Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge

Sathianathen, Niranjan J. and Heller, Nicholas and Tejpaul, Resha and Stai, Bethany and Kalapara, Arveen and Rickman, Jack and Dean, Joshua and Oestreich, Makinna and Blake, Paul and Kaluzniak, Heather and Raza, Shaneabbas and Rosenberg, Joel and Moore, Keenan and Walczak, Edward and Rengel, Zachary and Edgerton, Zach and Vasdev, Ranveer and Peterson, Matthew and McSweeney, Sean and Peterson, Sarah and Papanikolopoulos, Nikolaos and Weight, Christopher (2022) Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge. Frontiers in Digital Health, 3. ISSN 2673-253X

[thumbnail of pubmed-zip/versions/1/package-entries/fdgth-03-797607/fdgth-03-797607.pdf] Text
pubmed-zip/versions/1/package-entries/fdgth-03-797607/fdgth-03-797607.pdf - Published Version

Download (1MB)

Abstract

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.

Item Type: Article
Subjects: European Repository > Multidisciplinary
Divisions: Faculty of Law, Arts and Social Sciences > School of Education
Depositing User: Managing Editor
Date Deposited: 11 Jan 2023 07:14
Last Modified: 01 Mar 2024 03:37
URI: http://go7publish.com/id/eprint/1594

Actions (login required)

View Item
View Item