Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge
Purpose: Clinicians rely on imaging features to calculate complexity of renal masses based on validated scoring systems. These scoring methods are labor-intensive and are subjected to interobserver variability. Artificial intelligence has been increasingly utilized by the medical community to solve...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Digital Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fdgth.2021.797607/full |
| _version_ | 1811190556638838784 |
|---|---|
| author | Niranjan J. Sathianathen Nicholas Heller Resha Tejpaul Bethany Stai Arveen Kalapara Jack Rickman Joshua Dean Makinna Oestreich Paul Blake Heather Kaluzniak Shaneabbas Raza Joel Rosenberg Keenan Moore Edward Walczak Zachary Rengel Zach Edgerton Ranveer Vasdev Matthew Peterson Sean McSweeney Sarah Peterson Nikolaos Papanikolopoulos Christopher Weight |
| author_facet | Niranjan J. Sathianathen Nicholas Heller Resha Tejpaul Bethany Stai Arveen Kalapara Jack Rickman Joshua Dean Makinna Oestreich Paul Blake Heather Kaluzniak Shaneabbas Raza Joel Rosenberg Keenan Moore Edward Walczak Zachary Rengel Zach Edgerton Ranveer Vasdev Matthew Peterson Sean McSweeney Sarah Peterson Nikolaos Papanikolopoulos Christopher Weight |
| author_sort | Niranjan J. Sathianathen |
| collection | DOAJ |
| description | Purpose: Clinicians rely on imaging features to calculate complexity of renal masses based on validated scoring systems. These scoring methods are labor-intensive and are subjected to interobserver variability. Artificial intelligence has been increasingly utilized by the medical community to solve such issues. However, developing reliable algorithms is usually time-consuming and costly. We created an international community-driven competition (KiTS19) to develop and identify the best system for automatic segmentation of kidneys and kidney tumors in contrast CT and report the results.Methods: A training and test set of CT scans that was manually annotated by trained individuals were generated from consecutive patients undergoing renal surgery for whom demographic, clinical and outcome data were available. The KiTS19 Challenge was a machine learning competition hosted on grand-challenge.org in conjunction with an international conference. Teams were given 3 months to develop their algorithm using a full-annotated training set of images and an unannotated test set was released for 2 weeks from which average Sørensen-Dice coefficient between kidney and tumor regions were calculated across all 90 test cases.Results: There were 100 valid submissions that were based on deep neural networks but there were differences in pre-processing strategies, architectural details, and training procedures. The winning team scored a 0.974 kidney Dice and a 0.851 tumor Dice resulting in 0.912 composite score. Automatic segmentation of the kidney by the participating teams performed comparably to expert manual segmentation but was less reliable when segmenting the tumor.Conclusion: Rapid advancement in automated semantic segmentation of kidney lesions is possible with relatively high accuracy when the data is released publicly, and participation is incentivized. We hope that our findings will encourage further research that would enable the potential of adopting AI into the medical field. |
| first_indexed | 2024-04-11T14:51:59Z |
| format | Article |
| id | doaj.art-a5f01bacc11b4638ba993e895eb423f9 |
| institution | Directory Open Access Journal |
| issn | 2673-253X |
| language | English |
| last_indexed | 2024-04-11T14:51:59Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Digital Health |
| spelling | doaj.art-a5f01bacc11b4638ba993e895eb423f92022-12-22T04:17:23ZengFrontiers Media S.A.Frontiers in Digital Health2673-253X2022-01-01310.3389/fdgth.2021.797607797607Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International ChallengeNiranjan J. Sathianathen0Nicholas Heller1Resha Tejpaul2Bethany Stai3Arveen Kalapara4Jack Rickman5Joshua Dean6Makinna Oestreich7Paul Blake8Heather Kaluzniak9Shaneabbas Raza10Joel Rosenberg11Keenan Moore12Edward Walczak13Zachary Rengel14Zach Edgerton15Ranveer Vasdev16Matthew Peterson17Sean McSweeney18Sarah Peterson19Nikolaos Papanikolopoulos20Christopher Weight21Department of Urology, University of Minnesota, Minneapolis, MN, United StatesDepartment of Computer Science & Engineering, University of Minnesota, Minneapolis, MN, United StatesDepartment of Computer Science & Engineering, University of Minnesota, Minneapolis, MN, United StatesDepartment of Computer Science & Engineering, University of Minnesota, Minneapolis, MN, United StatesDepartment of Urology, University of Minnesota, Minneapolis, MN, United StatesDepartment of Computer Science & Engineering, University of Minnesota, Minneapolis, MN, United StatesDepartment of Computer Science & Engineering, University of Minnesota, Minneapolis, MN, United StatesDepartment of Urology, University of Minnesota, Minneapolis, MN, United StatesDepartment of Urology, University of Minnesota, Minneapolis, MN, United StatesDepartment of Urology, University of North Dakota, Grand Forks, ND, United StatesDepartment of Urology, University of North Dakota, Grand Forks, ND, United StatesDepartment of Urology, University of Minnesota, Minneapolis, MN, United StatesDepartment of Undergraduate Studies, Carleton College, Northfield, MN, United StatesDepartment of Urology, University of Minnesota, Minneapolis, MN, United StatesDepartment of Computer Science & Engineering, University of Minnesota, Minneapolis, MN, United StatesDepartment of Urology, University of Minnesota, Minneapolis, MN, United StatesDepartment of Urology, University of Minnesota, Minneapolis, MN, United StatesDepartment of Urology, University of Minnesota, Minneapolis, MN, United StatesDepartment of Urology, University of Minnesota, Minneapolis, MN, United StatesDepartment of Undergraduate Studies, Brigham Young University, Provo, UT, United StatesDepartment of Computer Science & Engineering, University of Minnesota, Minneapolis, MN, United StatesDepartment of Urology, University of Minnesota, Minneapolis, MN, United StatesPurpose: Clinicians rely on imaging features to calculate complexity of renal masses based on validated scoring systems. These scoring methods are labor-intensive and are subjected to interobserver variability. Artificial intelligence has been increasingly utilized by the medical community to solve such issues. However, developing reliable algorithms is usually time-consuming and costly. We created an international community-driven competition (KiTS19) to develop and identify the best system for automatic segmentation of kidneys and kidney tumors in contrast CT and report the results.Methods: A training and test set of CT scans that was manually annotated by trained individuals were generated from consecutive patients undergoing renal surgery for whom demographic, clinical and outcome data were available. The KiTS19 Challenge was a machine learning competition hosted on grand-challenge.org in conjunction with an international conference. Teams were given 3 months to develop their algorithm using a full-annotated training set of images and an unannotated test set was released for 2 weeks from which average Sørensen-Dice coefficient between kidney and tumor regions were calculated across all 90 test cases.Results: There were 100 valid submissions that were based on deep neural networks but there were differences in pre-processing strategies, architectural details, and training procedures. The winning team scored a 0.974 kidney Dice and a 0.851 tumor Dice resulting in 0.912 composite score. Automatic segmentation of the kidney by the participating teams performed comparably to expert manual segmentation but was less reliable when segmenting the tumor.Conclusion: Rapid advancement in automated semantic segmentation of kidney lesions is possible with relatively high accuracy when the data is released publicly, and participation is incentivized. We hope that our findings will encourage further research that would enable the potential of adopting AI into the medical field.https://www.frontiersin.org/articles/10.3389/fdgth.2021.797607/fullkidney tumorssemantic segmentationmedical imagesrenal massct scans |
| spellingShingle | Niranjan J. Sathianathen Nicholas Heller Resha Tejpaul Bethany Stai Arveen Kalapara Jack Rickman Joshua Dean Makinna Oestreich Paul Blake Heather Kaluzniak Shaneabbas Raza Joel Rosenberg Keenan Moore Edward Walczak Zachary Rengel Zach Edgerton Ranveer Vasdev Matthew Peterson Sean McSweeney Sarah Peterson Nikolaos Papanikolopoulos Christopher Weight Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge Frontiers in Digital Health kidney tumors semantic segmentation medical images renal mass ct scans |
| title | Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge |
| title_full | Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge |
| title_fullStr | Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge |
| title_full_unstemmed | Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge |
| title_short | Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge |
| title_sort | automatic segmentation of kidneys and kidney tumors the kits19 international challenge |
| topic | kidney tumors semantic segmentation medical images renal mass ct scans |
| url | https://www.frontiersin.org/articles/10.3389/fdgth.2021.797607/full |
| work_keys_str_mv | AT niranjanjsathianathen automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT nicholasheller automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT reshatejpaul automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT bethanystai automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT arveenkalapara automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT jackrickman automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT joshuadean automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT makinnaoestreich automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT paulblake automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT heatherkaluzniak automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT shaneabbasraza automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT joelrosenberg automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT keenanmoore automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT edwardwalczak automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT zacharyrengel automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT zachedgerton automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT ranveervasdev automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT matthewpeterson automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT seanmcsweeney automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT sarahpeterson automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT nikolaospapanikolopoulos automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge AT christopherweight automaticsegmentationofkidneysandkidneytumorsthekits19internationalchallenge |