Automated Kidney Tumor Segmentation with Convolution and Transformer Network

Zhiqiang Shen, Hua Yang, Zhen Zhang, Shaohua Zheng

Keywords: Convolutional neural network, Kidney tumor, Transformer

Abstract: Kidney cancer is one of the most common malignancies worldwide. Early diagnosis is an effective way to reduce the mortality and automated segmentation of kidney tumor in computed tomography scans is an important way to assisted kidney cancer diagnosis. In this paper, we propose a convolution-and-transformer network (COTRNet) for end to end kidney, kidney tumor, and kidney cyst segmentation. COTRNet is an encoder-decoder architecture where the encoder and the decoder are connected by skip connections. The encoder consists of four convolution-transformer layers to learn multi-scale features which have local and global receptive fields crucial for accurate segmentation. In addition, we leverage pretrained weights and deep supervision to further improve segmentation performance. Experimental results on the 2021 kidney and kidney tumor segmentation challenge demonstrated that our method achieve dice scores of 92.28%, 55.28%, and 50.56% for kidney, masses, and tumor, respectively.