55
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      The Medical Segmentation Decathlon

      research-article
      1 , , 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 11 , 5 , 15 , 15 , 16 , 16 , 17 , 11 , 18 , 17 , 19 , 16 , 1 , 1 , 20 , 11 , 1 , 9 , 21 , 22 , 23 , 21 , 24 , 25 , 26 , 27 , 25 , 28 , 29 , 30 , 31 , 32 , 29 , 33 , 22 , 33 , 34 , 31 , 35 , 36 , 22 , 35 , 27 , 37 , 38 , 39 , 24 , 23 , 40 , 2 , 3 , 4 , 41 , 1
      Nature Communications
      Nature Publishing Group UK
      Three-dimensional imaging, Translational research

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)—a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training.

          Abstract

          International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Here, the authors present the results of a biomedical image segmentation challenge, showing that a method capable of performing well on multiple tasks will generalize well to a previously unseen task.

          Related collections

          Most cited references34

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          Deep Residual Learning for Image Recognition

            Bookmark
            • Record: found
            • Abstract: not found
            • Book Chapter: not found

            U-Net: Convolutional Networks for Biomedical Image Segmentation

              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Plasma Hsp90 levels in patients with systemic sclerosis and relation to lung and skin involvement: a cross-sectional and longitudinal study

              Our previous study demonstrated increased expression of Heat shock protein (Hsp) 90 in the skin of patients with systemic sclerosis (SSc). We aimed to evaluate plasma Hsp90 in SSc and characterize its association with SSc-related features. Ninety-two SSc patients and 92 age-/sex-matched healthy controls were recruited for the cross-sectional analysis. The longitudinal analysis comprised 30 patients with SSc associated interstitial lung disease (ILD) routinely treated with cyclophosphamide. Hsp90 was increased in SSc compared to healthy controls. Hsp90 correlated positively with C-reactive protein and negatively with pulmonary function tests: forced vital capacity and diffusing capacity for carbon monoxide (DLCO). In patients with diffuse cutaneous (dc) SSc, Hsp90 positively correlated with the modified Rodnan skin score. In SSc-ILD patients treated with cyclophosphamide, no differences in Hsp90 were found between baseline and after 1, 6, or 12 months of therapy. However, baseline Hsp90 predicts the 12-month change in DLCO. This study shows that Hsp90 plasma levels are increased in SSc patients compared to age-/sex-matched healthy controls. Elevated Hsp90 in SSc is associated with increased inflammatory activity, worse lung functions, and in dcSSc, with the extent of skin involvement. Baseline plasma Hsp90 predicts the 12-month change in DLCO in SSc-ILD patients treated with cyclophosphamide.
                Bookmark

                Author and article information

                Contributors
                michela.antonelli@kcl.ac.uk
                Journal
                Nat Commun
                Nat Commun
                Nature Communications
                Nature Publishing Group UK (London )
                2041-1723
                15 July 2022
                15 July 2022
                2022
                : 13
                : 4128
                Affiliations
                [1 ]GRID grid.13097.3c, ISNI 0000 0001 2322 6764, School of Biomedical Engineering & Imaging Sciences, , King’s College London, ; London, UK
                [2 ]GRID grid.7497.d, ISNI 0000 0004 0492 0584, Div. Computer Assisted Medical Interventions, , German Cancer Research Center (DKFZ), ; Heidelberg, Germany
                [3 ]GRID grid.7497.d, ISNI 0000 0004 0492 0584, HI Helmholtz Imaging, , German Cancer Research Center (DKFZ), ; Heidelberg, Germany
                [4 ]GRID grid.7700.0, ISNI 0000 0001 2190 4373, Faculty of Mathematics and Computer Science, , University of Heidelberg, ; Heidelberg, Germany
                [5 ]GRID grid.25879.31, ISNI 0000 0004 1936 8972, Center for Biomedical Image Computing and Analytics (CBICA), , University of Pennsylvania, ; Philadelphia, PA USA
                [6 ]GRID grid.25879.31, ISNI 0000 0004 1936 8972, Department of Radiology, Perelman School of Medicine, , University of Pennsylvania, ; Philadelphia, PA USA
                [7 ]GRID grid.25879.31, ISNI 0000 0004 1936 8972, Department of Pathology and Laboratory Medicine, Perelman School of Medicine, , University of Pennsylvania, ; Philadelphia, PA USA
                [8 ]GRID grid.48336.3a, ISNI 0000 0004 1936 8075, Center for Biomedical Informatics and Information Technology, , National Cancer Institute (NIH), ; Bethesda, MD USA
                [9 ]GRID grid.7497.d, ISNI 0000 0004 0492 0584, Div. Biostatistics, , German Cancer Research Center (DKFZ), ; Heidelberg, Germany
                [10 ]GRID grid.152326.1, ISNI 0000 0001 2264 7217, Electrical Engineering and Computer Science, , Vanderbilt University, ; Nashville, TN USA
                [11 ]GRID grid.10417.33, ISNI 0000 0004 0444 9382, Radboud University Medical Center, , Radboud Institute for Health Sciences, ; Nijmegen, The Netherlands
                [12 ]GRID grid.7400.3, ISNI 0000 0004 1937 0650, Quantitative Biomedicine, , University of Zurich, ; Zurich, Switzerland
                [13 ]GRID grid.498210.6, ISNI 0000 0004 5999 1726, DeepMind, ; London, UK
                [14 ]GRID grid.410305.3, ISNI 0000 0001 2194 5650, Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, , National Institutes of Health Clinical Center (NIH), ; Bethesda, MD USA
                [15 ]GRID grid.6936.a, ISNI 0000000123222966, Department of Informatics, , Technische Universität München, ; München, Germany
                [16 ]GRID grid.51462.34, ISNI 0000 0001 2171 9952, Department of Radiology, , Memorial Sloan Kettering Cancer Center, ; New York, NY USA
                [17 ]GRID grid.412807.8, ISNI 0000 0004 1936 9916, Department of Psychiatry & Behavioral Sciences, , Vanderbilt University Medical Center, ; Nashville, TN USA
                [18 ]GRID grid.51462.34, ISNI 0000 0001 2171 9952, Department of Surgery, , Memorial Sloan Kettering Cancer Center, ; New York, NY USA
                [19 ]GRID grid.168010.e, ISNI 0000000419368956, Department of Radiology, , Stanford University, ; Stanford, CA USA
                [20 ]GRID grid.183158.6, ISNI 0000 0004 0435 3292, Department of Computer Science and Software Engineering, , École Polytechnique de Montréal, ; Montréal, QC Canada
                [21 ]GRID grid.7247.6, ISNI 0000000419370714, Universidad de los Andes, ; Bogota, Colombia
                [22 ]VUNO Inc., Seoul, Korea
                [23 ]Tencent Jarvis Lab, Shenzhen, China
                [24 ]GRID grid.12527.33, ISNI 0000 0001 0662 3178, Department of Automation, , Tsinghua University, ; Beijing, China
                [25 ]GRID grid.9227.e, ISNI 0000000119573309, Shenzhen Institute of Advanced Technology, , Chinese Academy of Sciences, ; Shenzhen, China
                [26 ]GRID grid.7497.d, ISNI 0000 0004 0492 0584, HI Applied Computer Vision Lab, Division of Medical Image Computing, , German Cancer Research Center (DKFZ), ; Heidelberg, Germany
                [27 ]GRID grid.12955.3a, ISNI 0000 0001 2264 7233, Department of Computer Science, , Xiamen University, ; Xiamen, China
                [28 ]Kakao Brain, Seongnam-si, Republic of Korea
                [29 ]Cerebriu A/S, Copenhagen, Denmark
                [30 ]GRID grid.5253.1, ISNI 0000 0001 0328 4908, Pattern Analysis and Learning Group, Department of Radiation Oncology, , Heidelberg University Hospital, ; Heidelberg, Germany
                [31 ]GRID grid.1957.a, ISNI 0000 0001 0728 696X, Institute of Imaging & Computer Vision, , RWTH Aachen University, ; Aachen, Germany
                [32 ]GRID grid.428590.2, ISNI 0000 0004 0496 8246, Fraunhofer Institute for Digital Medicine MEVIS, ; Bremen, Germany
                [33 ]GRID grid.5254.6, ISNI 0000 0001 0674 042X, Department of Computer Science, , University of Copenhagen, ; Copenhagen, Denmark
                [34 ]MaaDoTaa.com, San Diego, CA USA
                [35 ]GRID grid.5252.0, ISNI 0000 0004 1936 973X, Lab for Artificial Intelligence in Medical Imaging (AI-Med), Department of Child and Adolescent Psychiatry, , University Hospital, ; LMU München, Germany
                [36 ]GRID grid.16821.3c, ISNI 0000 0004 0368 8293, MoE Key Lab of Artificial Intelligence, AI Institute, , Shanghai Jiao Tong University, ; Shanghai, China
                [37 ]GRID grid.22069.3f, ISNI 0000 0004 0369 6365, Shanghai Key Laboratory of Multidimensional Information Processing, , East China Normal University, ; Shanghai, China
                [38 ]GRID grid.21107.35, ISNI 0000 0001 2171 9311, Johns Hopkins University, ; Baltimore, MD USA
                [39 ]GRID grid.451133.1, ISNI 0000 0004 0458 4453, NVIDIA, ; Santa Clara, CA USA
                [40 ]GRID grid.410356.5, ISNI 0000 0004 1936 8331, School of Computing/Department of Biomedical and Molecular Sciences, , Queen’s University, ; Kingston, ON Canada
                [41 ]GRID grid.7700.0, ISNI 0000 0001 2190 4373, Medical Faculty, , University of Heidelberg, ; Heidelberg, Germany
                Author information
                http://orcid.org/0000-0002-3005-4523
                http://orcid.org/0000-0003-4363-1876
                http://orcid.org/0000-0001-8734-6482
                http://orcid.org/0000-0002-1810-0267
                http://orcid.org/0000-0001-5733-2127
                http://orcid.org/0000-0003-1554-1291
                http://orcid.org/0000-0003-4136-5690
                http://orcid.org/0000-0002-6554-0310
                http://orcid.org/0000-0001-6753-3221
                http://orcid.org/0000-0002-6876-5507
                http://orcid.org/0000-0002-1076-7948
                http://orcid.org/0000-0003-2309-8517
                http://orcid.org/0000-0002-5940-0063
                http://orcid.org/0000-0003-0075-979X
                http://orcid.org/0000-0002-6626-2463
                http://orcid.org/0000-0002-1672-2185
                http://orcid.org/0000-0002-0358-4692
                http://orcid.org/0000-0003-0225-7662
                http://orcid.org/0000-0003-2195-2847
                http://orcid.org/0000-0003-1284-2558
                Article
                30695
                10.1038/s41467-022-30695-9
                9287542
                35840566
                6fe30237-4d69-4543-ab53-c868e069bcfb
                © The Author(s) 2022

                Open Access This 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 license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license 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 license, visit http://creativecommons.org/licenses/by/4.0/.

                History
                : 16 August 2021
                : 13 May 2022
                Categories
                Article
                Custom metadata
                © The Author(s) 2022

                Uncategorized
                three-dimensional imaging,translational research
                Uncategorized
                three-dimensional imaging, translational research

                Comments

                Comment on this article

                scite_
                0
                0
                0
                0
                Smart Citations
                0
                0
                0
                0
                Citing PublicationsSupportingMentioningContrasting
                View Citations

                See how this article has been cited at scite.ai

                scite shows how a scientific paper has been cited by providing the context of the citation, a classification describing whether it supports, mentions, or contrasts the cited claim, and a label indicating in which section the citation was made.

                Similar content108

                Cited by106

                Most referenced authors9,402