Cascaded U-net for Kidney and Tumor Segmentation from CT volumes
Contrast-enhanced Computed Tomography (CT) imaging is most useful tool in diagnosing and locating the kidney lesions. An automated kidney and tumor segmentation are very helpful because it can provide the precise information about the location and size of lesions which can be used in quantitative analysis of the tumor. Semantic segmentation of kidney is very challenging as it requires large dataset for training and its morphological heterogeneity makes it a difficult problem. The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was a competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) has publicly released a 210 cross sectional CT images with kidney tumors along with corresponding semantic segmentation masks. In this work we proposed a novel two stage 2D segmentation method to automatically segment kidney and tumor using the combination of Unet++ and squeeze and excite approach. The proposed network is trained in keras framework. Our method achieves a dice score of 0.98 and 0.965 with kidney and tumor respectively on training data and the results demonstrates the accuracy of our proposed method. Proposed method was able to segment kidney and tumor from abdominal CT images which can provide the exact location and size of the tumor. This information can also be used to analyze treatment response.