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

Authors
Santini, Gianmarco
Moreau, Noémie
Rubeaux, Mathieu

Issue Date
2019

Publisher
University of Minnesota Libraries Publishing

Type
Article

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 ensambling operation is added at the end to combine prediction results from previous stages reducing the variance between single models. The results obtained are promising and could be improved by incorporating prior knowledge about the benign cysts that regularly lower the tumor segmentation results.

Identifiers
doi: 10.24926/548719.023