The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge |
| |
| Institution: | 1. University of Minnesota, Minneapolis, United States;2. German Cancer Research Center (DKFZ), Heidelberg, Germany;3. University of Heidelberg, Heidelberg, Germany;4. PingAn Technology Co., Ltd, Shanghai, China;5. Shanghai United Imaging Intelligence Inc., Shanghai, China;6. Southern Medical University, Guangzhou, China;7. Peking University First Hospital, Beijing, China;8. Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;9. University of Chinese Academy of Sciences, Beijing, China;10. Southeast University, Nanjing, China;11. AI Lab, Lenovo Research, Beijing, China;12. School of Science, Nanjing University of Science and Technology, Nanjing, China;13. University of Melbourne, Melbourne, Australia;14. Brigham Young University, Provo, United States;15. University of North Dakota, Grand Forks, United States;p. Carleton College, Northfield, United States;1. Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal;2. ICVS/3B''s—PT Government Associate Laboratory, Braga/Guimarães, Portugal;3. Algoritmi Center, School of Engineering, University of Minho, Guimarães, Portugal;4. Lab on Cardiovascular Imaging & Dynamics, Department of Cardiovascular Sciences, KULeuven—University of Leuven, Leuven, Belgium;5. Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Faculdade de Engenharia, Universidade do Porto, Portugal;6. 2Ai—Polytechnic Institute of Cávado and Ave, Barcelos, Portugal;1. LIST, Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, Nanjing, China;2. Univ Rennes, Inserm, LTSI - UMR1099, Rennes F-35000, France;3. Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Electronics, Beijing Institute of Technology, Beijing, China;4. Department of Radiology, the First Affiliated Hospital of Nanjing Medical University, Nanjing, China;5. Centre de Recherche en Information Biomédicale Sino-Français (CRIBs), France;6. Department of Urology, the First Affiliated Hospital of Nanjing Medical University, Nanjing, China;7. Department of Medical Biophysics, University of Western Ontario, London, ON, Canada;1. Sungkyunkwan University School of Medicine, Seoul, Korea;2. Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea;3. School of Medicine, Boston University, Boston, MA 02118, USA |
| |
| Abstract: | There is a large body of literature linking anatomic and geometric characteristics of kidney tumors to perioperative and oncologic outcomes. Semantic segmentation of these tumors and their host kidneys is a promising tool for quantitatively characterizing these lesions, but its adoption is limited due to the manual effort required to produce high-quality 3D segmentations of these structures. Recently, methods based on deep learning have shown excellent results in automatic 3D segmentation, but they require large datasets for training, and there remains little consensus on which methods perform best. The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was a competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) which sought to address these issues and stimulate progress on this automatic segmentation problem. A training set of 210 cross sectional CT images with kidney tumors was publicly released with corresponding semantic segmentation masks. 106 teams from five continents used this data to develop automated systems to predict the true segmentation masks on a test set of 90 CT images for which the corresponding ground truth segmentations were kept private. These predictions were scored and ranked according to their average Sørensen-Dice coefficient between the kidney and tumor across all 90 cases. The winning team achieved a Dice of 0.974 for kidney and 0.851 for tumor, approaching the inter-annotator performance on kidney (0.983) but falling short on tumor (0.923). This challenge has now entered an “open leaderboard” phase where it serves as a challenging benchmark in 3D semantic segmentation. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
