Automatic 3D Liver Segmentation Using Sparse Representation of Global and Local Image Information via Level Set Formulation

TL;DR

This paper introduces a novel level set-based framework for automatic liver segmentation that leverages sparse representations of global and local image features, achieving superior accuracy on a public benchmark dataset.

Contribution

It presents a new cost function integrating sparse global and local image information via learned dictionaries for improved liver segmentation.

Findings

Achieved 79.6% segmentation accuracy, outperforming existing methods.

Utilized K-SVD to learn dictionaries from MICCAI-SLiver07 database.

Demonstrated the effectiveness of combining global and local features in segmentation.

Abstract

In this paper, a novel framework for automated liver segmentation via a level set formulation is presented. A sparse representation of both global (region-based) and local (voxel-wise) image information is embedded in a level set formulation to innovate a new cost function. Two dictionaries are build: A region-based feature dictionary and a voxel-wise dictionary. These dictionaries are learned, using the K-SVD method, from a public database of liver segmentation challenge (MICCAI-SLiver07). The learned dictionaries provide prior knowledge to the level set formulation. For the quantitative evaluation, the proposed method is evaluated using the testing data of MICCAI-SLiver07 database. The results are evaluated using different metric scores computed by the challenge organizers. The experimental results demonstrate the superiority of the proposed framework by achieving the highest segmentation accuracy (79.6\%) in comparison to the state-of-the-art methods.