Multi-layer feature fusion with cross-channel attention-based u-net for kidney tumor segmentation

Abstract

Renal tumors, especially renal cell carcinoma(RCC), show significant heterogeneity, posing challenges for diagnosis using radiology images: MRI, echocardiograms, and CT scans. U-Net based deep learning techniques are emerging as a promising approach for automated medical image segmentation for minimally invasive diagnosis of renal tumors. However, current techniques need further improvements in accuracy to become clinically useful to radiologists. In this study, we present an improved U-Net based model for end-to-end automated semantic segmentation of CT scan images to identify renal tumors. The model uses residual connections across convolution layers, integrates a multi-layer feature fusion (MFF) and cross-channel attention (CCA) within encoder-blocks, and skip-connection augmented with additional information derived using MFF and CCA. We evaluated our model on the KiTS19 dataset using 210 patients’ data. For kidney segmentation, our model achieves Dice Similarity Coefficient (DSC) of 0.97 and Jaccard index (JI) of 0.95. For renal tumor segmentation, our model achieves DSC of 0.96, and JI of 0.91. Based upon the comparison of available DSC scores, our model outperforms the current leading models.