Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) challenge results

Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key challenges such as annotation variability, calibration, and uncertainty estimation. This is why we created the Calibrati...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computers in biology and medicine Jg. 197; H. Pt B; S. 111024
Hauptverfasser:	Riera-Marín, Meritxell, O.K., Sikha, Rodríguez-Comas, Júlia, May, Matthias Stefan, Pan, Zhaohong, Zhou, Xiang, Liang, Xiaokun, Erick, Franciskus Xaverius, Prenner, Andrea, Hémon, Cédric, Boussot, Valentin, Dillenseger, Jean-Louis, Nunes, Jean-Claude, Qayyum, Abdul, Mazher, Moona, Niederer, Steven A., Kushibar, Kaisar, Martín-Isla, Carlos, Radeva, Petia, Lekadir, Karim, Barfoot, Theodore, Garcia Peraza Herrera, Luis C., Glocker, Ben, Vercauteren, Tom, Gago, Lucas, Englemann, Justin, Kleiss, Joy-Marie, Aubanell, Anton, Antolin, Andreu, García-López, Javier, González Ballester, Miguel A., Galdrán, Adrián
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States Elsevier Ltd 01.10.2025 Elsevier
Schlagworte:	Abdominal CT Artificial Intelligence Bioengineering Calibration Computer Science Deep Learning Engineering Sciences Humans Image Processing, Computer-Assisted - methods Imaging Internal Medicine Life Sciences Medical Imaging Multi-class image segmentation Multiple expert annotations Other Signal and Image processing Uncertainty Multiple expert annotations Uncertainty Multi-class image segmentation Calibration Abdominal CT abdominal CT
ISSN:	0010-4825, 1879-0534, 1879-0534
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key challenges such as annotation variability, calibration, and uncertainty estimation. This is why we created the Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS), which highlights the critical role of multiple annotators in establishing a more comprehensive ground truth, emphasizing that segmentation is inherently subjective and that leveraging inter-annotator variability is essential for robust model evaluation. Seven teams participated in the challenge, submitting a variety of DL models evaluated using metrics such as Dice Similarity Coefficient (DSC), Expected Calibration Error (ECE), and Continuous Ranked Probability Score (CRPS). By incorporating consensus and dissensus ground truth, we assess how DL models handle uncertainty and whether their confidence estimates align with true segmentation performance. Our findings reinforce the importance of well-calibrated models, as better calibration is strongly correlated with the quality of the results. Furthermore, we demonstrate that segmentation models trained on diverse datasets and enriched with pre-trained knowledge exhibit greater robustness, particularly in cases deviating from standard anatomical structures. Notably, the best-performing models achieved high DSC and well-calibrated uncertainty estimates. This work underscores the need for multi-annotator ground truth, thorough calibration assessments, and uncertainty-aware evaluations to develop trustworthy and clinically reliable DL-based medical image segmentation models. •The CURVAS challenge assessed DL segmentation under annotation uncertainty.•Multi-rater CT annotations evaluated consensus and disagreement in three organs.•Metrics account for expert variability, enabling more reliable model assessment.•Calibration-aware models showed strong links between confidence and accuracy.•Volume estimation and robustness to ambiguity support clinical applicability.
AbstractList	Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key challenges such as annotation variability, calibration, and uncertainty estimation. This is why we created the Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS), which highlights the critical role of multiple annotators in establishing a more comprehensive ground truth, emphasizing that segmentation is inherently subjective and that leveraging inter-annotator variability is essential for robust model evaluation. Seven teams participated in the challenge, submitting a variety of DL models evaluated using metrics such as Dice Similarity Coefficient (DSC), Expected Calibration Error (ECE), and Continuous Ranked Probability Score (CRPS). By incorporating consensus and dissensus ground truth, we assess how DL models handle uncertainty and whether their confidence estimates align with true segmentation performance. Our findings reinforce the importance of well-calibrated models, as better calibration is strongly correlated with the quality of the results. Furthermore, we demonstrate that segmentation models trained on diverse datasets and enriched with pre-trained knowledge exhibit greater robustness, particularly in cases deviating from standard anatomical structures. Notably, the best-performing models achieved high DSC and well-calibrated uncertainty estimates. This work underscores the need for multi-annotator ground truth, thorough calibration assessments, and uncertainty-aware evaluations to develop trustworthy and clinically reliable DL-based medical image segmentation models. Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key challenges such as annotation variability, calibration, and uncertainty estimation. This is why we created the Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS), which highlights the critical role of multiple annotators in establishing a more comprehensive ground truth, emphasizing that segmentation is inherently subjective and that leveraging inter-annotator variability is essential for robust model evaluation. Seven teams participated in the challenge, submitting a variety of DL models evaluated using metrics such as Dice Similarity Coefficient (DSC), Expected Calibration Error (ECE), and Continuous Ranked Probability Score (CRPS). By incorporating consensus and dissensus ground truth, we assess how DL models handle uncertainty and whether their confidence estimates align with true segmentation performance. Our findings reinforce the importance of well-calibrated models, as better calibration is strongly correlated with the quality of the results. Furthermore, we demonstrate that segmentation models trained on diverse datasets and enriched with pre-trained knowledge exhibit greater robustness, particularly in cases deviating from standard anatomical structures. Notably, the best-performing models achieved high DSC and well-calibrated uncertainty estimates. This work underscores the need for multi-annotator ground truth, thorough calibration assessments, and uncertainty-aware evaluations to develop trustworthy and clinically reliable DL-based medical image segmentation models.Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key challenges such as annotation variability, calibration, and uncertainty estimation. This is why we created the Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS), which highlights the critical role of multiple annotators in establishing a more comprehensive ground truth, emphasizing that segmentation is inherently subjective and that leveraging inter-annotator variability is essential for robust model evaluation. Seven teams participated in the challenge, submitting a variety of DL models evaluated using metrics such as Dice Similarity Coefficient (DSC), Expected Calibration Error (ECE), and Continuous Ranked Probability Score (CRPS). By incorporating consensus and dissensus ground truth, we assess how DL models handle uncertainty and whether their confidence estimates align with true segmentation performance. Our findings reinforce the importance of well-calibrated models, as better calibration is strongly correlated with the quality of the results. Furthermore, we demonstrate that segmentation models trained on diverse datasets and enriched with pre-trained knowledge exhibit greater robustness, particularly in cases deviating from standard anatomical structures. Notably, the best-performing models achieved high DSC and well-calibrated uncertainty estimates. This work underscores the need for multi-annotator ground truth, thorough calibration assessments, and uncertainty-aware evaluations to develop trustworthy and clinically reliable DL-based medical image segmentation models. AbstractDeep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key challenges such as annotation variability, calibration, and uncertainty estimation. This is why we created the Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS), which highlights the critical role of multiple annotators in establishing a more comprehensive ground truth, emphasizing that segmentation is inherently subjective and that leveraging inter-annotator variability is essential for robust model evaluation. Seven teams participated in the challenge, submitting a variety of DL models evaluated using metrics such as Dice Similarity Coefficient (DSC), Expected Calibration Error (ECE), and Continuous Ranked Probability Score (CRPS). By incorporating consensus and dissensus ground truth, we assess how DL models handle uncertainty and whether their confidence estimates align with true segmentation performance. Our findings reinforce the importance of well-calibrated models, as better calibration is strongly correlated with the quality of the results. Furthermore, we demonstrate that segmentation models trained on diverse datasets and enriched with pre-trained knowledge exhibit greater robustness, particularly in cases deviating from standard anatomical structures. Notably, the best-performing models achieved high DSC and well-calibrated uncertainty estimates. This work underscores the need for multi-annotator ground truth, thorough calibration assessments, and uncertainty-aware evaluations to develop trustworthy and clinically reliable DL-based medical image segmentation models. Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key challenges such as annotation variability, calibration, and uncertainty estimation. This is why we created the Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS), which highlights the critical role of multiple annotators in establishing a more comprehensive ground truth, emphasizing that segmentation is inherently subjective and that leveraging inter-annotator variability is essential for robust model evaluation. Seven teams participated in the challenge, submitting a variety of DL models evaluated using metrics such as Dice Similarity Coefficient (DSC), Expected Calibration Error (ECE), and Continuous Ranked Probability Score (CRPS). By incorporating consensus and dissensus ground truth, we assess how DL models handle uncertainty and whether their confidence estimates align with true segmentation performance. Our findings reinforce the importance of well-calibrated models, as better calibration is strongly correlated with the quality of the results. Furthermore, we demonstrate that segmentation models trained on diverse datasets and enriched with pre-trained knowledge exhibit greater robustness, particularly in cases deviating from standard anatomical structures. Notably, the best-performing models achieved high DSC and well-calibrated uncertainty estimates. This work underscores the need for multi-annotator ground truth, thorough calibration assessments, and uncertainty-aware evaluations to develop trustworthy and clinically reliable DL-based medical image segmentation models. •The CURVAS challenge assessed DL segmentation under annotation uncertainty.•Multi-rater CT annotations evaluated consensus and disagreement in three organs.•Metrics account for expert variability, enabling more reliable model assessment.•Calibration-aware models showed strong links between confidence and accuracy.•Volume estimation and robustness to ambiguity support clinical applicability.
ArticleNumber	111024
Author	O.K., Sikha Riera-Marín, Meritxell Dillenseger, Jean-Louis Vercauteren, Tom Boussot, Valentin Kleiss, Joy-Marie Antolin, Andreu García-López, Javier Zhou, Xiang Barfoot, Theodore Gago, Lucas Mazher, Moona Liang, Xiaokun May, Matthias Stefan Pan, Zhaohong Hémon, Cédric González Ballester, Miguel A. Qayyum, Abdul Nunes, Jean-Claude Lekadir, Karim Englemann, Justin Martín-Isla, Carlos Niederer, Steven A. Rodríguez-Comas, Júlia Erick, Franciskus Xaverius Prenner, Andrea Radeva, Petia Aubanell, Anton Garcia Peraza Herrera, Luis C. Kushibar, Kaisar Glocker, Ben Galdrán, Adrián
Author_xml	– sequence: 1 givenname: Meritxell orcidid: 0000-0001-6221-5443 surname: Riera-Marín fullname: Riera-Marín, Meritxell email: m.riera@sycaitechnologies.com organization: Sycai Technologies SL, Scientific and Technical Department, Barcelona, Spain – sequence: 2 givenname: Sikha orcidid: 0000-0002-3499-8062 surname: O.K. fullname: O.K., Sikha organization: BCN Medtech, Universitat Pompeu Fabra, Barcelona, Spain – sequence: 3 givenname: Júlia orcidid: 0000-0002-4788-6668 surname: Rodríguez-Comas fullname: Rodríguez-Comas, Júlia organization: Sycai Technologies SL, Scientific and Technical Department, Barcelona, Spain – sequence: 4 givenname: Matthias Stefan orcidid: 0000-0002-2540-850X surname: May fullname: May, Matthias Stefan organization: Universitätsklinikum Erlangen, Department of Radiology of the Uniklinikum Erlangen (UKER), Erlangen, Germany – sequence: 5 givenname: Zhaohong orcidid: 0009-0007-9566-4131 surname: Pan fullname: Pan, Zhaohong organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China – sequence: 6 givenname: Xiang orcidid: 0009-0009-2843-4605 surname: Zhou fullname: Zhou, Xiang organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China – sequence: 7 givenname: Xiaokun orcidid: 0000-0002-1207-5726 surname: Liang fullname: Liang, Xiaokun organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China – sequence: 8 givenname: Franciskus Xaverius orcidid: 0000-0001-6004-7896 surname: Erick fullname: Erick, Franciskus Xaverius organization: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany – sequence: 9 givenname: Andrea orcidid: 0009-0004-8485-7702 surname: Prenner fullname: Prenner, Andrea organization: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany – sequence: 10 givenname: Cédric orcidid: 0009-0003-6669-5108 surname: Hémon fullname: Hémon, Cédric organization: Université de Rennes 1, CLCC Eugène Marquis, and INSERM UMR 1099 LTSI, Rennes, France – sequence: 11 givenname: Valentin orcidid: 0009-0003-2465-5458 surname: Boussot fullname: Boussot, Valentin organization: Université de Rennes 1, CLCC Eugène Marquis, and INSERM UMR 1099 LTSI, Rennes, France – sequence: 12 givenname: Jean-Louis orcidid: 0000-0001-8840-3944 surname: Dillenseger fullname: Dillenseger, Jean-Louis organization: Université de Rennes 1, CLCC Eugène Marquis, and INSERM UMR 1099 LTSI, Rennes, France – sequence: 13 givenname: Jean-Claude orcidid: 0000-0001-6560-1518 surname: Nunes fullname: Nunes, Jean-Claude organization: Université de Rennes 1, CLCC Eugène Marquis, and INSERM UMR 1099 LTSI, Rennes, France – sequence: 14 givenname: Abdul orcidid: 0000-0003-3102-1595 surname: Qayyum fullname: Qayyum, Abdul organization: National Heart and Lung Institute, Faculty of Medicine, Imperial College London, London, United Kingdom – sequence: 15 givenname: Moona orcidid: 0000-0003-4444-5776 surname: Mazher fullname: Mazher, Moona organization: Centre for Medical Image Computing, Department of Computer Science, University College London, London, United Kingdom – sequence: 16 givenname: Steven A. orcidid: 0000-0002-4612-6982 surname: Niederer fullname: Niederer, Steven A. organization: Centre for Medical Image Computing, Department of Computer Science, University College London, London, United Kingdom – sequence: 17 givenname: Kaisar orcidid: 0000-0001-7507-5208 surname: Kushibar fullname: Kushibar, Kaisar organization: Barcelona Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain – sequence: 18 givenname: Carlos orcidid: 0000-0003-4270-4009 surname: Martín-Isla fullname: Martín-Isla, Carlos organization: Barcelona Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain – sequence: 19 givenname: Petia orcidid: 0000-0003-0047-5172 surname: Radeva fullname: Radeva, Petia organization: AIBA, Facultat de Matemàtiques i Informàtica, and Institute of Neuroscience, Universitat de Barcelona, Barcelona, Spain – sequence: 20 givenname: Karim orcidid: 0000-0002-9456-1612 surname: Lekadir fullname: Lekadir, Karim organization: Barcelona Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain – sequence: 21 givenname: Theodore orcidid: 0009-0005-2309-5238 surname: Barfoot fullname: Barfoot, Theodore organization: King’s College London (KCL), London, United Kingdom – sequence: 22 givenname: Luis C. orcidid: 0000-0002-7362-0353 surname: Garcia Peraza Herrera fullname: Garcia Peraza Herrera, Luis C. organization: King’s College London (KCL), London, United Kingdom – sequence: 23 givenname: Ben orcidid: 0000-0002-4897-9356 surname: Glocker fullname: Glocker, Ben organization: King’s College London (KCL), London, United Kingdom – sequence: 24 givenname: Tom orcidid: 0000-0003-1794-0456 surname: Vercauteren fullname: Vercauteren, Tom organization: King’s College London (KCL), London, United Kingdom – sequence: 25 givenname: Lucas orcidid: 0000-0002-4694-6120 surname: Gago fullname: Gago, Lucas organization: Universitat de Barcelona (UB), Barcelona, Spain – sequence: 26 givenname: Justin orcidid: 0000-0002-5345-6023 surname: Englemann fullname: Englemann, Justin organization: University of Edinburgh, Edinburgh, United Kingdom – sequence: 27 givenname: Joy-Marie orcidid: 0009-0001-2330-4248 surname: Kleiss fullname: Kleiss, Joy-Marie organization: Universitätsklinikum Erlangen, Department of Radiology of the Uniklinikum Erlangen (UKER), Erlangen, Germany – sequence: 28 givenname: Anton orcidid: 0000-0002-3511-6025 surname: Aubanell fullname: Aubanell, Anton organization: Hospital de Sant Pau i la Santa Creu, Diagnostic Imaging Department, Barcelona, Spain – sequence: 29 givenname: Andreu orcidid: 0000-0001-6973-4246 surname: Antolin fullname: Antolin, Andreu organization: Hospital Universitari Vall d’Hebron, Department of Radiology, Institut de Diagnòstic per la Imatge (IDI), Barcelona, Spain – sequence: 30 givenname: Javier orcidid: 0000-0001-9241-8479 surname: García-López fullname: García-López, Javier organization: Sycai Technologies SL, Scientific and Technical Department, Barcelona, Spain – sequence: 31 givenname: Miguel A. orcidid: 0000-0002-9227-6826 surname: González Ballester fullname: González Ballester, Miguel A. organization: BCN Medtech, Universitat Pompeu Fabra, Barcelona, Spain – sequence: 32 givenname: Adrián orcidid: 0000-0002-5992-1520 surname: Galdrán fullname: Galdrán, Adrián organization: TECNALIA, Basque Research and Technology Alliance (BRTA), Bizcaia, Spain
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/40934552$$D View this record in MEDLINE/PubMed https://hal.science/hal-05263956$$DView record in HAL
BookMark	eNqNkk9r3DAQxUVJaTZpv0LRMTl4O5It_7mUbpc2KSwUst1chSyPt9ra0layA_vtK-MkhUIhp4GZ3zyG9-aCnFlnkRDKYMmA5R8OS-36Y21cj82SAxdLxhjw7BVZsLKoEhBpdkYWAAySrOTinFyEcACADFJ4Q84zqNJMCL4gfq06U3s1GGepsg3dWY1-UMYOJ9o6T_uxG8ydGtDTe9eNPdJVCBhCj3agxs5z5_fK0i3up-6sdbXe3d2vttdU_1Rdh3aP1GOIcHhLXreqC_jusV6S3dcvP9a3yeb7zbf1apPotORDgoCFqqta87ZgQhWqbFnFWA6FQp43TatygZVW0LSCC6WgFZohE1VRRUfSKr0k17NuPEAevemVP0mnjLxdbeTUA8HztBL5A4vs1cwevfs9Yhhkb4LGrlMW3RhkyrOqzIqyKCP6_hEd62j_s_KTpxEoZ0B7F4LH9hlhIKf45EH-jU9O8ck5vrj6eV7F6MuDQS-DNhgTaYxHPcjGmZeIfPxHRHfGGq26X3jCcHCjt9F3yWTgEuR2-pLpSbgAlhb5ZNyn_wu87IY_WabStQ
Cites_doi	10.1109/TMI.2019.2959609 10.1016/j.inffus.2021.05.008 10.1007/s10994-023-06336-7 10.1038/s41551-022-00988-x 10.1109/TMI.2004.828354 10.1016/j.artmed.2024.102830 10.1109/TPAMI.2021.3100536 10.1016/j.inffus.2024.102226 10.1111/j.1365-2753.2011.01705.x 10.1038/s41592-020-01008-z 10.1016/j.media.2024.103285 10.1016/j.media.2022.102642 10.1155/2023/1883597 10.1109/TMI.2009.2013851
ContentType	Journal Article
Copyright	2025 Elsevier Ltd Elsevier Ltd Copyright © 2025 Elsevier Ltd. All rights reserved. Attribution
Copyright_xml	– notice: 2025 Elsevier Ltd – notice: Elsevier Ltd – notice: Copyright © 2025 Elsevier Ltd. All rights reserved. – notice: Attribution
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 1XC VOOES
DOI	10.1016/j.compbiomed.2025.111024
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE MEDLINE - Academic
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 Computer Science
EISSN	1879-0534
EndPage	111024
ExternalDocumentID	oai:HAL:hal-05263956v1 40934552 10_1016_j_compbiomed_2025_111024 S0010482525013769 1_s2_0_S0010482525013769
Genre	Journal Article
GroupedDBID	--- --K --M --Z -~X .1- .55 .DC .FO .GJ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 29F 4.4 457 4G. 53G 5GY 5VS 7-5 71M 77I 7RV 7X7 88E 8AO 8FE 8FG 8FH 8FI 8FJ 8G5 8P~ 9JN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABMZM ABOCM ABUWG ABWVN ABXDB ACDAQ ACGFS ACIEU ACIUM ACIWK ACLOT ACNNM ACPRK ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO AEBSH AEIPS AEKER AENEX AEUPX AEVXI AFFHD AFJKZ AFKRA AFPUW AFRAH AFRHN AFTJW AFXIZ AGHFR AGQPQ AGUBO AGYEJ AHHHB AHMBA AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX AOUOD APXCP ARAPS ASPBG AVWKF AXJTR AZFZN AZQEC BBNVY BENPR BGLVJ BHPHI BKEYQ BKOJK BLXMC BNPGV BPHCQ BVXVI CCPQU CS3 DU5 DWQXO EBS EFJIC EFKBS EFLBG EJD EMOBN EO8 EO9 EP2 EP3 EX3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN FYUFA G-2 G-Q GBLVA GBOLZ GNUQQ GUQSH HCIFZ HLZ HMCUK HMK HMO HVGLF HZ~ IHE J1W K6V K7- KOM LK8 LX9 M1P M29 M2O M41 M7P MO0 N9A NAPCQ O-L O9- OAUVE OZT P-8 P-9 P2P P62 PC. PHGZM PHGZT PJZUB PPXIY PQGLB PQQKQ PROAC PSQYO Q38 R2- ROL RPZ RXW SAE SBC SCC SDF SDG SDP SEL SES SEW SPC SPCBC SSH SSV SSZ SV3 T5K TAE UAP UKHRP WOW WUQ X7M XPP Z5R ZGI ~G- ~HD 9DU AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 1XC VOOES
ID	FETCH-LOGICAL-c382t-e0e7ab9bc2f715a7a8f1911607ae26ddfa65e9ca0df525aa0f5c1e15979202393
ISSN	0010-4825 1879-0534
IngestDate	Mon Oct 20 06:21:40 EDT 2025 Thu Oct 02 21:31:58 EDT 2025 Sun Oct 05 01:50:25 EDT 2025 Sat Nov 29 06:55:51 EST 2025 Sat Nov 08 18:04:51 EST 2025 Sat Oct 25 09:17:24 EDT 2025 Sat Nov 15 06:41:42 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	Pt B
Keywords	Multiple expert annotations Uncertainty Multi-class image segmentation Calibration Abdominal CT abdominal CT
Language	English
License	Copyright © 2025 Elsevier Ltd. All rights reserved. Attribution: http://creativecommons.org/licenses/by
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c382t-e0e7ab9bc2f715a7a8f1911607ae26ddfa65e9ca0df525aa0f5c1e15979202393
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0002-4897-9356 0000-0001-7507-5208 0000-0002-2540-850X 0000-0003-3102-1595 0000-0002-5345-6023 0009-0003-6669-5108 0000-0002-4694-6120 0009-0009-2843-4605 0000-0001-8840-3944 0000-0002-3511-6025 0009-0001-2330-4248 0000-0002-4612-6982 0000-0003-1794-0456 0009-0003-2465-5458 0000-0001-6221-5443 0000-0002-3499-8062 0009-0005-2309-5238 0000-0001-6560-1518 0000-0002-1207-5726 0000-0001-6004-7896 0000-0002-7362-0353 0009-0004-8485-7702 0009-0007-9566-4131 0000-0003-4270-4009 0000-0003-0047-5172 0000-0002-9227-6826 0000-0003-4444-5776 0000-0001-6973-4246 0000-0001-9241-8479 0000-0002-9456-1612 0000-0002-4788-6668 0000-0002-5992-1520
OpenAccessLink	https://hal.science/hal-05263956
PMID	40934552
PQID	3249847878
PQPubID	23479
PageCount	1
ParticipantIDs	hal_primary_oai_HAL_hal_05263956v1 proquest_miscellaneous_3249847878 pubmed_primary_40934552 crossref_primary_10_1016_j_compbiomed_2025_111024 elsevier_sciencedirect_doi_10_1016_j_compbiomed_2025_111024 elsevier_clinicalkeyesjournals_1_s2_0_S0010482525013769 elsevier_clinicalkey_doi_10_1016_j_compbiomed_2025_111024
PublicationCentury	2000
PublicationDate	2025-10-01
PublicationDateYYYYMMDD	2025-10-01
PublicationDate_xml	– month: 10 year: 2025 text: 2025-10-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	Computers in biology and medicine
PublicationTitleAlternate	Comput Biol Med
PublicationYear	2025
Publisher	Elsevier Ltd Elsevier
Publisher_xml	– name: Elsevier Ltd – name: Elsevier
References	Tuijn, Janssens, Robben, van den Bergh (b6) 2012; 18 Islam, Glocker (b3) 2021 Abdar, Pourpanah, Hussain, Rezazadegan, Liu, Ghavamzadeh, Fieguth, Cao, Khosravi, Acharya, Makarenkov, Nahavandi (b9) 2021; 76 Chen, Ding, Zhu, Xu, Ji, Wang, Zang, Li (b31) 2024 C CÇiçek, Abdulkadir, Lienkamp, Brox, Ronneberger (b33) 2016 Barfoot, Garcia Peraza Herrera, Glocker, Vercauteren (b41) 2024 Mehta, Rastegari (b44) 2022 Zhang, Zheng, Shi (b2) 2023; 2023 Silva Filho, Song, Perello-Nieto, Santos-Rodriguez, Kull, Flach (b15) 2023; 112 Zhou, Siddiquee, Tajbakhsh, Liang (b42) 2020; 39 Qu, Zhang, Qiao, Liu, Tang, Yuille, Zhou (b37) 2023 Loshchilov, Hutter (b46) 2019 Warfield, Zou, Wells (b23) 2004; 23 Chua, Kim, Choi, Lee, Deshpande, Schwab, Lev, Gonzalez, Gee, Do (b14) 2023; 7 Wasserthal, Breit, Meyer, Pradella, Hinck, Sauter, Heye, Boll, Cyriac, Yang, Bach, Segeroth (b18) 2023 W. Li, A. Yuille, Z. Zhou, How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?, in: The Twelfth International Conference on Learning Representations, 2024. Franchi, Laurent, Legu’ery, Bursuc, Pilzer, Yao (b29) 2023 Li, Navarro, Ezhov, Bayat, Das, Kofler, Shit, Waldmannstetter, Paetzold, Hu, Wiestler, Zimmer, Amiranashvili, Prabhakar, Berger, Weidner, AlonsoBasant, Rashid, Baid, Adel, Ali, Baheti, Bai, Bhatt, Cetindag, Chen, Cheng, Dutand, Dular, Elattar, Feng, Gao, Huisman, Hu, Innani, Jiat, Karimi, Kuijf, Kwak, Le, Lia, Lin, Liu, Ma, Ma, Ma, Oksuz, Holland, Oliveira, Pal, Pei, Qiao, Saha, Selvan, Shen, Silva, Spiclin, Talbar, Wang, Wang, Wang, Wang, Xia, Xu, Yan, Yergin, Yu, Zeng, Zhang, Zhao, Zheng, Zukovec, Do, Becker, Simpson, Konukoglu, Jakab, Bakas, Joskowicz, Menze (b25) 2024 Guo, Pleiss, Sun, Weinberger (b12) 2017; vol. 70 Ji, Bai, Yang, Ge, Zhu, Zhang, Li, Zhang, Ma, Wan, Luo (b27) 2022 Jensen, Jørgensen, Jalaboi, Hansen, Olsen (b4) 2019 Tang, Yang, Li, Roth, Landman, Xu, Nath, Hatamizadeh (b34) 2022 Bernhardt, Ribeiro, Glocker (b11) 2022 Brachmann (b21) 2021 Ma, Zhang, Gu, Zhu, Ge, Zhang, An, Wang, Wang, Liu, Cao, Zhang, Liu, Wang, Li, He, Yang (b28) 2022; 44 Tan, Le (b43) 2019 Riera-Marín, García López, Kleiss, S. O K, Galdrán, May, González-Ballester, Rodráguez Comas, Schmidt, Hessman, Aubanell, Antolín (b49) 2024 SYCAI Technologies (b17) 2024 Huang, Miron, Hone, Li (b24) 2024 Smith (b47) 2018 DeVries, Taylor (b8) 2018 Qayyum, Razzak, Mazher, Lu, Niederer (b32) 2024; 106 Perez, Wang (b48) 2017 Zhou (b36) 2023 Bassi, Li, Tang, Isensee, Wang, Chen, Chou, Kirchhoff, Rokuss, Huang, Ye, He, Wald, Ulrich, Baumgartner, Roy, Maier-Hein, Jaeger, Ye, Xie, Zhang, Chen, Xia, Xing, Zhu, Sadegheih, Bozorgpour, Kumari, Azad, Merhof, Shi, Ma, Du, Bai, Huang, Zhao, Wang, Li, Gu, Dong, Yang, Mazurowski, Gupta, Wu, Zhuang, Chen, Roth, Xu, Blaschko, Decherchi, Cavalli, Yuille, Zhou (b40) 2024 Lin, Goyal, Girshick, He, Dollár (b45) 2017 Li, Qu, Chen, Bassi, Shi, Lai, Yu, Xue, Chen, Lin, Tang, Cao, Han, Zhang, Liu, Zhang, Ma, Wang, Zhang, Yuille, Zhou (b38) 2024; 97 Luo, Liao, Xiao, Chen, Song, Zhang, Li, Metaxas, Wang, Zhang (b26) 2022; 82 Heimann, van Ginneken, Styner, Arzhaeva, Aurich, Bauer, Beck, Becker, Beichel, Bekes, Bello, Binnig, Bischof, Bornik, Cashman, Chi, Cordova, Dawant, Fidrich, Furst, Furukawa, Grenacher, Hornegger, Kainmüller, Kitney, Kobatake, Lamecker, Lange, Lee, Lennon, Li, Li, Meinzer, Nemeth, Raicu, Rau, van Rikxoort, Rousson, Rusko, Saddi, Schmidt, Seghers, Shimizu, Slagmolen, Sorantin, Soza, Susomboon, Waite, Wimmer, Wolf (b22) 2009; 28 J. Nixon, M.W. Dusenberry, L. Zhang, G. Jerfel, D. Tran, Measuring Calibration in Deep Learning, in: Proceedings of the IEEE/CVF CVPR Workshops, 2019. Isensee, Jaeger, Kohl, Petersen, Maier-Hein (b19) 2021; 18 Riera-Marín, López, Kleiss, S. O. K, Galdrán, May, González-Ballester, Rodríguez-Comas, Schmidt, Hessman, Aubanell, Antolín (b16) 2024 Liu, Zhang, Chen, Xiao, Lu, Landman, Yuan, Yuille, Tang, Zhou (b35) 2023 Ng, Guo, Biswas, Petersen, Piechnik, Neubauer, Wright (b7) 2022 Jungo, Meier, Ermis, Blatti-Moreno, Herrmann, Wiest, Reyes (b5) 2018 Westenberger (b20) 2021 Sudre, Anson, Ingala, Lane, Jimenez, Haider, Varsavsky, Tanno, Smith, Ourselin, Jäger, Cardoso (b1) 2019 Alkin, Beck, Pöppel, Hochreiter, Brandstetter (b30) 2024 Lambert, Forbes, Doyle, Dehaene, Dojat (b10) 2024; 150 Li (10.1016/j.compbiomed.2025.111024_b38) 2024; 97 10.1016/j.compbiomed.2025.111024_b13 Lin (10.1016/j.compbiomed.2025.111024_b45) 2017 Bernhardt (10.1016/j.compbiomed.2025.111024_b11) 2022 Ng (10.1016/j.compbiomed.2025.111024_b7) 2022 Zhang (10.1016/j.compbiomed.2025.111024_b2) 2023; 2023 Guo (10.1016/j.compbiomed.2025.111024_b12) 2017; vol. 70 Qayyum (10.1016/j.compbiomed.2025.111024_b32) 2024; 106 Zhou (10.1016/j.compbiomed.2025.111024_b36) 2023 DeVries (10.1016/j.compbiomed.2025.111024_b8) 2018 Abdar (10.1016/j.compbiomed.2025.111024_b9) 2021; 76 Ma (10.1016/j.compbiomed.2025.111024_b28) 2022; 44 Lambert (10.1016/j.compbiomed.2025.111024_b10) 2024; 150 Tuijn (10.1016/j.compbiomed.2025.111024_b6) 2012; 18 Huang (10.1016/j.compbiomed.2025.111024_b24) 2024 Franchi (10.1016/j.compbiomed.2025.111024_b29) 2023 Westenberger (10.1016/j.compbiomed.2025.111024_b20) 2021 Jungo (10.1016/j.compbiomed.2025.111024_b5) 2018 Ji (10.1016/j.compbiomed.2025.111024_b27) 2022 Alkin (10.1016/j.compbiomed.2025.111024_b30) 2024 Luo (10.1016/j.compbiomed.2025.111024_b26) 2022; 82 Riera-Marín (10.1016/j.compbiomed.2025.111024_b49) 2024 Smith (10.1016/j.compbiomed.2025.111024_b47) 2018 Islam (10.1016/j.compbiomed.2025.111024_b3) 2021 Heimann (10.1016/j.compbiomed.2025.111024_b22) 2009; 28 Jensen (10.1016/j.compbiomed.2025.111024_b4) 2019 Isensee (10.1016/j.compbiomed.2025.111024_b19) 2021; 18 Qu (10.1016/j.compbiomed.2025.111024_b37) 2023 C CÇiçek (10.1016/j.compbiomed.2025.111024_b33) 2016 Liu (10.1016/j.compbiomed.2025.111024_b35) 2023 Brachmann (10.1016/j.compbiomed.2025.111024_b21) 2021 Li (10.1016/j.compbiomed.2025.111024_b25) 2024 10.1016/j.compbiomed.2025.111024_b39 Zhou (10.1016/j.compbiomed.2025.111024_b42) 2020; 39 Tan (10.1016/j.compbiomed.2025.111024_b43) 2019 Chua (10.1016/j.compbiomed.2025.111024_b14) 2023; 7 SYCAI Technologies (10.1016/j.compbiomed.2025.111024_b17) 2024 Barfoot (10.1016/j.compbiomed.2025.111024_b41) 2024 Sudre (10.1016/j.compbiomed.2025.111024_b1) 2019 Chen (10.1016/j.compbiomed.2025.111024_b31) 2024 Bassi (10.1016/j.compbiomed.2025.111024_b40) 2024 Loshchilov (10.1016/j.compbiomed.2025.111024_b46) 2019 Mehta (10.1016/j.compbiomed.2025.111024_b44) 2022 Riera-Marín (10.1016/j.compbiomed.2025.111024_b16) 2024 Warfield (10.1016/j.compbiomed.2025.111024_b23) 2004; 23 Silva Filho (10.1016/j.compbiomed.2025.111024_b15) 2023; 112 Tang (10.1016/j.compbiomed.2025.111024_b34) 2022 Wasserthal (10.1016/j.compbiomed.2025.111024_b18) 2023 Perez (10.1016/j.compbiomed.2025.111024_b48) 2017
References_xml	– year: 2021 ident: b21 article-title: Evaluation einer semi-automatischen Segmentierungsmethode für die Volumetrie des renalen Kortex, der Medulla und des gesamten Nierenparenchyms in nativen T1-gewichteten MR-Bildern – year: 2024 ident: b16 article-title: CURVAS challenge dataset: Calibration and uncertainty for multirater volume assessment in multiorgan segmentation publication-title: Zenodo – year: 2024 ident: b24 article-title: Segmenting medical images: From unet to Res-UNet and nnUNet – volume: 97 year: 2024 ident: b38 article-title: Abdomenatlas: a large-scale, detailed-annotated, and multi-center dataset for efficient transfer learning and open algorithmic benchmarking publication-title: Med. Image Anal. – year: 2024 ident: b31 article-title: xLSTM-UNet can be an effective 2D and 3D medical image segmentation backbone with vision-LSTM (ViL) better than its mamba counterpart – year: 2024 ident: b49 article-title: CURVAS: Calibration and uncertainty for multirater volume assessment in multiorgan segmentation publication-title: Zenodo – start-page: 21095 year: 2023 end-page: 21107 ident: b35 article-title: CLIP-driven universal model for organ segmentation and tumor detection publication-title: 2023 IEEE/CVF International Conference on Computer Vision – volume: vol. 70 start-page: 1321 year: 2017 end-page: 1330 ident: b12 article-title: On calibration of modern neural networks publication-title: Proceedings of the 34th International Conference on Machine Learning – start-page: 677 year: 2021 end-page: 688 ident: b3 article-title: Spatially varying label smoothing: Capturing uncertainty from expert annotations publication-title: Proceedings of IPMI 2021 – year: 2022 ident: b11 article-title: Failure detection in medical image classification: A reality check and benchmarking testbed publication-title: Trans. Mach. Learn. Res. – year: 2024 ident: b40 article-title: Touchstone benchmark: Are we on the right way for evaluating AI algorithms for medical segmentation? publication-title: Conference on Neural Information Processing Systems – start-page: 540 year: 2019 end-page: 548 ident: b4 article-title: Improving uncertainty estimation in convolutional neural networks using inter-rater agreement publication-title: Proceedings of MICCAI 2019 – volume: 150 year: 2024 ident: b10 article-title: Trustworthy clinical AI solutions: A unified review of uncertainty quantification in deep learning models for medical image analysis publication-title: Artif. Intell. Med. – start-page: 682 year: 2018 end-page: 690 ident: b5 article-title: On the effect of inter-observer variability for a reliable estimation of uncertainty of medical image segmentation publication-title: Proceedings of MICCAI 2018 – year: 2024 ident: b17 article-title: CURVAS challenge repository, GitHub repository – volume: 23 start-page: 903 year: 2004 end-page: 921 ident: b23 article-title: Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation publication-title: IEEE Trans. Med. Imaging – year: 2018 ident: b47 article-title: A disciplined approach to neural network hyper-parameters: Part 1 – learning rate, batch size, momentum, and weight decay – start-page: 20698 year: 2022 end-page: 20708 ident: b34 article-title: Self-supervised pre-training of swin transformers for 3D medical image analysis publication-title: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition – year: 2023 ident: b36 article-title: AbdomenAtlas, GitHub repository – reference: J. Nixon, M.W. Dusenberry, L. Zhang, G. Jerfel, D. Tran, Measuring Calibration in Deep Learning, in: Proceedings of the IEEE/CVF CVPR Workshops, 2019. – volume: 18 start-page: 203 year: 2021 end-page: 211 ident: b19 article-title: Nnu-net: A self-configuring method for deep learning-based biomedical image segmentation publication-title: Nature Methods – year: 2022 ident: b27 article-title: AMOS: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation – year: 2023 ident: b29 article-title: Make me a BNN: A simple strategy for estimating Bayesian uncertainty from pre-trained models – start-page: 6105 year: 2019 end-page: 6114 ident: b43 article-title: EfficientNet: Rethinking model scaling for convolutional neural networks publication-title: Proceedings of the 36th International Conference on Machine Learning – year: 2024 ident: b25 article-title: QUBIQ: Uncertainty quantification for biomedical image segmentation challenge – volume: 2023 year: 2023 ident: b2 article-title: A soft label method for medical image segmentation with multirater annotations publication-title: Comput. Intell. Neurosci. – volume: 82 year: 2022 ident: b26 article-title: WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image publication-title: Med. Image Anal. – volume: 44 start-page: 6695 year: 2022 end-page: 6714 ident: b28 article-title: AbdomenCT-1K: Is abdominal organ segmentation a solved problem? publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 39 start-page: 1856 year: 2020 end-page: 1867 ident: b42 article-title: UNet++: Redesigning skip connections to exploit multiscale features in image segmentation publication-title: IEEE Trans. Med. Imaging – year: 2021 ident: b20 article-title: Automatische Gewebesegmentierung der Nieren und des Pankreas im Ganzkörper-MRT mittels Deep Learning – year: 2018 ident: b8 article-title: Leveraging uncertainty estimates for predicting segmentation quality – reference: W. Li, A. Yuille, Z. Zhou, How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?, in: The Twelfth International Conference on Learning Representations, 2024. – year: 2022 ident: b7 article-title: Estimating uncertainty in neural networks for cardiac MRI segmentation: A benchmark study publication-title: IEEE Trans. Biomed. Eng. – start-page: 2999 year: 2017 end-page: 3007 ident: b45 article-title: Focal loss for dense object detection publication-title: 2017 IEEE International Conference on Computer Vision – year: 2023 ident: b37 article-title: AbdomenAtlas-8K: Annotating 8 000CT volumes for multi-organ segmentation in three weeks – year: 2023 ident: b18 article-title: TotalSegmentator: Robust segmentation of 104 anatomic structures in CT images publication-title: Radiol.: Artif. Intell. – volume: 76 start-page: 243 year: 2021 end-page: 297 ident: b9 article-title: A review of uncertainty quantification in deep learning: Techniques, applications and challenges publication-title: Inf. Fusion – year: 2017 ident: b48 article-title: The effectiveness of data augmentation in image classification using deep learning – start-page: 424 year: 2016 end-page: 432 ident: b33 article-title: 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation – start-page: 665 year: 2019 end-page: 673 ident: b1 article-title: Let’s agree to disagree: Learning highly debatable multirater labelling publication-title: Proceedings of MICCAI 2019 – volume: 7 start-page: 711 year: 2023 end-page: 718 ident: b14 article-title: Tackling prediction uncertainty in machine learning for healthcare publication-title: Nat. Biomed. Eng. – year: 2024 ident: b30 article-title: Vision-LSTM: xLSTM as generic vision backbone – start-page: 139 year: 2024 end-page: 149 ident: b41 article-title: Average Calibration Error: A Differentiable Loss for Improved Reliability in Image Segmentation – year: 2022 ident: b44 article-title: MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer – volume: 18 start-page: 887 year: 2012 end-page: 895 ident: b6 article-title: Reducing interrater variability and improving health care: a meta-analytical review publication-title: J. Eval. Clin. Pract. – year: 2019 ident: b46 article-title: Decoupled weight decay regularization – volume: 112 start-page: 3211 year: 2023 end-page: 3260 ident: b15 article-title: Classifier calibration: a survey on how to assess and improve predicted class probabilities publication-title: Mach. Learn. – volume: 106 year: 2024 ident: b32 article-title: Unsupervised unpaired multiple fusion adaptation aided with self-attention generative adversarial network for scar tissues segmentation framework publication-title: Inf. Fusion – volume: 28 start-page: 1251 year: 2009 end-page: 1265 ident: b22 article-title: Comparison and evaluation of methods for liver segmentation from CT datasets publication-title: IEEE Trans. Med. Imaging – year: 2018 ident: 10.1016/j.compbiomed.2025.111024_b47 – start-page: 139 year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b41 – year: 2017 ident: 10.1016/j.compbiomed.2025.111024_b48 – volume: 39 start-page: 1856 issue: 6 year: 2020 ident: 10.1016/j.compbiomed.2025.111024_b42 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 – year: 2021 ident: 10.1016/j.compbiomed.2025.111024_b20 – year: 2022 ident: 10.1016/j.compbiomed.2025.111024_b27 – start-page: 682 year: 2018 ident: 10.1016/j.compbiomed.2025.111024_b5 article-title: On the effect of inter-observer variability for a reliable estimation of uncertainty of medical image segmentation – year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b30 – volume: 76 start-page: 243 year: 2021 ident: 10.1016/j.compbiomed.2025.111024_b9 article-title: A review of uncertainty quantification in deep learning: Techniques, applications and challenges publication-title: Inf. Fusion doi: 10.1016/j.inffus.2021.05.008 – ident: 10.1016/j.compbiomed.2025.111024_b13 – year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b49 article-title: CURVAS: Calibration and uncertainty for multirater volume assessment in multiorgan segmentation publication-title: Zenodo – volume: 112 start-page: 3211 issue: 9 year: 2023 ident: 10.1016/j.compbiomed.2025.111024_b15 article-title: Classifier calibration: a survey on how to assess and improve predicted class probabilities publication-title: Mach. Learn. doi: 10.1007/s10994-023-06336-7 – year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b17 – year: 2021 ident: 10.1016/j.compbiomed.2025.111024_b21 – year: 2018 ident: 10.1016/j.compbiomed.2025.111024_b8 – start-page: 6105 year: 2019 ident: 10.1016/j.compbiomed.2025.111024_b43 article-title: EfficientNet: Rethinking model scaling for convolutional neural networks – start-page: 677 year: 2021 ident: 10.1016/j.compbiomed.2025.111024_b3 article-title: Spatially varying label smoothing: Capturing uncertainty from expert annotations – volume: 7 start-page: 711 issue: 6 year: 2023 ident: 10.1016/j.compbiomed.2025.111024_b14 article-title: Tackling prediction uncertainty in machine learning for healthcare publication-title: Nat. Biomed. Eng. doi: 10.1038/s41551-022-00988-x – start-page: 665 year: 2019 ident: 10.1016/j.compbiomed.2025.111024_b1 article-title: Let’s agree to disagree: Learning highly debatable multirater labelling – year: 2022 ident: 10.1016/j.compbiomed.2025.111024_b11 article-title: Failure detection in medical image classification: A reality check and benchmarking testbed publication-title: Trans. Mach. Learn. Res. – start-page: 20698 year: 2022 ident: 10.1016/j.compbiomed.2025.111024_b34 article-title: Self-supervised pre-training of swin transformers for 3D medical image analysis – year: 2023 ident: 10.1016/j.compbiomed.2025.111024_b36 – year: 2022 ident: 10.1016/j.compbiomed.2025.111024_b44 – volume: 23 start-page: 903 issue: 7 year: 2004 ident: 10.1016/j.compbiomed.2025.111024_b23 article-title: Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2004.828354 – volume: 150 year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b10 article-title: Trustworthy clinical AI solutions: A unified review of uncertainty quantification in deep learning models for medical image analysis publication-title: Artif. Intell. Med. doi: 10.1016/j.artmed.2024.102830 – year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b40 article-title: Touchstone benchmark: Are we on the right way for evaluating AI algorithms for medical segmentation? – year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b24 – year: 2019 ident: 10.1016/j.compbiomed.2025.111024_b46 – start-page: 21095 year: 2023 ident: 10.1016/j.compbiomed.2025.111024_b35 article-title: CLIP-driven universal model for organ segmentation and tumor detection – volume: 44 start-page: 6695 issue: 10 year: 2022 ident: 10.1016/j.compbiomed.2025.111024_b28 article-title: AbdomenCT-1K: Is abdominal organ segmentation a solved problem? publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2021.3100536 – volume: vol. 70 start-page: 1321 year: 2017 ident: 10.1016/j.compbiomed.2025.111024_b12 article-title: On calibration of modern neural networks – year: 2023 ident: 10.1016/j.compbiomed.2025.111024_b29 – volume: 106 year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b32 article-title: Unsupervised unpaired multiple fusion adaptation aided with self-attention generative adversarial network for scar tissues segmentation framework publication-title: Inf. Fusion doi: 10.1016/j.inffus.2024.102226 – year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b16 article-title: CURVAS challenge dataset: Calibration and uncertainty for multirater volume assessment in multiorgan segmentation publication-title: Zenodo – start-page: 2999 year: 2017 ident: 10.1016/j.compbiomed.2025.111024_b45 article-title: Focal loss for dense object detection – volume: 18 start-page: 887 issue: 4 year: 2012 ident: 10.1016/j.compbiomed.2025.111024_b6 article-title: Reducing interrater variability and improving health care: a meta-analytical review publication-title: J. Eval. Clin. Pract. doi: 10.1111/j.1365-2753.2011.01705.x – volume: 18 start-page: 203 year: 2021 ident: 10.1016/j.compbiomed.2025.111024_b19 article-title: Nnu-net: A self-configuring method for deep learning-based biomedical image segmentation publication-title: Nature Methods doi: 10.1038/s41592-020-01008-z – volume: 97 year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b38 article-title: Abdomenatlas: a large-scale, detailed-annotated, and multi-center dataset for efficient transfer learning and open algorithmic benchmarking publication-title: Med. Image Anal. doi: 10.1016/j.media.2024.103285 – year: 2023 ident: 10.1016/j.compbiomed.2025.111024_b37 – volume: 82 year: 2022 ident: 10.1016/j.compbiomed.2025.111024_b26 article-title: WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image publication-title: Med. Image Anal. doi: 10.1016/j.media.2022.102642 – volume: 2023 year: 2023 ident: 10.1016/j.compbiomed.2025.111024_b2 article-title: A soft label method for medical image segmentation with multirater annotations publication-title: Comput. Intell. Neurosci. doi: 10.1155/2023/1883597 – ident: 10.1016/j.compbiomed.2025.111024_b39 – start-page: 424 year: 2016 ident: 10.1016/j.compbiomed.2025.111024_b33 – year: 2023 ident: 10.1016/j.compbiomed.2025.111024_b18 article-title: TotalSegmentator: Robust segmentation of 104 anatomic structures in CT images publication-title: Radiol.: Artif. Intell. – year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b25 – year: 2024 ident: 10.1016/j.compbiomed.2025.111024_b31 – year: 2022 ident: 10.1016/j.compbiomed.2025.111024_b7 article-title: Estimating uncertainty in neural networks for cardiac MRI segmentation: A benchmark study publication-title: IEEE Trans. Biomed. Eng. – volume: 28 start-page: 1251 issue: 8 year: 2009 ident: 10.1016/j.compbiomed.2025.111024_b22 article-title: Comparison and evaluation of methods for liver segmentation from CT datasets publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2009.2013851 – start-page: 540 year: 2019 ident: 10.1016/j.compbiomed.2025.111024_b4 article-title: Improving uncertainty estimation in convolutional neural networks using inter-rater agreement
SSID	ssj0004030
Score	2.422448
Snippet	Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models... AbstractDeep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these...
SourceID	hal proquest pubmed crossref elsevier
SourceType	Open Access Repository Aggregation Database Index Database Publisher
StartPage	111024
SubjectTerms	Abdominal CT Artificial Intelligence Bioengineering Calibration Computer Science Deep Learning Engineering Sciences Humans Image Processing, Computer-Assisted - methods Imaging Internal Medicine Life Sciences Medical Imaging Multi-class image segmentation Multiple expert annotations Other Signal and Image processing Uncertainty
Title	Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) challenge results
URI	https://www.clinicalkey.com/#!/content/1-s2.0-S0010482525013769 https://www.clinicalkey.es/playcontent/1-s2.0-S0010482525013769 https://dx.doi.org/10.1016/j.compbiomed.2025.111024 https://www.ncbi.nlm.nih.gov/pubmed/40934552 https://www.proquest.com/docview/3249847878 https://hal.science/hal-05263956
Volume	197
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: ScienceDirect customDbUrl: eissn: 1879-0534 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004030 issn: 0010-4825 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLa6DSFeEHfKZTKIB9CUyUnrOBZPZQwNWAdqt6lvlpM4W8fIpqadCv-R_8TxJU4ZmxhIvESRm-M0Pp_P8eU7xwi96KaZpAXlQUZYHoD1I9ClaBR085zEnBcsZiZQeJvt7CSjEf_cav2oY2HOjllZJvM5P_2vqoYyULYOnf0LdftKoQDuQelwBbXD9UqK19FWqdOrXhXfA7WabX_HzTQUwoHUyRH3jWla6_nsnHr1w_xuDnsCQ3Lw1cUmlWa7d2-w3xvqhYSsPoNlDabrIFAtDnLrkyIM1XYxy9P5jfwB-GQZ9KXdrn9racXQRtO5OvbMj0_rH40FG46_HHofMjjJndDBTH0PNjTLyQBSF77pHY_9k335zcYkTaeHY1lpWlvheoRb7Iiop815Aw4F3cTGSnsDbhm-zgSD8SY2LPs372AXKo60ck9tdoN1_ZL1RuTXhNznHKWnL9bMuCPR1CR0TcLWtIRWIkY5-ImV3vvN0YcmUJd0bEyU-wpHLbOEw4v_1WXjpaVDTdy9bFZkRke7t9BNN63BPQvH26ilyjvoet_p-y6aLKASAxTwAioxoBI3qMQWlbhBJR6XuEElXkQlfmkx-Qp7RGKHyHto793m7sZW4I77CLJOEk0DRRSTKU-zqGAhlUwmRQiuOCZMqijO80LGVPFMkrygEZWSFDQLFQzHGY9MJr_7aLk8KdVDhHnKUgJmJk81cZZzSaRiMU9zBlIkJ20U1o0qTm1WF_EnpbYRr1tf1FHL4GcFgOsKsuwiWVU5u1GJUFSRIGJo8mUBMmBmEoLv52302ku6MbEd617xvc-h8f0n6lTyW71toct0nqcOp_FZ2EbPahQJ8C16w1CW6mRWCZhs8URn70ra6IGFl6-rS3inS2n06B-a8jG60XTuJ2h5Opmpp-hadjYdV5NVtMRGyarrOj8Bmvb-0A
linkProvider	Elsevier
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=Calibration+and+Uncertainty+for+multiRater+Volume+Assessment+in+multiorgan+Segmentation+%28CURVAS%29+challenge+results&rft.jtitle=Computers+in+biology+and+medicine&rft.au=Riera-Mar%C3%ADn%2C+Meritxell&rft.au=O.K.%2C+Sikha&rft.au=Rodr%C3%ADguez-Comas%2C+J%C3%BAlia&rft.au=May%2C+Matthias+Stefan&rft.date=2025-10-01&rft.issn=0010-4825&rft.volume=197&rft.spage=111024&rft_id=info:doi/10.1016%2Fj.compbiomed.2025.111024&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_compbiomed_2025_111024
thumbnail_m	http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F00104825%2FS0010482525X00160%2Fcov150h.gif