A Two-stage Cascaded Deep Neural Network with Multi-decoding Paths for Kidney Tumor Segmentation

Tian He, Zhen Zhang, Chenhao Pei, Liqin Huang

Keywords: Kidney, Kidney tumor Segmentation, Cascaded deep neural network, Multi-decoding

Abstract: Kidney cancer is aggressive cancer that accounts for a large proportion of adult malignancies. Computed tomography (CT) imaging is an effective tool for kidney cancer diagnosis. Automatic and accurate kidney and kidney tumor segmentation in CT scans is crucial for treatment and surgery planning. However, kidney tumors and cysts have various morphologies, with blurred edges and unpredictable positions. Therefore, precise segmentation of tumors and cysts faces a huge challenge. Consider these difficulties, we propose a cascaded deep neural network, which first accurately locate the kidney area through 2D U-Net, and then segment kidneys, kidney tumors and renal cysts through Multi-decoding Segmentation Network(MDS-Net) from the ROI of the kidney. We evaluated our method on the 2021 Kidney and Kidney Tumor Segmentation Challenge (KiTS21) dataset. The method dice score achieves 93.40\%, 68.32\%, 64.26\% for kidney, kidney mass, and kidney tumors, respectively. The model of cascade network proposed in this paper has a promising application prospect in kidney cancer diagnosis.