Vessel extraction under non-uniform illumination: a level set approach.

Area of Science:

• Medical Imaging
• Image Processing
• Computational Biology

Background:

• Vessel extraction is crucial for clinical diagnosis and analysis.
• Existing methods struggle with challenges like non-uniform illumination and blurry image data.
• Accurate vessel segmentation is essential for quantitative analysis in various medical applications.

Purpose of the Study:

• To present a novel level-set-based active contour model for enhanced vessel extraction.
• To introduce a new local term that incorporates local image contrast into the model.
• To demonstrate the model's superior performance compared to existing methods, particularly in challenging imaging conditions.

Main Methods:

• Development of a level-set-based active contour model.
• Inclusion of a novel local image contrast term within the active contour framework.
• Experimental validation using both synthetic datasets and real-world clinical angiograms.

Main Results:

• The proposed model maintains performance on blurry images, similar to existing methods.
• The novel approach effectively overcomes limitations in handling non-uniform illumination.
• Experiments show successful vessel extraction in diverse and challenging imaging scenarios.

Conclusions:

• The proposed level-set active contour method offers a robust solution for vessel extraction.
• Incorporating local image contrast significantly improves segmentation accuracy under non-uniform illumination.
• This technique holds promise for improving clinical practice through more reliable medical image analysis.