Kidney and kidney tumor segmentation using a two-stage cascade framework

Chaonan Lin, Rongda Fu, Shaohua Zheng

Keywords: cascade framework, kidney/tumor segmentation, deep learning

Abstract: Automatic segmentation of kidney tumors and lesions in medical images is an essential measure for clinical treatment and diagnosis. In this work, we proposed a two-stage cascade network to segment three hierarchical regions: kidney, kidney tumor and cyst from CT scans. The cascade is designed to decompose the four-class segmentation problem into two segmentation subtasks. The kidney is obtained in the first stage using a modified 3D U-Net called Kidney-Net. In the second stage, we designed a fine segmentation model, which named Masses-Net to segment kidney tumor and cyst based on the kidney which obtained in the first stage. A multi-dimension feature (MDF) module is utilized to learn more spatial and contextual information. The convolutional block attention module (CBAM) also introduced to focus on the important feature. Moreover, we adopted a deep supervision mechanism for regularizing segmentation accuracy and feature learning in the decoding part. Experiments with KiTS2021 validation set show that our proposed method achieve Sørensen-Dice scores of 0.9304, 0.5729 and 0.563 for kidney, masses (tumor and cyst) and kidney tumor, respectively.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/kidney-and-kidney-tumor-segmentation-using-a/code)