Adaptive Feature Medical Segmentation Network: an adaptable deep learning paradigm for high-performance 3D brain lesion segmentation in medical imaging
In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancemen...
Gespeichert in:
| Veröffentlicht in: | Frontiers in neuroscience Jg. 18; S. 1363930 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Switzerland
Frontiers Media S.A
2024
|
| Schlagworte: | |
| ISSN: | 1662-453X, 1662-4548, 1662-453X |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancement or sacrifice fine details for computational efficiency. Therefore, balancing performance and precision in compute-intensive medical imaging remains a hot research topic.
We introduce a novel encoder-decoder network architecture named the Adaptive Feature Medical Segmentation Network (AFMS-Net) with two encoder variants: the Single Adaptive Encoder Block (SAEB) and the Dual Adaptive Encoder Block (DAEB). A squeeze-and-excite mechanism is employed in SAEB to identify significant data while disregarding peripheral details. This approach is best suited for scenarios requiring quick and efficient segmentation, with an emphasis on identifying key lesion areas. In contrast, the DAEB utilizes an advanced channel spatial attention strategy for fine-grained delineation and multiple-class classifications. Additionally, both architectures incorporate a Segmentation Path (SegPath) module between the encoder and decoder, refining segmentation, enhancing feature extraction, and improving model performance and stability.
AFMS-Net demonstrates exceptional performance across several notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022. Its design aims to construct a lightweight architecture capable of handling complex segmentation challenges with high precision.
The proposed AFMS-Net addresses the critical balance issue between performance and computational efficiency in the segmentation of brain lesions. By introducing two tailored encoder variants, the network adapts to varying requirements of speed and feature. This approach not only advances the state-of-the-art in lesion segmentation but also provides a scalable framework for future research in medical image processing. |
|---|---|
| AbstractList | In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancement or sacrifice fine details for computational efficiency. Therefore, balancing performance and precision in compute-intensive medical imaging remains a hot research topic.IntroductionIn neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancement or sacrifice fine details for computational efficiency. Therefore, balancing performance and precision in compute-intensive medical imaging remains a hot research topic.We introduce a novel encoder-decoder network architecture named the Adaptive Feature Medical Segmentation Network (AFMS-Net) with two encoder variants: the Single Adaptive Encoder Block (SAEB) and the Dual Adaptive Encoder Block (DAEB). A squeeze-and-excite mechanism is employed in SAEB to identify significant data while disregarding peripheral details. This approach is best suited for scenarios requiring quick and efficient segmentation, with an emphasis on identifying key lesion areas. In contrast, the DAEB utilizes an advanced channel spatial attention strategy for fine-grained delineation and multiple-class classifications. Additionally, both architectures incorporate a Segmentation Path (SegPath) module between the encoder and decoder, refining segmentation, enhancing feature extraction, and improving model performance and stability.MethodsWe introduce a novel encoder-decoder network architecture named the Adaptive Feature Medical Segmentation Network (AFMS-Net) with two encoder variants: the Single Adaptive Encoder Block (SAEB) and the Dual Adaptive Encoder Block (DAEB). A squeeze-and-excite mechanism is employed in SAEB to identify significant data while disregarding peripheral details. This approach is best suited for scenarios requiring quick and efficient segmentation, with an emphasis on identifying key lesion areas. In contrast, the DAEB utilizes an advanced channel spatial attention strategy for fine-grained delineation and multiple-class classifications. Additionally, both architectures incorporate a Segmentation Path (SegPath) module between the encoder and decoder, refining segmentation, enhancing feature extraction, and improving model performance and stability.AFMS-Net demonstrates exceptional performance across several notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022. Its design aims to construct a lightweight architecture capable of handling complex segmentation challenges with high precision.ResultsAFMS-Net demonstrates exceptional performance across several notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022. Its design aims to construct a lightweight architecture capable of handling complex segmentation challenges with high precision.The proposed AFMS-Net addresses the critical balance issue between performance and computational efficiency in the segmentation of brain lesions. By introducing two tailored encoder variants, the network adapts to varying requirements of speed and feature. This approach not only advances the state-of-the-art in lesion segmentation but also provides a scalable framework for future research in medical image processing.DiscussionThe proposed AFMS-Net addresses the critical balance issue between performance and computational efficiency in the segmentation of brain lesions. By introducing two tailored encoder variants, the network adapts to varying requirements of speed and feature. This approach not only advances the state-of-the-art in lesion segmentation but also provides a scalable framework for future research in medical image processing. In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancement or sacrifice fine details for computational efficiency. Therefore, balancing performance and precision in compute-intensive medical imaging remains a hot research topic. We introduce a novel encoder-decoder network architecture named the Adaptive Feature Medical Segmentation Network (AFMS-Net) with two encoder variants: the Single Adaptive Encoder Block (SAEB) and the Dual Adaptive Encoder Block (DAEB). A squeeze-and-excite mechanism is employed in SAEB to identify significant data while disregarding peripheral details. This approach is best suited for scenarios requiring quick and efficient segmentation, with an emphasis on identifying key lesion areas. In contrast, the DAEB utilizes an advanced channel spatial attention strategy for fine-grained delineation and multiple-class classifications. Additionally, both architectures incorporate a Segmentation Path (SegPath) module between the encoder and decoder, refining segmentation, enhancing feature extraction, and improving model performance and stability. AFMS-Net demonstrates exceptional performance across several notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022. Its design aims to construct a lightweight architecture capable of handling complex segmentation challenges with high precision. The proposed AFMS-Net addresses the critical balance issue between performance and computational efficiency in the segmentation of brain lesions. By introducing two tailored encoder variants, the network adapts to varying requirements of speed and feature. This approach not only advances the state-of-the-art in lesion segmentation but also provides a scalable framework for future research in medical image processing. IntroductionIn neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancement or sacrifice fine details for computational efficiency. Therefore, balancing performance and precision in compute-intensive medical imaging remains a hot research topic.MethodsWe introduce a novel encoder-decoder network architecture named the Adaptive Feature Medical Segmentation Network (AFMS-Net) with two encoder variants: the Single Adaptive Encoder Block (SAEB) and the Dual Adaptive Encoder Block (DAEB). A squeeze-and-excite mechanism is employed in SAEB to identify significant data while disregarding peripheral details. This approach is best suited for scenarios requiring quick and efficient segmentation, with an emphasis on identifying key lesion areas. In contrast, the DAEB utilizes an advanced channel spatial attention strategy for fine-grained delineation and multiple-class classifications. Additionally, both architectures incorporate a Segmentation Path (SegPath) module between the encoder and decoder, refining segmentation, enhancing feature extraction, and improving model performance and stability.ResultsAFMS-Net demonstrates exceptional performance across several notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022. Its design aims to construct a lightweight architecture capable of handling complex segmentation challenges with high precision.DiscussionThe proposed AFMS-Net addresses the critical balance issue between performance and computational efficiency in the segmentation of brain lesions. By introducing two tailored encoder variants, the network adapts to varying requirements of speed and feature. This approach not only advances the state-of-the-art in lesion segmentation but also provides a scalable framework for future research in medical image processing. |
| Author | Hassan, Haseeb Miao, Xiaoqiang Huang, Bingding Zeng, Xueqiang Kang, Yan Zaman, Asim Khan, Rashid Cao, Anbo Yang, Yingjian Guo, Yingwei Lu, Jiaxi Yang, Huihui |
| Author_xml | – sequence: 1 givenname: Asim surname: Zaman fullname: Zaman, Asim – sequence: 2 givenname: Haseeb surname: Hassan fullname: Hassan, Haseeb – sequence: 3 givenname: Xueqiang surname: Zeng fullname: Zeng, Xueqiang – sequence: 4 givenname: Rashid surname: Khan fullname: Khan, Rashid – sequence: 5 givenname: Jiaxi surname: Lu fullname: Lu, Jiaxi – sequence: 6 givenname: Huihui surname: Yang fullname: Yang, Huihui – sequence: 7 givenname: Xiaoqiang surname: Miao fullname: Miao, Xiaoqiang – sequence: 8 givenname: Anbo surname: Cao fullname: Cao, Anbo – sequence: 9 givenname: Yingjian surname: Yang fullname: Yang, Yingjian – sequence: 10 givenname: Bingding surname: Huang fullname: Huang, Bingding – sequence: 11 givenname: Yingwei surname: Guo fullname: Guo, Yingwei – sequence: 12 givenname: Yan surname: Kang fullname: Kang, Yan |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38680446$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9Uctu1DAUtVARfcAPsEBespnBiR3HYVe1tFQqsAAkdta1fZ26JE6wMyC-pL-LpzNUFQtWvr46D_ucY3IQp4iEvKzYmnPVvfExxLyuWS3WFZe84-wJOaqkrFei4d8OHs2H5DjnW8ZkrUT9jBxyJRUTQh6Ru1MH8xJ-Ir1AWDYJ6Qd0wcJAP2M_YlxgCVOkH3H5NaXvbylEClsGmAGpQ5zpgJDKQ3o6QwIX-pH6KdGb0N-sZkxlHiFapPycmgQhFnzeKubH8mU97m3DCH1Re06eehgyvtifJ-TrxbsvZ-9X158ur85Or1dWVHxZObA1OmywNSiNgMp0IIxpEX3rGoXQdVYZDthKAS2vpDDKOe6rxklWy46fkKudrpvgVs-p2KffeoKg7xdT6jWkJdgBdd1Y5aoSIDZSCMXKRTpvBffeQAW-aL3eac1p-rHBvOgxZIvDABGnTdacCSW6pu3aAn21h25M-fmD8d9iCqDeAWyack7oHyAV09v29X37etu-3rdfSOofkg27hJcS_fA_6h9-4rmI |
| CitedBy_id | crossref_primary_10_1007_s00521_024_10919_3 crossref_primary_10_3389_frai_2025_1466643 crossref_primary_10_1007_s40747_024_01751_2 crossref_primary_10_1016_j_compbiomed_2025_110380 crossref_primary_10_3390_jimaging11010002 crossref_primary_10_1016_j_ymeth_2025_04_016 crossref_primary_10_3389_fphys_2025_1528067 crossref_primary_10_3233_XST_240108 |
| Cites_doi | 10.1016/j.media.2020.101874 10.1109/LGRS.2020.2988294 10.3389/fmed.2023.1273441 10.1007/s00521-022-07419-7 10.1109/TMI.2019.2959609 10.1109/TMI.2020.3046692 10.1016/j.media.2022.102581 10.1007/978-3-030-32226-7_20 10.1109/TMI.2012.2210558 10.3389/fnins.2022.872601 10.1038/s41597-022-01875-5 10.1109/SIU.2019.8806244 10.3389/fnins.2022.1099560 10.1109/CVPR.2018.00745 10.1007/s41019-016-0011-3 10.3389/fonc.2021.638182 10.1007/978-3-319-46723-8_49 10.1016/j.neuroimage.2004.12.007 10.1007/978-3-030-11726-9_28 10.1016/j.neunet.2019.08.025 10.1109/ICASSP40776.2020.9053405 10.1109/ACCESS.2021.3075294 10.1109/TBME.2013.2271383 10.3389/fcomp.2023.1178450 10.1109/ISM46123.2019.00049 10.1109/ISNIB57382.2022.10075787 10.1038/s41598-021-93427-x 10.1049/ipr2.12419 10.1109/TMI.2022.3224873 10.1038/s41592-020-01008-z 10.1016/j.media.2004.06.019 10.3390/diagnostics13132161 10.3389/fnhum.2023.1275795 10.1007/s10554-008-9408-z 10.1109/TMI.2020.3034995 10.1016/j.compbiomed.2021.105123 10.1109/ICPR48806.2021.9413186 10.1007/978-3-319-24574-4_28 10.1109/IACS.2018.8355444 10.1007/978-3-030-01234-2_1 |
| ContentType | Journal Article |
| Copyright | Copyright © 2024 Zaman, Hassan, Zeng, Khan, Lu, Yang, Miao, Cao, Yang, Huang, Guo and Kang. |
| Copyright_xml | – notice: Copyright © 2024 Zaman, Hassan, Zeng, Khan, Lu, Yang, Miao, Cao, Yang, Huang, Guo and Kang. |
| DBID | AAYXX CITATION NPM 7X8 DOA |
| DOI | 10.3389/fnins.2024.1363930 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Anatomy & Physiology |
| EISSN | 1662-453X |
| ExternalDocumentID | oai_doaj_org_article_25c8d1842e5644808d16dfc43ffba1af 38680446 10_3389_fnins_2024_1363930 |
| Genre | Journal Article |
| GroupedDBID | --- 29H 2WC 53G 5GY 5VS 88I 8FE 8FH 9T4 AAFWJ AAYXX ABUWG ACGFO ACGFS ADRAZ AEGXH AENEX AFFHD AFKRA AFPKN AIAGR ALMA_UNASSIGNED_HOLDINGS AZQEC BBNVY BENPR BHPHI BPHCQ CCPQU CITATION CS3 DIK DU5 DWQXO E3Z EBS EJD EMOBN F5P FRP GNUQQ GROUPED_DOAJ GX1 HCIFZ HYE KQ8 LK8 M2P M48 M7P O5R O5S OK1 OVT P2P PGMZT PHGZM PHGZT PIMPY PQGLB PQQKQ PROAC RNS RPM W2D ACXDI C1A IAO IEA IHR ISR M~E NPM 7X8 PUEGO |
| ID | FETCH-LOGICAL-c413t-dac2ede5e7be6b4a1b9a4bb7eef7d58ea99c8b3ae764a73164b8dd3f15d602693 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 9 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001208375000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1662-453X 1662-4548 |
| IngestDate | Fri Oct 03 12:50:39 EDT 2025 Fri Sep 05 12:05:11 EDT 2025 Thu Jan 02 22:39:03 EST 2025 Tue Nov 18 22:29:31 EST 2025 Sat Nov 29 04:31:19 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | deep learning attention mechanism encoder-decoder architecture neurological diagnostics computer-aided diagnosis adaptive feature extraction medical image analysis brain lesion segmentation |
| Language | English |
| License | Copyright © 2024 Zaman, Hassan, Zeng, Khan, Lu, Yang, Miao, Cao, Yang, Huang, Guo and Kang. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c413t-dac2ede5e7be6b4a1b9a4bb7eef7d58ea99c8b3ae764a73164b8dd3f15d602693 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | https://doaj.org/article/25c8d1842e5644808d16dfc43ffba1af |
| PMID | 38680446 |
| PQID | 3048495797 |
| PQPubID | 23479 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_25c8d1842e5644808d16dfc43ffba1af proquest_miscellaneous_3048495797 pubmed_primary_38680446 crossref_primary_10_3389_fnins_2024_1363930 crossref_citationtrail_10_3389_fnins_2024_1363930 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-00-00 |
| PublicationDateYYYYMMDD | 2024-01-01 |
| PublicationDate_xml | – year: 2024 text: 2024-00-00 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland |
| PublicationTitle | Frontiers in neuroscience |
| PublicationTitleAlternate | Front Neurosci |
| PublicationYear | 2024 |
| Publisher | Frontiers Media S.A |
| Publisher_xml | – name: Frontiers Media S.A |
| References | Wang (ref39) 2019 Mou (ref27) 2021; 67 Wang (ref40) 2022; 16 Myronenko (ref29) 2019 Kermi (ref20) 2022 Hassan (ref10) 2022; 141 Gooya (ref7) 2012; 31 Ronneberger (ref33) 2015 Hernandez Petzsche (ref11) 2022; 9 Li (ref22) 2020; 18 Huang (ref14) 2020 Xia (ref42) 2022; 82 Hu (ref13) 2018 Anbeek (ref1) 2004; 8 Ibtehaz (ref16) 2020; 121 Limonova (ref24) 2021 Stoyanov (ref36) 2018 Liew (ref23) 2017 Yang (ref43) 2021; 11 Islam (ref18) 2013; 60 Guo (ref9) 2021; 9 Woo (ref41) 2018 Vedaei (ref38) 2023; 16 Baid (ref2) 2021 Zeng (ref45) 2023; 13 Gao (ref6) 2023; 17 Ma (ref25) 2023; 10 Zhou (ref47) 2018 Tan (ref37) 2019 Hurlock (ref15) 2009; 25 Nie (ref30) 2022; 16 Siuly (ref35) 2016; 1 Celaya (ref3) 2022; 42 Isensee (ref17) 2021; 18 Mehrani (ref26) 2023 Mubashar (ref28) 2022; 34 Jha (ref19) 2019 Zhou (ref48) 2019; 39 Chau (ref4) 2005; 25 Çiçek (ref5) 2016 Greenspan (ref8) 2023 Yurtkulu (ref44) 2019 Shatnawi (ref34) 2018 Zhang (ref46) 2020; 40 Li (ref21) 2020; 40 Rashid (ref32) 2021; 11 Howard (ref12) 2017 Oktay (ref31) 2018 |
| References_xml | – volume: 67 start-page: 101874 year: 2021 ident: ref27 article-title: CS2-Net: deep learning segmentation of curvilinear structures in medical imaging publication-title: Med. Image Anal. doi: 10.1016/j.media.2020.101874 – volume: 18 start-page: 905 year: 2020 ident: ref22 article-title: SCAttNet: semantic segmentation network with spatial and channel attention mechanism for high-resolution remote sensing images publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2020.2988294 – volume: 10 start-page: 1273441 year: 2023 ident: ref25 article-title: SW-UNet: a U-Net fusing sliding window transformer block with CNN for segmentation of lung nodules publication-title: Front. Med. doi: 10.3389/fmed.2023.1273441 – year: 2017 ident: ref23 article-title: The Anatomical Tracings of Lesions After Stroke (ATLAS) Dataset—Release 1.1 – volume: 34 start-page: 17723 year: 2022 ident: ref28 article-title: R2U++: a multiscale recurrent residual U-net with dense skip connections for medical image segmentation publication-title: Neural Comput. Appl. doi: 10.1007/s00521-022-07419-7 – volume: 39 start-page: 1856 year: 2019 ident: ref48 article-title: UNet++: redesigning skip connections to exploit multiscale features in image segmentation publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2019.2959609 – volume: 40 start-page: 1065 year: 2020 ident: ref21 article-title: Analyzing overfitting under class imbalance in neural networks for image segmentation publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2020.3046692 – volume: 82 start-page: 102581 year: 2022 ident: ref42 article-title: 3D vessel-like structure segmentation in medical images by an edge-reinforced network publication-title: Med. Image Anal. doi: 10.1016/j.media.2022.102581 – year: 2019 ident: ref39 article-title: Volumetric attention for 3D medical image segmentation and detection doi: 10.1007/978-3-030-32226-7_20 – volume: 31 start-page: 1941 year: 2012 ident: ref7 article-title: GLISTR: glioma image segmentation and registration publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2012.2210558 – volume: 16 start-page: 872601 year: 2022 ident: ref30 article-title: N-Net: a novel dense fully convolutional neural network for thyroid nodule segmentation publication-title: Front. Neurosci. doi: 10.3389/fnins.2022.872601 – year: 2018 ident: ref31 article-title: Attention U-Net: learning where to look for the pancreas – volume: 9 start-page: 762 year: 2022 ident: ref11 article-title: ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset publication-title: Sci. Data doi: 10.1038/s41597-022-01875-5 – year: 2019 ident: ref44 article-title: Semantic segmentation with extended DeepLabv3 architecture doi: 10.1109/SIU.2019.8806244 – volume: 16 start-page: 1099560 year: 2023 ident: ref38 article-title: Identification of chronic mild traumatic brain injury using resting state functional MRI and machine learning techniques publication-title: Front. Neurosci. doi: 10.3389/fnins.2022.1099560 – year: 2018 ident: ref13 article-title: Squeeze-and-excitation networks doi: 10.1109/CVPR.2018.00745 – volume: 1 start-page: 54 year: 2016 ident: ref35 article-title: Medical big data: neurological diseases diagnosis through medical data analysis publication-title: Data Sci. Eng. doi: 10.1007/s41019-016-0011-3 – volume: 11 start-page: 638182 year: 2021 ident: ref43 article-title: Artificial convolutional neural network in object detection and semantic segmentation for medical imaging analysis publication-title: Front. Oncol. doi: 10.3389/fonc.2021.638182 – year: 2016 ident: ref5 article-title: 3D U-Net: learning dense volumetric segmentation from sparse annotation doi: 10.1007/978-3-319-46723-8_49 – volume: 25 start-page: 408 year: 2005 ident: ref4 article-title: The Talairach coordinate of a point in the MNI space: how to interpret it publication-title: NeuroImage doi: 10.1016/j.neuroimage.2004.12.007 – year: 2019 ident: ref29 article-title: 3D MRI brain tumor segmentation using autoencoder regularization doi: 10.1007/978-3-030-11726-9_28 – volume: 121 start-page: 74 year: 2020 ident: ref16 article-title: MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation publication-title: Neural Netw. doi: 10.1016/j.neunet.2019.08.025 – start-page: 21013 year: 2019 ident: ref37 article-title: EfficientNet: rethinking model scaling for convolutional neural networks – year: 2020 ident: ref14 article-title: UNet 3+: A full-scale connected UNet for medical image segmentation doi: 10.1109/ICASSP40776.2020.9053405 – volume: 9 start-page: 69382 year: 2021 ident: ref9 article-title: Double U-Nets for image segmentation by integrating the region and boundary information publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3075294 – volume: 60 start-page: 3204 year: 2013 ident: ref18 article-title: Multifractal texture estimation for detection and segmentation of brain tumors publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2013.2271383 – year: 2023 ident: ref26 article-title: Self-attention in vision transformers performs perceptual grouping, not attention doi: 10.3389/fcomp.2023.1178450 – year: 2019 ident: ref19 article-title: ResUNet++: an advanced architecture for medical image segmentation doi: 10.1109/ISM46123.2019.00049 – year: 2022 ident: ref20 article-title: A deep learning-based 3D-GAN for glioma subregions detection and segmentation in multimodal brain MRI volumes doi: 10.1109/ISNIB57382.2022.10075787 – volume: 11 start-page: 14124 year: 2021 ident: ref32 article-title: DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI publication-title: Sci. Rep. doi: 10.1038/s41598-021-93427-x – year: 2021 ident: ref2 article-title: The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification – volume: 16 start-page: 1243 year: 2022 ident: ref40 article-title: Medical image segmentation using deep learning: a survey publication-title: IET Image Process. doi: 10.1049/ipr2.12419 – volume: 42 start-page: 1172 year: 2022 ident: ref3 article-title: PocketNet: a smaller neural network for medical image analysis publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2022.3224873 – volume: 18 start-page: 203 year: 2021 ident: ref17 article-title: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation publication-title: Nat. Methods doi: 10.1038/s41592-020-01008-z – volume: 8 start-page: 205 year: 2004 ident: ref1 article-title: Automatic segmentation of different-sized white matter lesions by voxel probability estimation publication-title: Med. Image Anal. doi: 10.1016/j.media.2004.06.019 – volume: 13 start-page: 2161 year: 2023 ident: ref45 article-title: Tubular structure segmentation via multi-scale reverse attention sparse convolution publication-title: Diagnostics doi: 10.3390/diagnostics13132161 – volume: 17 start-page: 1275795 year: 2023 ident: ref6 article-title: MMGan: a multimodal MR brain tumor image segmentation method publication-title: Front. Hum. Neurosci. doi: 10.3389/fnhum.2023.1275795 – volume: 25 start-page: 31 year: 2009 ident: ref15 article-title: History of cardiac computed tomography: single to 320-detector row multislice computed tomography publication-title: Int. J. Cardiovasc. Imaging doi: 10.1007/s10554-008-9408-z – start-page: 14224 year: 2023 ident: ref8 – volume: 40 start-page: 661 year: 2020 ident: ref46 article-title: Inter-slice context residual learning for 3D medical image segmentation publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2020.3034995 – volume: 141 start-page: 105123 year: 2022 ident: ref10 article-title: Review and classification of AI-enabled COVID-19 CT imaging models based on computer vision tasks publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2021.105123 – start-page: 11040 year: 2018 ident: ref36 – year: 2021 ident: ref24 article-title: ResNet-like architecture with low hardware requirements doi: 10.1109/ICPR48806.2021.9413186 – year: 2015 ident: ref33 article-title: U-Net: convolutional networks for biomedical image segmentation doi: 10.1007/978-3-319-24574-4_28 – year: 2017 ident: ref12 article-title: MobileNets: efficient convolutional neural networks for mobile vision applications – year: 2018 ident: ref34 article-title: A comparative study of open source deep learning frameworks doi: 10.1109/IACS.2018.8355444 – year: 2018 ident: ref47 – year: 2018 ident: ref41 article-title: CBAM: convolutional block attention module doi: 10.1007/978-3-030-01234-2_1 |
| SSID | ssj0062842 |
| Score | 2.4028137 |
| Snippet | In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex... IntroductionIn neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its... |
| SourceID | doaj proquest pubmed crossref |
| SourceType | Open Website Aggregation Database Index Database Enrichment Source |
| StartPage | 1363930 |
| SubjectTerms | adaptive feature extraction attention mechanism brain lesion segmentation computer-aided diagnosis encoder-decoder architecture medical image analysis |
| Title | Adaptive Feature Medical Segmentation Network: an adaptable deep learning paradigm for high-performance 3D brain lesion segmentation in medical imaging |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/38680446 https://www.proquest.com/docview/3048495797 https://doaj.org/article/25c8d1842e5644808d16dfc43ffba1af |
| Volume | 18 |
| WOSCitedRecordID | wos001208375000001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: DOA dateStart: 20070101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: M7P dateStart: 20230101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: BENPR dateStart: 20230101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: PIMPY dateStart: 20230101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: M2P dateStart: 20230101 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELag5cClAspjC6yMhLigqJs4iR1uW2gFh64iHtJysvwYr1Yi6WoflfpL-nc742SXvQAXLpZi-RXPeDxjj-dj7G0KpUM9WSUO8jLJjcc1VwRMjLdAXlGZsBFsQk4majqt6j2oL_IJ68IDdxN3mhVOeTRDMijIlBjhR-mDy0UI1qQmkPQdyWprTHUyuEShm3VPZNAEq05DO28pNneWk1uXqMjneW8bitH6_6xixq3m4hE76nVEPu7G9pjdg_YJOx63aB83N_wdj16b8Tj8mN2OvVmQyOKkzG2WwPurF_4NZk3_sKjlk87b-wM3LTdUg15McQ-w4D1uxIxTFHA_nzUc9VhOYYyTxe9XBVx84pbgJLA8HbDx1X7zmN303c6biHv0lP24OP_-8XPSgy0kDvexdeKNy8BDAdJCaXOT2srk1kqAIH2hwFSVU1YYkGVuCO4qt8p7EdLCE4pVJZ6xg_aqhReMBxUqU0BqIHjU1kYmsxmMwIYipAFbGbB0O_fa9ZHICRDjl0aLhOilI7000Uv39Bqw97s6iy4Ox19LnxFJdyUphnbMQM7SPWfpf3HWgL3ZMoTGNUcXKaaFq81KCxR7Od1vygF73nHKriuhSkWX5Cf_Ywgv2UP6re7I5xU7WC838Jo9cNfr-Wo5ZPflVA3Z4dn5pP46jAsA08usplRielh_uax_3gEK8hDm |
| linkProvider | Directory of Open Access Journals |
| 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=Adaptive+Feature+Medical+Segmentation+Network%3A+an+adaptable+deep+learning+paradigm+for+high-performance+3D+brain+lesion+segmentation+in+medical+imaging&rft.jtitle=Frontiers+in+neuroscience&rft.au=Zaman%2C+Asim&rft.au=Hassan%2C+Haseeb&rft.au=Zeng%2C+Xueqiang&rft.au=Khan%2C+Rashid&rft.date=2024&rft.issn=1662-453X&rft.eissn=1662-453X&rft.volume=18&rft_id=info:doi/10.3389%2Ffnins.2024.1363930&rft.externalDBID=n%2Fa&rft.externalDocID=10_3389_fnins_2024_1363930 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1662-453X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1662-453X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1662-453X&client=summon |