Melanoma segmentation using deep learning with test-time augmentations and conditional random fields
In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task more challenging. Lesion segmentation is an initial step in CAD schemes as it leads to low error rates in quantification of the structure, boundary, a...
Gespeichert in:
| Veröffentlicht in: | Scientific reports Jg. 12; H. 1; S. 3948 - 16 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
London
Nature Publishing Group UK
10.03.2022
Nature Publishing Group Nature Research Nature Portfolio |
| Schlagworte: | |
| ISSN: | 2045-2322, 2045-2322 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task more challenging. Lesion segmentation is an initial step in CAD schemes as it leads to low error rates in quantification of the structure, boundary, and scale of the skin lesion. Subjective clinical assessment of the skin lesion segmentation results provided by current state-of-the-art deep learning segmentation techniques does not offer the required results as per the inter-observer agreement of expert dermatologists. This study proposes a novel deep learning-based, fully automated approach to skin lesion segmentation, including sophisticated pre and postprocessing approaches. We use three deep learning models, including UNet, deep residual U-Net (ResUNet), and improved ResUNet (ResUNet++). The preprocessing phase combines morphological filters with an inpainting algorithm to eliminate unnecessary hair structures from the dermoscopic images. Finally, we used test time augmentation (TTA) and conditional random field (CRF) in the postprocessing stage to improve segmentation accuracy. The proposed method was trained and evaluated on ISIC-2016 and ISIC-2017 skin lesion datasets. It achieved an average Jaccard Index of 85.96% and 80.05% for ISIC-2016 and ISIC-2017 datasets, when trained individually. When trained on combined dataset (ISIC-2016 and ISIC-2017), the proposed method achieved an average Jaccard Index of 80.73% and 90.02% on ISIC-2017 and ISIC-2016 testing datasets. The proposed methodological framework can be used to design a fully automated computer-aided skin lesion diagnostic system due to its high scalability and robustness. |
|---|---|
| AbstractList | In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task more challenging. Lesion segmentation is an initial step in CAD schemes as it leads to low error rates in quantification of the structure, boundary, and scale of the skin lesion. Subjective clinical assessment of the skin lesion segmentation results provided by current state-of-the-art deep learning segmentation techniques does not offer the required results as per the inter-observer agreement of expert dermatologists. This study proposes a novel deep learning-based, fully automated approach to skin lesion segmentation, including sophisticated pre and postprocessing approaches. We use three deep learning models, including UNet, deep residual U-Net (ResUNet), and improved ResUNet (ResUNet++). The preprocessing phase combines morphological filters with an inpainting algorithm to eliminate unnecessary hair structures from the dermoscopic images. Finally, we used test time augmentation (TTA) and conditional random field (CRF) in the postprocessing stage to improve segmentation accuracy. The proposed method was trained and evaluated on ISIC-2016 and ISIC-2017 skin lesion datasets. It achieved an average Jaccard Index of 85.96% and 80.05% for ISIC-2016 and ISIC-2017 datasets, when trained individually. When trained on combined dataset (ISIC-2016 and ISIC-2017), the proposed method achieved an average Jaccard Index of 80.73% and 90.02% on ISIC-2017 and ISIC-2016 testing datasets. The proposed methodological framework can be used to design a fully automated computer-aided skin lesion diagnostic system due to its high scalability and robustness. In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task more challenging. Lesion segmentation is an initial step in CAD schemes as it leads to low error rates in quantification of the structure, boundary, and scale of the skin lesion. Subjective clinical assessment of the skin lesion segmentation results provided by current state-of-the-art deep learning segmentation techniques does not offer the required results as per the inter-observer agreement of expert dermatologists. This study proposes a novel deep learning-based, fully automated approach to skin lesion segmentation, including sophisticated pre and postprocessing approaches. We use three deep learning models, including UNet, deep residual U-Net (ResUNet), and improved ResUNet (ResUNet++). The preprocessing phase combines morphological filters with an inpainting algorithm to eliminate unnecessary hair structures from the dermoscopic images. Finally, we used test time augmentation (TTA) and conditional random field (CRF) in the postprocessing stage to improve segmentation accuracy. The proposed method was trained and evaluated on ISIC-2016 and ISIC-2017 skin lesion datasets. It achieved an average Jaccard Index of 85.96% and 80.05% for ISIC-2016 and ISIC-2017 datasets, when trained individually. When trained on combined dataset (ISIC-2016 and ISIC-2017), the proposed method achieved an average Jaccard Index of 80.73% and 90.02% on ISIC-2017 and ISIC-2016 testing datasets. The proposed methodological framework can be used to design a fully automated computer-aided skin lesion diagnostic system due to its high scalability and robustness.In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task more challenging. Lesion segmentation is an initial step in CAD schemes as it leads to low error rates in quantification of the structure, boundary, and scale of the skin lesion. Subjective clinical assessment of the skin lesion segmentation results provided by current state-of-the-art deep learning segmentation techniques does not offer the required results as per the inter-observer agreement of expert dermatologists. This study proposes a novel deep learning-based, fully automated approach to skin lesion segmentation, including sophisticated pre and postprocessing approaches. We use three deep learning models, including UNet, deep residual U-Net (ResUNet), and improved ResUNet (ResUNet++). The preprocessing phase combines morphological filters with an inpainting algorithm to eliminate unnecessary hair structures from the dermoscopic images. Finally, we used test time augmentation (TTA) and conditional random field (CRF) in the postprocessing stage to improve segmentation accuracy. The proposed method was trained and evaluated on ISIC-2016 and ISIC-2017 skin lesion datasets. It achieved an average Jaccard Index of 85.96% and 80.05% for ISIC-2016 and ISIC-2017 datasets, when trained individually. When trained on combined dataset (ISIC-2016 and ISIC-2017), the proposed method achieved an average Jaccard Index of 80.73% and 90.02% on ISIC-2017 and ISIC-2016 testing datasets. The proposed methodological framework can be used to design a fully automated computer-aided skin lesion diagnostic system due to its high scalability and robustness. Abstract In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task more challenging. Lesion segmentation is an initial step in CAD schemes as it leads to low error rates in quantification of the structure, boundary, and scale of the skin lesion. Subjective clinical assessment of the skin lesion segmentation results provided by current state-of-the-art deep learning segmentation techniques does not offer the required results as per the inter-observer agreement of expert dermatologists. This study proposes a novel deep learning-based, fully automated approach to skin lesion segmentation, including sophisticated pre and postprocessing approaches. We use three deep learning models, including UNet, deep residual U-Net (ResUNet), and improved ResUNet (ResUNet++). The preprocessing phase combines morphological filters with an inpainting algorithm to eliminate unnecessary hair structures from the dermoscopic images. Finally, we used test time augmentation (TTA) and conditional random field (CRF) in the postprocessing stage to improve segmentation accuracy. The proposed method was trained and evaluated on ISIC-2016 and ISIC-2017 skin lesion datasets. It achieved an average Jaccard Index of 85.96% and 80.05% for ISIC-2016 and ISIC-2017 datasets, when trained individually. When trained on combined dataset (ISIC-2016 and ISIC-2017), the proposed method achieved an average Jaccard Index of 80.73% and 90.02% on ISIC-2017 and ISIC-2016 testing datasets. The proposed methodological framework can be used to design a fully automated computer-aided skin lesion diagnostic system due to its high scalability and robustness. |
| ArticleNumber | 3948 |
| Author | Ashraf, Hassan Gilani, Syed Omer Waris, Asim Niazi, Imran Khan Ghafoor, Muhammad Fazeel |
| Author_xml | – sequence: 1 givenname: Hassan surname: Ashraf fullname: Ashraf, Hassan organization: Department of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering (SMME), National University of Sciences and Technology (NUST) – sequence: 2 givenname: Asim surname: Waris fullname: Waris, Asim email: asim.waris@smme.nust.edu.pk organization: Department of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering (SMME), National University of Sciences and Technology (NUST) – sequence: 3 givenname: Muhammad Fazeel surname: Ghafoor fullname: Ghafoor, Muhammad Fazeel organization: Department of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering (SMME), National University of Sciences and Technology (NUST) – sequence: 4 givenname: Syed Omer surname: Gilani fullname: Gilani, Syed Omer organization: Department of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering (SMME), National University of Sciences and Technology (NUST) – sequence: 5 givenname: Imran Khan surname: Niazi fullname: Niazi, Imran Khan organization: Department of Health Science and Technology, Aalborg University, Center of Chiropractic Research, New Zealand College of Chiropractic, Faculty of Health and Environmental Sciences, Health and Rehabilitation Research Institute, AUT University |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/35273282$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9Ustu3CAUtapUTZrmB7qoLHXTjVtzAQObSlXUR6RU3bRrxJhrhxE2U7AT5e-Lx9O8FmEDF84598F5XRyNYcSieEvqj6Sm8lNihCtZ1QBVLaTk1e2L4gRqxiugAEcPzsfFWUrbOi8OihH1qjimHAQFCSeF_YnejGEwZcJ-wHEykwtjOSc39qVF3JUeTRyX6MZNV-WEaaomN2Bp5nt8Ks1oyzaM1i2h8WXMF2EoO4fepjfFy874hGeH_bT48-3r7_Mf1eWv7xfnXy6rlks2VQDcoOqsEUxtNq1QjQSDraKCGkZFbWVjTUcZY1grpB0naEAQYyTJAF7T0-Ji1bXBbPUuusHEWx2M0_uLEHtt4uRaj5oDb4hA3gmKTAmreIfIOAdGJBFm0fq8au3mzYC2za1G4x-JPn4Z3ZXuw7WWilAJPAvQVcA77DEn3zh9DXvi_jz7XE2rN6gBGqlBASUssz4c0sbwd87D1oNLLfr8SRjmpKGhUoBoYKnw_RPoNswxD3-PEpIuv51R7x72cdfAfwtkAKyANoaUInZ3EFLrxWp6tZrOVtN7q-nbTJJPSK1brZBn4fzz1MNcUs4z9hjvy36G9Q99cekE |
| CitedBy_id | crossref_primary_10_1080_01431161_2025_2496001 crossref_primary_10_32604_cmes_2024_050124 crossref_primary_10_1109_ACCESS_2024_3514865 crossref_primary_10_3390_a15120443 crossref_primary_10_3390_eng5040146 crossref_primary_10_1007_s10462_023_10631_z crossref_primary_10_1038_s41598_025_02757_7 crossref_primary_10_3390_fi14100277 crossref_primary_10_3390_s25072043 crossref_primary_10_1007_s11042_023_16934_1 crossref_primary_10_1016_j_bspc_2024_106037 crossref_primary_10_3390_app131810076 crossref_primary_10_21597_jist_1575214 crossref_primary_10_1007_s00521_023_08729_0 crossref_primary_10_7717_peerj_cs_1953 crossref_primary_10_3390_diagnostics13132274 crossref_primary_10_1007_s10278_025_01449_y crossref_primary_10_1080_01431161_2023_2288948 crossref_primary_10_1016_j_engappai_2025_112043 crossref_primary_10_1007_s10278_023_00819_8 crossref_primary_10_1038_s41598_023_39648_8 crossref_primary_10_1002_aisy_202400558 crossref_primary_10_1007_s10278_024_01000_5 crossref_primary_10_1007_s11760_023_02732_7 crossref_primary_10_3390_diagnostics12071548 crossref_primary_10_1007_s10278_024_01106_w crossref_primary_10_3390_computation11030063 crossref_primary_10_3390_app13148512 crossref_primary_10_1016_j_knosys_2023_110828 crossref_primary_10_1016_j_ins_2023_01_081 crossref_primary_10_1016_j_heliyon_2024_e40608 crossref_primary_10_3390_cancers16061120 crossref_primary_10_1109_ACCESS_2023_3339635 crossref_primary_10_3390_jimaging11010015 crossref_primary_10_1111_jdv_20319 |
| Cites_doi | 10.1109/JBHI.2019.2891049 10.1001/jamadermatol.2015.1187 10.1109/TMI.2017.2695227 10.3390/s20061601 10.1016/j.jaad.2017.08.016 10.1109/TBME.2017.2712771 10.1147/JRD.2017.2708299 10.1109/TMI.2016.2642839 10.1109/TIP.2011.2146190 10.1016/j.cmpb.2018.05.027 10.1017/S0022215116000554 10.3390/s18020556 10.1038/s41598-020-61808-3 10.1109/LGRS.2018.2802944 10.1145/1553374.1553479 10.1007/978-3-319-24574-4_28 10.1109/SSCI.2017.8280804 10.1109/ISBI.2018.8363547 10.1109/CVPR.2015.7298965 10.1109/ISM46123.2019.00049 |
| ContentType | Journal Article |
| Copyright | The Author(s) 2022 2022. The Author(s). The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: The Author(s) 2022 – notice: 2022. The Author(s). – notice: The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | C6C AAYXX CITATION CGR CUY CVF ECM EIF NPM 3V. 7X7 7XB 88A 88E 88I 8FE 8FH 8FI 8FJ 8FK ABUWG AEUYN AFKRA AZQEC BBNVY BENPR BHPHI CCPQU DWQXO FYUFA GHDGH GNUQQ HCIFZ K9. LK8 M0S M1P M2P M7P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PRINS Q9U 7X8 JLOSS Q33 5PM DOA |
| DOI | 10.1038/s41598-022-07885-y |
| DatabaseName | Springer Nature OA Free Journals (WRLC) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Biology Database (Alumni Edition) Medical Database (Alumni Edition) Science Database (Alumni Edition) ProQuest SciTech Collection ProQuest Natural Science Collection ProQuest Hospital Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest One Sustainability ProQuest Central UK/Ireland ProQuest Central Essentials - QC Biological Science Collection ProQuest Central Natural Science Collection ProQuest One ProQuest Central Korea Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Premium Collection ProQuest Health & Medical Complete (Alumni) Biological Sciences ProQuest Health & Medical Collection Medical Database Science Database (ProQuest) Biological Science Database ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic MEDLINE - Academic Université de Liège - Open Repository and Bibliography (ORBI) (Open Access titles only) Université de Liège - Open Repository and Bibliography (ORBI) PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Publicly Available Content Database ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest One Health & Nursing ProQuest Natural Science Collection ProQuest Central China ProQuest Biology Journals (Alumni Edition) ProQuest Central ProQuest One Applied & Life Sciences ProQuest One Sustainability ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) Natural Science Collection ProQuest Central Korea Health & Medical Research Collection Biological Science Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest Science Journals (Alumni Edition) ProQuest Biological Science Collection ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) Biological Science Database ProQuest SciTech Collection ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | CrossRef MEDLINE - Academic MEDLINE Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals (WRLC) 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: PIMPY name: ProQuest - Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Biology |
| EISSN | 2045-2322 |
| EndPage | 16 |
| ExternalDocumentID | oai_doaj_org_article_525617e5f73e497d95fee455241817a0 PMC8913825 oai_orbi_ulg_ac_be_2268_292314 35273282 10_1038_s41598_022_07885_y |
| Genre | Journal Article |
| GroupedDBID | 0R~ 3V. 4.4 53G 5VS 7X7 88A 88E 88I 8FE 8FH 8FI 8FJ AAFWJ AAJSJ AAKDD ABDBF ABUWG ACGFS ACSMW ACUHS ADBBV ADRAZ AENEX AEUYN AFKRA AJTQC ALIPV ALMA_UNASSIGNED_HOLDINGS AOIJS AZQEC BAWUL BBNVY BCNDV BENPR BHPHI BPHCQ BVXVI C6C CCPQU DIK DWQXO EBD EBLON EBS ESX FYUFA GNUQQ GROUPED_DOAJ GX1 HCIFZ HH5 HMCUK HYE KQ8 LK8 M0L M1P M2P M48 M7P M~E NAO OK1 PIMPY PQQKQ PROAC PSQYO RNT RNTTT RPM SNYQT UKHRP AASML AAYXX AFFHD AFPKN CITATION PHGZM PHGZT PJZUB PPXIY PQGLB CGR CUY CVF ECM EIF NPM 7XB 8FK K9. PKEHL PQEST PQUKI PRINS Q9U 7X8 PUEGO EJD IPNFZ JLOSS Q33 RIG 5PM |
| ID | FETCH-LOGICAL-c584t-225ae9fda749bbc79682aec9373a4370d86daf3444e09e3f51ea271aa813a4503 |
| IEDL.DBID | 7X7 |
| ISICitedReferencesCount | 41 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000838209800039&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2045-2322 |
| IngestDate | Fri Oct 03 12:39:15 EDT 2025 Tue Nov 04 02:01:27 EST 2025 Sat Nov 29 01:25:53 EST 2025 Fri Sep 05 07:30:24 EDT 2025 Tue Oct 07 08:04:46 EDT 2025 Thu Jan 02 22:54:06 EST 2025 Sat Nov 29 02:51:42 EST 2025 Tue Nov 18 21:52:24 EST 2025 Fri Feb 21 02:36:34 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| License | 2022. The Author(s). Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c584t-225ae9fda749bbc79682aec9373a4370d86daf3444e09e3f51ea271aa813a4503 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 scopus-id:2-s2.0-85126244339 |
| ORCID | 0000-0003-0519-0619 |
| OpenAccessLink | https://www.proquest.com/docview/2637832941?pq-origsite=%requestingapplication% |
| PMID | 35273282 |
| PQID | 2637832941 |
| PQPubID | 2041939 |
| PageCount | 16 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_525617e5f73e497d95fee455241817a0 pubmedcentral_primary_oai_pubmedcentral_nih_gov_8913825 liege_orbi_v2_oai_orbi_ulg_ac_be_2268_292314 proquest_miscellaneous_2638727620 proquest_journals_2637832941 pubmed_primary_35273282 crossref_primary_10_1038_s41598_022_07885_y crossref_citationtrail_10_1038_s41598_022_07885_y springer_journals_10_1038_s41598_022_07885_y |
| PublicationCentury | 2000 |
| PublicationDate | 2022-03-10 |
| PublicationDateYYYYMMDD | 2022-03-10 |
| PublicationDate_xml | – month: 03 year: 2022 text: 2022-03-10 day: 10 |
| PublicationDecade | 2020 |
| PublicationPlace | London |
| PublicationPlace_xml | – name: London – name: England |
| PublicationTitle | Scientific reports |
| PublicationTitleAbbrev | Sci Rep |
| PublicationTitleAlternate | Sci Rep |
| PublicationYear | 2022 |
| Publisher | Nature Publishing Group UK Nature Publishing Group Nature Research Nature Portfolio |
| Publisher_xml | – name: Nature Publishing Group UK – name: Nature Publishing Group – name: Nature Research – name: Nature Portfolio |
| References | Li (CR26) 2011; 20 Zafar (CR10) 2020; 20 Codella (CR14) 2017; 61 CR19 Li, Shen (CR24) 2018; 18 CR18 CR17 CR15 Marchetti (CR4) 2018; 78 Hagerty (CR3) 2019; 23 CR13 Zhang, Liu, Wang (CR16) 2018; 15 CR11 Moshkov, Mathe, Kertesz-Farkas, Hollandi, Horvath (CR20) 2020; 10 Radiuk (CR21) 2017; 20 Bi (CR5) 2017; 64 CR8 CR7 CR9 CR25 CR22 Yuan, Chao, Lo (CR6) 2017; 36 Newlands, Currie, Memon, Whitaker, Woolford (CR2) 2016; 130 Rogers, Weinstock, Feldman, Coldiron (CR1) 2015; 151 Al-Masni, Al-Antari, Choi, Han, Kim (CR12) 2018; 162 Yu, Chen, Dou, Qin, Heng (CR23) 2016; 36 MA Al-Masni (7885_CR12) 2018; 162 7885_CR19 JR Hagerty (7885_CR3) 2019; 23 7885_CR15 7885_CR18 7885_CR17 N Moshkov (7885_CR20) 2020; 10 K Zafar (7885_CR10) 2020; 20 7885_CR11 C Newlands (7885_CR2) 2016; 130 7885_CR13 NC Codella (7885_CR14) 2017; 61 Y Yuan (7885_CR6) 2017; 36 L Bi (7885_CR5) 2017; 64 7885_CR7 7885_CR8 7885_CR9 7885_CR22 MA Marchetti (7885_CR4) 2018; 78 7885_CR25 HW Rogers (7885_CR1) 2015; 151 Z Zhang (7885_CR16) 2018; 15 C Li (7885_CR26) 2011; 20 Lequan Yu (7885_CR23) 2016; 36 Y Li (7885_CR24) 2018; 18 PM Radiuk (7885_CR21) 2017; 20 |
| References_xml | – volume: 23 start-page: 1385 year: 2019 end-page: 1391 ident: CR3 article-title: Deep learning and handcrafted method fusion: Higher diagnostic accuracy for melanoma dermoscopy images publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2019.2891049 – ident: CR22 – ident: CR18 – volume: 151 start-page: 1081 year: 2015 end-page: 1086 ident: CR1 article-title: Incidence estimate of nonmelanoma skin cancer (keratinocyte carcinomas) in the us population, 2012 publication-title: JAMA Dermatol. doi: 10.1001/jamadermatol.2015.1187 – volume: 36 start-page: 1876 year: 2017 end-page: 1886 ident: CR6 article-title: Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2017.2695227 – volume: 20 start-page: 1601 year: 2020 ident: CR10 article-title: Skin lesion segmentation from dermoscopic images using convolutional neural network publication-title: Sensors doi: 10.3390/s20061601 – ident: CR8 – ident: CR25 – volume: 78 start-page: 270 year: 2018 end-page: 277 ident: CR4 article-title: Results of the 2016 international skin imaging collaboration international symposium on biomedical imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images publication-title: J. Am. Acad. Dermatol. doi: 10.1016/j.jaad.2017.08.016 – ident: CR19 – volume: 64 start-page: 2065 year: 2017 end-page: 2074 ident: CR5 article-title: Dermoscopic image segmentation via multistage fully convolutional networks publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2017.2712771 – volume: 61 start-page: 5 year: 2017 end-page: 1 ident: CR14 article-title: Deep learning ensembles for melanoma recognition in dermoscopy images publication-title: IBM J. Res. Dev. doi: 10.1147/JRD.2017.2708299 – volume: 36 start-page: 994 issue: 4 year: 2016 end-page: 1004 ident: CR23 article-title: Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks publication-title: IEEE Transactions on Medical Imaging doi: 10.1109/TMI.2016.2642839 – ident: CR15 – volume: 20 start-page: 20 year: 2017 end-page: 24 ident: CR21 article-title: Impact of training set batch size on the performance of convolutional neural networks for diverse datasets publication-title: Inf. Technol. Manag. Sci. – volume: 20 start-page: 2007 year: 2011 end-page: 2016 ident: CR26 article-title: A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2011.2146190 – ident: CR17 – ident: CR13 – ident: CR11 – ident: CR9 – volume: 162 start-page: 221 year: 2018 end-page: 231 ident: CR12 article-title: Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks publication-title: Comput. Methods Progr. Biomed. doi: 10.1016/j.cmpb.2018.05.027 – volume: 130 start-page: S125 year: 2016 end-page: S132 ident: CR2 article-title: Non-melanoma skin cancer: United kingdom national multidisciplinary guidelines publication-title: J. Laryngol. Otol. doi: 10.1017/S0022215116000554 – volume: 18 start-page: 556 year: 2018 ident: CR24 article-title: Skin lesion analysis towards melanoma detection using deep learning network publication-title: Sensors doi: 10.3390/s18020556 – ident: CR7 – volume: 10 start-page: 1 year: 2020 end-page: 7 ident: CR20 article-title: Test-time augmentation for deep learning-based cell segmentation on microscopy images publication-title: Sci. Rep. doi: 10.1038/s41598-020-61808-3 – volume: 15 start-page: 749 year: 2018 end-page: 753 ident: CR16 article-title: Road extraction by deep residual u-net. IEEE Geosci publication-title: Remote Sens. Lett. doi: 10.1109/LGRS.2018.2802944 – volume: 23 start-page: 1385 year: 2019 ident: 7885_CR3 publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2019.2891049 – volume: 151 start-page: 1081 year: 2015 ident: 7885_CR1 publication-title: JAMA Dermatol. doi: 10.1001/jamadermatol.2015.1187 – ident: 7885_CR22 doi: 10.1145/1553374.1553479 – ident: 7885_CR8 – ident: 7885_CR15 doi: 10.1007/978-3-319-24574-4_28 – volume: 36 start-page: 994 issue: 4 year: 2016 ident: 7885_CR23 publication-title: IEEE Transactions on Medical Imaging doi: 10.1109/TMI.2016.2642839 – ident: 7885_CR7 doi: 10.1109/SSCI.2017.8280804 – ident: 7885_CR13 doi: 10.1109/ISBI.2018.8363547 – volume: 15 start-page: 749 year: 2018 ident: 7885_CR16 publication-title: Remote Sens. Lett. doi: 10.1109/LGRS.2018.2802944 – volume: 130 start-page: S125 year: 2016 ident: 7885_CR2 publication-title: J. Laryngol. Otol. doi: 10.1017/S0022215116000554 – volume: 18 start-page: 556 year: 2018 ident: 7885_CR24 publication-title: Sensors doi: 10.3390/s18020556 – ident: 7885_CR11 – volume: 61 start-page: 5 year: 2017 ident: 7885_CR14 publication-title: IBM J. Res. Dev. doi: 10.1147/JRD.2017.2708299 – ident: 7885_CR18 doi: 10.1109/CVPR.2015.7298965 – ident: 7885_CR19 – volume: 20 start-page: 2007 year: 2011 ident: 7885_CR26 publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2011.2146190 – volume: 162 start-page: 221 year: 2018 ident: 7885_CR12 publication-title: Comput. Methods Progr. Biomed. doi: 10.1016/j.cmpb.2018.05.027 – volume: 36 start-page: 1876 year: 2017 ident: 7885_CR6 publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2017.2695227 – ident: 7885_CR25 – volume: 20 start-page: 20 year: 2017 ident: 7885_CR21 publication-title: Inf. Technol. Manag. Sci. – volume: 10 start-page: 1 year: 2020 ident: 7885_CR20 publication-title: Sci. Rep. doi: 10.1038/s41598-020-61808-3 – volume: 64 start-page: 2065 year: 2017 ident: 7885_CR5 publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2017.2712771 – volume: 20 start-page: 1601 year: 2020 ident: 7885_CR10 publication-title: Sensors doi: 10.3390/s20061601 – ident: 7885_CR17 doi: 10.1109/ISM46123.2019.00049 – volume: 78 start-page: 270 year: 2018 ident: 7885_CR4 publication-title: J. Am. Acad. Dermatol. doi: 10.1016/j.jaad.2017.08.016 – ident: 7885_CR9 doi: 10.1109/TMI.2017.2695227 |
| SSID | ssj0000529419 |
| Score | 2.5568166 |
| Snippet | In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task more... Abstract In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task... |
| SourceID | doaj pubmedcentral liege proquest pubmed crossref springer |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 3948 |
| SubjectTerms | 692/699 692/700 Automation Datasets Deep Learning Dermoscopy Dermoscopy - methods Engineering, computing & technology Humanities and Social Sciences Humans Ingénierie, informatique & technologie Lesions Melanoma Melanoma - diagnostic imaging Multidisciplinary Neural Networks, Computer Science Science (multidisciplinary) Segmentation Skin Diseases Skin lesions Skin Neoplasms Skin Neoplasms - diagnostic imaging Skin Neoplasms - pathology |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lj9MwELbQCiQuiDdZFmQkbhBt_KrtIyBWHGDFAdDerEk8KZXadLVpV-q_Z-yk3S3PC1IOVTJxY89M5pvMeIaxl9gKhwQb6O1XuVI3AGWNmHZyRaWisG2VI_jfPtrTU3d25j9fa_WVcsKG8sDDwh0bssnCommtQu1t9KZF1MaQ5XHCQvbWK-uvOVNDVW_ptfDjLplKueOeLFXaTSZTsqVzptzsWaJcsJ8A6jyFqn-HNn9NmvwpcpoN0slddmdEkvzNMIN77AZ299mtobfk5gGLn3AO3XIBvMfpYtxh1PGU5z7lEfGcjw0jpjx9i-UEOVdl6jTPYX1F33PoIiefOc6Gj4acbFtcLnjOfOsfsq8n77-8-1COLRXKhpDGqiTtBfRtBKt9XTfWT5wEbAijKNDKVtFNIrRKa42VR9UagSCtAHCCCEylHrGDbtnhE8Yl1EhM8F5Wta6jpINGdwYjgbCooWBiu7yhGeuNp7YX85Dj3sqFgSWBWBIyS8KmYK9295wP1Tb-Sv02cW1HmSpl5xMkP2GUn_Av-SnY68xzuqmehUuZR8m_13MapQk1BoKoLsgEhXXBjraiEUZt74OcKEtvRpK4gr3YXSY9TcEX6HC5zjSOsOJE0j8-HiRp9-AqVcEj37dgdk_G9ma2f6Wbfc-1wFOUmZx8msVWGq8e688rd_g_Vu4puy2zOqXkxiN2sLpY4zN2s7lczfqL51kffwD-Mzcy priority: 102 providerName: Directory of Open Access Journals |
| Title | Melanoma segmentation using deep learning with test-time augmentations and conditional random fields |
| URI | https://link.springer.com/article/10.1038/s41598-022-07885-y https://www.ncbi.nlm.nih.gov/pubmed/35273282 https://www.proquest.com/docview/2637832941 https://www.proquest.com/docview/2638727620 https://orbi.uliege.be/handle/2268/292314 https://pubmed.ncbi.nlm.nih.gov/PMC8913825 https://doaj.org/article/525617e5f73e497d95fee455241817a0 |
| Volume | 12 |
| WOSCitedRecordID | wos000838209800039&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 (WRLC) customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: DOA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: M~E dateStart: 20110101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: M7P dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: 7X7 dateStart: 20110101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest - Publicly Available Content Database customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: PIMPY dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: BENPR dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database (ProQuest) customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: M2P dateStart: 20110101 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dj9MwDI_gDiRe-D4oHFOQeIPq2iRdkifEoTuBxKYJARpPUdq4Y9LWjnU7af89TtptGh_3gjRF0-qmyew4v9qOTcgrKFMFCBtQ-yUqFoW1cQ7gT3I5zl0qyyR48L99ksOhGo_1qDO4NV1Y5VYnBkXt6sLbyM9Yn0uUPi3St4ufsa8a5b2rXQmNm-TYl832ci7Hcmdj8V4skerurEzC1VmD-5U_U8Z8yKVSWbw52I9C2n6EqTPvsP4b5vwzdPI3_2nYli7v_e-E7pO7HSCl71oJekBuQPWQ3G5LVG4eETeAma3quaUNTObdQaWK-nD5CXUAC9rVnZhQb9KliFxXsS9YT-16T99QWzmKr95u2toeKW6Rrp7TEEDXPCZfLy--vP8Qd5UZ4gIByypGJWBBl85KofO8kLqvmIUCoQ63gsvEqb6zJRdCQKKBl1kKlsnUWpUiQZbwE3JU1RU8JZTZHBBFaM2SXOSO4Qd7Vxk4xHJO2IikW_6Yoktb7qtnzExwn3NlWp4a5KkJPDWbiLze3bNok3ZcS33u2b6j9Am3ww_1cmK69WsyhIaphKyUHISWTmclgMgyHLpKpU0i8iYIDd6UT80VC72E7-sZ9lKYHAwiXWWYR9QiIqdboTCd0mjMXiIi8nJ3GZe79-HYCup1oFEIOfsMn_ikFcXdwLlPpoev0BGRB0J6MLPDK9X0R0gp7p3VimU4i60474f173_u2fWzeE7usLDSfPTjKTlaLdfwgtwqrlbTZtkLSzW0qkeOzy-Go8-9YBHBdsBGvpXYHo8-DkbffwFDWU2I |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwELaWLgguvB-BBYwEJ4g2cZzaOSDEa7XVttUeFrScjBNPSqU2KU27qH-K38jYSVqVx972gNRD1EwcO_lm_MUz4yHkOeShBKQNaP0C6fNMaz8FsJlcJopMKPLAefA_98VwKE9Pk-Md8rPNhbFhla1NdIbalJldI99n3Ugg-hIevpl9923VKOtdbUto1LA4gtUP_GSrXvc-4Pt9wdjBx5P3h35TVcDPcLJd-AhgDUlutOBJmmYi6UqmIcNpOtI8EoGRXaPziHMOQQJRHoegmQi1liEKxEGE7V4iuxzBHnTI7nFvcPxlvapj_WY8TJrsnCCS-xXOkDaLjdkgTyljf7U1A7pCAUiMJ9ZF_jeW-2ew5m8eWzcRHtz43x7hTXK9odz0ba0jt8gOFLfJlboI5-oOMQOY6KKcalrBaNqkYhXUJgSMqAGY0aayxojaRWuK3HzhL8ZToHq5ka-oLgzNShsB4FZXKZIAU06pCxGs7pJPFzLEe6RTlAU8IJTpFJAnJQkLUp4ahj9sXcZgkK0arj0StnhQWbMxu60PMlEuQCCSqsaQQgwphyG18sjL9TWzeluSc6XfWZitJe2W4u6Pcj5SjYVSMZLfUECciwh4IkwS5wA8jrHrMhQ68MgrB1K8KB2rM-ZaccfLCbaSqRQUcnmpmP1m4B7Za0GoGrNYqQ0CPfJsfRoNmvVS6QLKpZORSKq7DO94v4b-uuOR3S6QSeYRsaUUWyPbPlOMv7lN0607XrIYR9Gqz6Zb_35yD88fxVNy9fBk0Ff93vDoEbnGnJbbWM890lnMl_CYXM7OFuNq_qQxFJR8vWjF-gUtW6Sq |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwELaWLiAuvB-FBYwEJ4ia2E7tHBBi2a1Y7VJVCNDejBNPSqU2KU27qH-NX8fYTVqVx972gNRD1TiOnX4z89kz4yHkOeSRAqQNqP1CFYjMmCAFcJlclnMbyTz0HvwvJ7LfV6enyWCH_GxyYVxYZaMTvaK2Zeb2yDusyyWiLxFRJ6_DIgYHvTfT74GrIOU8rU05jRVEjmH5A5dv1eujA_yvXzDWO_z07n1QVxgIMjS88wDBbCDJrZEiSdNMJl3FDGRosrkRXIZWda3JuRACwgR4HkdgmIyMURE2iEOO_V4iu5LjoqdFdvcP-4OP6x0e50MTUVJn6oRcdSq0li6jjbmAT6XiYLllDX3RACTJY-cu_xvj_TNw8zfvrTeKvRv_8-u8Sa7XVJy-XcnOLbIDxW1yZVWcc3mH2A8wNkU5MbSC4aRO0SqoSxQYUgswpXXFjSF1m9kUOfs8mI8mQM1i076iprA0K11kgN91pUgObDmhPnSwuks-X8gU75FWURbwgFBmUkD-lCQsTEVqGX6wdxWDRRZrhWmTqMGGzuoD213dkLH2gQNc6RWeNOJJezzpZZu8XN8zXR1Xcm7rfQe5dUt31Lj_oZwNda25dIykOJIQ55KDSKRN4hxAxDEOXUXShG3yygMWb0pH-oz5Xvz3xRh7yXQKGjm-0sytJUSb7DWA1LW6rPQGjW3ybH0ZFZ3zXpkCyoVvo5Bsdxk-8f5KDNYD5-4YQaZYm8gtAdma2faVYvTNH6bu3PSKxTiLRpQ2w_r3m3t4_iyekqsoTfrkqH_8iFxjXuBdCOgeac1nC3hMLmdn81E1e1LrDEq-XrRc_QJVvq1E |
| 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=Melanoma+segmentation+using+deep+learning+with+test-time+augmentations+and+conditional+random+fields&rft.jtitle=Scientific+reports&rft.au=Ashraf%2C+Hassan&rft.au=Waris%2C+Asim&rft.au=Ghafoor%2C+Muhammad+Fazeel&rft.au=Gilani%2C+Syed+Omer&rft.date=2022-03-10&rft.pub=Nature+Research&rft.issn=2045-2322&rft.eissn=2045-2322&rft_id=info:doi/10.1038%2Fs41598-022-07885-y&rft_id=info%3Apmid%2F35273282&rft.externalDBID=n%2Fa&rft.externalDocID=oai_orbi_ulg_ac_be_2268_292314 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2045-2322&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2045-2322&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2045-2322&client=summon |