Multi-Layer Feature Fusion with Cross-Channel Attention-Based U-Net for Kidney Tumor Segmentation

TL;DR

This paper introduces an enhanced U-Net model with multi-layer feature fusion and cross-channel attention for improved kidney tumor segmentation in CT images, achieving state-of-the-art accuracy on the KiTS19 dataset.

Contribution

The study proposes a novel U-Net based architecture incorporating residual connections, multi-layer feature fusion, and cross-channel attention for better renal tumor segmentation.

Findings

Achieved DSC of 0.97 for kidney segmentation

Achieved DSC of 0.96 for tumor segmentation

Outperformed existing models on KiTS19 dataset

Abstract

Renal tumors, especially renal cell carcinoma (RCC), show significant heterogeneity, posing challenges for diagnosis using radiology images such as 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 incorporates skip connections augmented with additional information derived using MFF and CCA. We evaluated our model on the KiTS19 dataset, which contains data from 210 patients. For kidney segmentation, our model achieves a Dice Similarity Coefficient (DSC) of 0.97 and a Jaccard index (JI) of 0.95. For renal tumor segmentation, our model achieves a DSC of 0.96 and a JI of 0.91. Based on a comparison of available DSC scores, our model outperforms the current leading models.