AS2LS: Adaptive Anatomical Structure-Based Two-Layer Level Set Framework for Medical Image Segmentation.

Area of Science:

• Medical Image Analysis
• Computer Vision
• Biomedical Engineering

Background:

• Medical image segmentation is challenging due to intricate structures, intensity variations, noise, and blurred edges.
• Existing segmentation algorithms offer improvements but still have limitations in handling complex medical images.
• Accurate segmentation is crucial for diagnosis, treatment planning, and disease monitoring.

Purpose of the Study:

• To propose a novel adaptive anatomical structure-based two-layer level set framework (AS2LS) for enhanced medical image segmentation.
• To improve the segmentation accuracy of organs with concentric structures, such as the left ventricle and fundus.
• To address challenges posed by inhomogeneous intensity, blurred boundaries, and surrounding organ interference.

Main Methods:

• Development of an adaptive anatomical structure-based two-layer level set framework (AS2LS).
• Utilizing adaptive fitting of region and edge intensity information for segmentation.
• Introduction of a novel two-layer level set representation based on anatomical structures and a two-stage level set evolution algorithm.

Main Results:

• The AS2LS framework achieved high accuracy in segmenting complex medical images.
• Demonstrated superior performance in segmenting organs with concentric structures, including the left ventricle and fundus.
• Experimental results showed AS2LS outperformed representative level set and deep learning methods.

Conclusions:

• The proposed AS2LS framework offers a significant advancement in medical image segmentation accuracy.
• AS2LS effectively handles challenging image characteristics like intensity inhomogeneity and blurred boundaries.
• This method provides a robust solution for segmenting organs with complex anatomical structures.