AttResDU-Net: Medical Image Segmentation Using Attention-based Residual Double U-Net

TL;DR

This paper introduces AttResDU-Net, an advanced neural network architecture with attention and residual connections, significantly improving automatic medical image segmentation accuracy across multiple datasets.

Contribution

The paper proposes AttResDU-Net, a novel architecture combining attention gates and residual connections to enhance segmentation performance in medical imaging tasks.

Findings

Achieved high Dice scores on three datasets: 94.35%, 91.68%, 92.45%.

Improved focus on target regions with attention gates.

Facilitated training of deeper models with residual connections.

Abstract

Manually inspecting polyps from a colonoscopy for colorectal cancer or performing a biopsy on skin lesions for skin cancer are time-consuming, laborious, and complex procedures. Automatic medical image segmentation aims to expedite this diagnosis process. However, numerous challenges exist due to significant variations in the appearance and sizes of objects with no distinct boundaries. This paper proposes an attention-based residual Double U-Net architecture (AttResDU-Net) that improves on the existing medical image segmentation networks. Inspired by the Double U-Net, this architecture incorporates attention gates on the skip connections and residual connections in the convolutional blocks. The attention gates allow the model to retain more relevant spatial information by suppressing irrelevant feature representation from the down-sampling path for which the model learns to focus on target regions of varying shapes and sizes. Moreover, the residual connections help to train deeper models by ensuring better gradient flow. We conducted experiments on three datasets: CVC Clinic-DB, ISIC 2018, and the 2018 Data Science Bowl datasets and achieved Dice Coefficient scores of 94.35%, 91.68% and 92.45% respectively. Our results suggest that AttResDU-Net can be facilitated as a reliable method for automatic medical image segmentation in practice.