3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes

TL;DR

This paper introduces a novel 3D deeply supervised network for automatic liver segmentation from CT volumes, combining end-to-end learning with deep supervision and CRF refinement, achieving fast and accurate results.

Contribution

The paper proposes a 3D deeply supervised network with deep supervision and CRF refinement for improved liver segmentation from CT images.

Findings

Achieves competitive segmentation accuracy with state-of-the-art methods.

Offers faster processing speed compared to existing approaches.

Demonstrates effective optimization and discrimination capabilities.

Abstract

Automatic liver segmentation from CT volumes is a crucial prerequisite yet challenging task for computer-aided hepatic disease diagnosis and treatment. In this paper, we present a novel 3D deeply supervised network (3D DSN) to address this challenging task. The proposed 3D DSN takes advantage of a fully convolutional architecture which performs efficient end-to-end learning and inference. More importantly, we introduce a deep supervision mechanism during the learning process to combat potential optimization difficulties, and thus the model can acquire a much faster convergence rate and more powerful discrimination capability. On top of the high-quality score map produced by the 3D DSN, a conditional random field model is further employed to obtain refined segmentation results. We evaluated our framework on the public MICCAI-SLiver07 dataset. Extensive experiments demonstrated that our method achieves competitive segmentation results to state-of-the-art approaches with a much faster processing speed.