Upgraded W-Net with Attention Gates and its Application in Unsupervised 3D Liver Segmentation

TL;DR

This paper introduces an enhanced W-Net architecture with attention gates for unsupervised 3D liver segmentation, achieving high accuracy without relying on manually labeled data.

Contribution

It proposes a novel unsupervised 3D segmentation method using an upgraded W-Net with attention gates and combined loss functions, advancing automated medical image analysis.

Findings

Dice coefficient of 0.88 for liver segmentation

Effective noise suppression in segmentation results

Potential for unsupervised medical image segmentation

Abstract

Segmentation of biomedical images can assist radiologists to make a better diagnosis and take decisions faster by helping in the detection of abnormalities, such as tumors. Manual or semi-automated segmentation, however, can be a time-consuming task. Most deep learning based automated segmentation methods are supervised and rely on manually segmented ground-truth. A possible solution for the problem would be an unsupervised deep learning based approach for automated segmentation, which this research work tries to address. We use a W-Net architecture and modified it, such that it can be applied to 3D volumes. In addition, to suppress noise in the segmentation we added attention gates to the skip connections. The loss for the segmentation output was calculated using soft N-Cuts and for the reconstruction output using SSIM. Conditional Random Fields were used as a post-processing step to fine-tune the results. The proposed method has shown promising results, with a dice coefficient of 0.88 for the liver segmentation compared against manual segmentation.