Extraction of Kidney Anatomy based on a 3D U-ResNet with Overlap-Tile Strategy

Jannes Adam, Niklas Agethen, Robert Bohnsack, René Finzel, Timo Günnemann, Lena Philipp, Marcel Plutat, Markus Rink, Tingting Xue, Felix Thielke, Hans Meine

Keywords: U-ResNet, residual connection, medical image segmentation

Abstract: In this paper we present our approach for the KiTS21 Challenge. The goal is to automatically segment kidney, (renal) tumors and (renal) cysts based on 3D computed tomography (CT) images of the abdomen. We were provided with 300 cases for this purpose. To solve this problem we used a 3D U-ResNet with pre- and postprocessing and data augmentation. The preprocessing includes implementation of the overlap-tile strategy by preparing the input patches, while the postprocessing was applied to remove false-positive artefacts.