Kidney tumor segmentation using an ensembling multi-stage deep learning approach. A contribution to the KiTS19 challenge

TL;DR

This paper presents an automatic multi-stage deep learning approach using Residual UNet and ensembling to accurately segment kidneys and tumors in CT scans, achieving high Dice scores and aiding kidney cancer treatment planning.

Contribution

It introduces a novel multi-stage 2.5D deep learning segmentation method with ensembling, improving accuracy for kidney and tumor delineation in the KiTS19 challenge.

Findings

Achieved mean Dice scores of 0.96 for kidneys and 0.74 for tumors.

Ensembling reduced variance and improved segmentation robustness.

Results demonstrate promising accuracy, with potential improvements by integrating prior knowledge.

Abstract

Precise characterization of the kidney and kidney tumor characteristics is of outmost importance in the context of kidney cancer treatment, especially for nephron sparing surgery which requires a precise localization of the tissues to be removed. The need for accurate and automatic delineation tools is at the origin of the KiTS19 challenge. It aims at accelerating the research and development in this field to aid prognosis and treatment planning by providing a characterized dataset of 300 CT scans to be segmented. To address the challenge, we proposed an automatic, multi-stage, 2.5D deep learning-based segmentation approach based on Residual UNet framework. An ensembling operation is added at the end to combine prediction results from previous stages reducing the variance between single models. Our neural network segmentation algorithm reaches a mean Dice score of 0.96 and 0.74 for kidney and kidney tumors, respectively on 90 unseen test cases. The results obtained are promising and could be improved by incorporating prior knowledge about the benign cysts that regularly lower the tumor segmentation results.