: Bayesian Statistical Modelling
  year: 2007
  ident: e_1_2_7_34_1
– ident: e_1_2_7_22_1
  doi: 10.1007/s002590050425
– ident: e_1_2_7_5_1
  article-title: PET‐guided delineation of radiation therapy treatment volumes: A survey of image segmentation techniques
  publication-title: Eur. J. Nucl. Med. Mol. Imaging
– ident: e_1_2_7_24_1
  doi: 10.1109/51.334636
– start-page: 645
  year: 1998
  ident: e_1_2_7_35_1
– ident: e_1_2_7_29_1
  doi: 10.1006/cviu.2001.0951
– ident: e_1_2_7_41_1
  doi: 10.1109/TPAMI.1986.4767851
– ident: e_1_2_7_15_1
  doi: 10.1016/S0933-3657(98)00069-4
– volume: 33
  start-page: 183
  year: 2004
  ident: e_1_2_7_51_1
  article-title: Semi‐quantitative measurements of normal organs with variable metabolic activity on FDG PET imaging
  publication-title: Ann. Acad. Med. Singapore
  doi: 10.47102/annals-acadmedsg.V33N2p183
– ident: e_1_2_7_21_1
  doi: 10.1016/j.compmedimag.2008.08.004
– volume: 48
  start-page: 68S
  year: 2007
  ident: e_1_2_7_4_1
  article-title: PET‐based treatment planning in radiotherapy: A new standard?
  publication-title: J. Nucl. Med.
– ident: e_1_2_7_43_1
  doi: 10.1118/1.3160108
– ident: e_1_2_7_8_1
  doi: 10.1016/j.ctrv.2006.02.002
– ident: e_1_2_7_6_1
  doi: 10.1056/NEJMra050276
– ident: e_1_2_7_10_1
  doi: 10.1118/1.2432404
– ident: e_1_2_7_62_1
  doi: 10.1118/1.2791035
– ident: e_1_2_7_59_1
  doi: 10.1016/S0167-8140(03)00270-6
– ident: e_1_2_7_9_1
  doi: 10.1007/s00259-008-0943-6
– ident: e_1_2_7_32_1
  doi: 10.1016/j.dsp.2007.11.005
– ident: e_1_2_7_42_1
  doi: 10.1016/j.acra.2004.07.012
– start-page: 286
  volume-title: Wavelets, Time‐Frequency Methods and Phase Space
  year: 1989
  ident: e_1_2_7_46_1
  doi: 10.1007/978-3-642-97177-8_28
– ident: e_1_2_7_18_1
  doi: 10.1109/TMI.2003.816956
– ident: e_1_2_7_12_1
  doi: 10.1109/TMI.2008.2012036
– ident: e_1_2_7_55_1
  doi: 10.1016/j.radonc.2003.10.009
– ident: e_1_2_7_7_1
  doi: 10.1016/j.lungcan.2007.03.020
– ident: e_1_2_7_19_1
  doi: 10.1016/j.compmedimag.2005.10.001
– ident: e_1_2_7_50_1
  doi: 10.1109/23.910837
– ident: e_1_2_7_37_1
  doi: 10.1109/TSMC.1987.6499296
– ident: e_1_2_7_45_1
  doi: 10.1016/0165-1684(94)90211-9
– ident: e_1_2_7_31_1
  doi: 10.1109/TSMCB.2004.831165
– ident: e_1_2_7_13_1
  doi: 10.2967/jnumed.106.035774
– ident: e_1_2_7_16_1
  doi: 10.1109/42.802752
– ident: e_1_2_7_30_1
  doi: 10.1109/42.996338
– ident: e_1_2_7_28_1
  doi: 10.1049/ip-vis:20000218
– ident: e_1_2_7_54_1
  doi: 10.1007/s00259-006-0363-4
– ident: e_1_2_7_60_1
  doi: 10.1109/JPROC.2003.817883
– ident: e_1_2_7_57_1
  doi: 10.1016/j.acra.2009.02.014
– ident: e_1_2_7_39_1
  doi: 10.1109/34.56205
– volume: 50
  start-page: 27P
  year: 2009
  ident: e_1_2_7_56_1
  article-title: Comparative methods for 18F‐FDG PET‐based delineation of target volumes in non‐small‐cell lung cancer [abstract]
  publication-title: J. Nucl. Med.
– ident: e_1_2_7_23_1
  doi: 10.1016/j.acra.2005.08.035
– ident: e_1_2_7_3_1
  doi: 10.1016/S0360-3016(00)00467-3
– volume: 3
  start-page: 32
  year: 1973
  ident: e_1_2_7_36_1
  article-title: A fuzzy relative of the ISODATA process and its use in detecting compact well‐separated clusters
  publication-title: IEEE Trans. Syst. Man Cybern.
– ident: e_1_2_7_52_1
  doi: 10.1016/j.ijrobp.2006.12.067
– ident: e_1_2_7_47_1
  doi: 10.1017/CBO9780511564352
– ident: e_1_2_7_11_1
  doi: 10.1118/1.2799886
SSID ssj0006350
Score 2.3944771
Snippet Purpose: Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This...
Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty...
SourceID proquest
pubmed
crossref
wiley
scitation
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1309
SubjectTerms Algorithms
anisotropic diffusion filtering
Artificial Intelligence
cancer
Carcinoma, Non-Small-Cell Lung - diagnostic imaging
cellular biophysics
Computed tomography
Diffusion
discrete wavelet transforms
FCM segmentation
Fuzzy Logic
Humans
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
image segmentation
Integral transforms
intensity heterogeneity
lung
Lung Neoplasms - diagnostic imaging
Medical image noise
medical image processing
Medical image segmentation
Medical image spatial resolution
Medical imaging
Neural networks, fuzzy logic, artificial intelligence
Pattern Recognition, Automated - methods
phantoms
Phantoms, Imaging
positron emission tomography
positron emission tomography (PET)
Positron-Emission Tomography - instrumentation
Positron-Emission Tomography - methods
Reproducibility of Results
Segmentation
Sensitivity and Specificity
tumours
Wavelet transform
Wavelets
à trous wavelet transform
Title A novel fuzzy C-means algorithm for unsupervised heterogeneous tumor quantification in PET
URI http://dx.doi.org/10.1118/1.3301610
https://onlinelibrary.wiley.com/doi/abs/10.1118%2F1.3301610
https://www.ncbi.nlm.nih.gov/pubmed/20384268
https://www.proquest.com/docview/733880695
Volume 37
WOSCitedRecordID wos000275160300038&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 2473-4209
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0006350
  issn: 0094-2405
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB6VLc8Dj_IKj8oCVHEJbOykdsRptXTFgVYr1Ep7QLIc26Er7SbLZrMSPfET-I38EsZxNqiioEqcchk7ief1TWYyA_BKc5MzBOKhTbgJ48joMBMJqrsRNNu3CRWZHzbBj47EZJKOt-Dd5l8Y3x-i--DmNKOx107BVdZOIYlc4Xr0BkNxxCsYr29TlNu4B9vvP41OPnaGGH2p_wMljV0SIWkbC-Hyt93i8-7oD4x5C26gJ_JJ8fPwtfE_ozv_9eR34XYLO8nAy8k92LLFDlw_bBPrO3CtqQTV1X34PCBFubYzktdnZ9_I8Of3H3OL_oyo2ZdyOV2dzgniXFIXVb1wdqayhpy6mpoSRdGWdUVW9RwJvtbK1yE1b0WmBRkfHD-Ak9HB8fBD2I5gCHWC3i2MNLNZjmZAay1yjdGZMFGaK2WZRWBJlUsEKmYFZ4IalauYcoNcT3Wuo8wY9hB6RVnYx0AijdF2joBGM4RglqsspjGPNWVpRnW_H8DrDSfk5sjdmIyZ9HGKkJFszy2AFx3pwjfluIiIbNgpUWVcHkQ1xyA5cx1w9tMkgEeezd0utM8EYhYRwMuO7_-6Bb8E1UA2bJMN2-RQOqZduP-6XP5eJRcmD2CvkaO_7y0Px-7y5LKET-GmL39wRXTPoLda1vY5XNXr1bRa7sIVPhG7rRr9AkPkG3o
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3db9MwED9NHTB44GMMCJ8WIMRLoImTxZF4qcqqIdqqQp20h0mWYztbpTYpTVOJPe1P2N-4v2TnOA2aGGgST3k5O4nv63e-8xngvYxUShGIuzqMlBt4SroJC1HdFfOTXR36LLGXTUTDITs8jEcb8GV9Fsb2h2g23IxmVPbaKLjZkK613FSue58wFkfAggH7ZoBiFLZg8-uP3kG_scToTO0RlDgwWYSw7iyEwz83g6_6oz9A5j3YQldks-JX8WvlgHoP_u_TH8L9GniSjpWUR7Chs224M6hT69twu6oFlcVjOOqQLF_pKUnL09NfpHtxdj7T6NGImB7ni8nyZEYQ6ZIyK8q5sTSFVuTEVNXkKIw6LwuyLGdI8LMUthKp-i0yychob7wDB729cXffrS9hcGWI_s31JNVJioZASslSifEZU16cCqGpRmjpC5MKFFSziDJfiVQEfqSQ77FMpZcoRZ9AK8sz_QyIJzHeThHSSIogTEciCfwgCqRP48SX7bYDH9es4Os1NxdlTLmNVBj3eL1uDrxtSOe2Lcd1RGTNT45KYzIholoGHlHTA2c3Dh14avnczOK3KUPUwhx41zD-X6-IbkDV4RXbeMU23uWGadfOv8oXv0fxuUod-FAJ0t_n5oOReTy_KeEb2NofD_q8_234_QXctcUQpqTuJbSWi1K_gltytZwUi9e1Nl0CjLYegg
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9NAEB5VLZRy4FEeNc8VIMTFEHvteC1xidJGINooQq3UQ6XVeh80UmKncRypPfET-I38Ema9jlFFQZU4-TK7tveb2fnGM54FeCMTZSgScV_HifKjQEk_YzGau2Jh1tVxyDJ32EQyHLLj43S0Bh9X_8K4_hDtBzdrGfV-bQ1cz5RprNxWrgfvMRZHwoIB-0YUp100y43dr4Oj_XYnRmfqfkFJI5tFiJvOQjj8Qzv4sj_6g2TehlvoilxW_DJ_rR3Q4O7_Pfo9uNMQT9JzmnIf1nS-DZsHTWp9G27WtaCyfAAnPZIXSz0hprq4OCf9n99_TDV6NCIm34r5eHE6Jch0SZWX1czuNKVW5NRW1RSojLqoSrKopihwVglXiVS_FhnnZLR3-BCOBnuH_U9-cwiDL2P0b34gqc4MbgRSSmYkxmdMBakRQlON1DIUNhUoqGYJZaESRkRhohD3VBoZZErRR7CeF7neARJIjLcNUhpJkYTpRGRRGCWRDGmahbLT8eDdCgq-WnN7UMaEu0iF8YA36-bBq1Z05tpyXCVEVnhyNBqbCRH1MvCE2h443TT24LHDuZ0l7FCGrIV58LoF_l-3SK4h1eM1bLyGjfe5Be3K-ZfF_Pcojjrjwdtakf4-Nz8Y2cuT6wq-hM3R7oDvfx5-eQpbrhbCVtQ9g_XFvNLP4YZcLsbl_EVjTL8A6h4d_Q
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+novel+fuzzy+C-means+algorithm+for+unsupervised+heterogeneous+tumor+quantification+in+PET&rft.jtitle=Medical+physics+%28Lancaster%29&rft.au=Belhassen%2C+Saoussen&rft.au=Zaidi%2C+Habib&rft.date=2010-03-01&rft.issn=0094-2405&rft.eissn=2473-4209&rft.volume=37&rft.issue=3&rft.spage=1309&rft.epage=1324&rft_id=info:doi/10.1118%2F1.3301610
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0094-2405&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0094-2405&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0094-2405&client=summon