Active Contours Driven by Multi-Feature Gaussian Distribution Fitting Energy with Application to Vessel Segmentation.

Area of Science:

• Medical image analysis
• Computer vision
• Biomedical engineering

Background:

• Active contour models are crucial for image segmentation, but struggle with intensity inhomogeneity.
• Accurate segmentation of retinal vessels is vital for diagnosing eye diseases.

Purpose of the Study:

• To develop a novel region-based active contour model for improved image segmentation.
• To enhance the segmentation of small vessels with varying widths in retinal images.

Main Methods:

• Proposed a novel region-based active contour model integrating image intensities and vesselness values.
• Utilized a multi-feature Gaussian distribution fitting energy within a level set formulation.
• Incorporated a regularization term for enhanced segmentation accuracy.

Main Results:

• The proposed model demonstrated superior accuracy compared to existing methods on the STARE dataset.
• Successfully segmented small retinal vessels exhibiting diverse widths.
• Overcame limitations of traditional active contour models in handling intensity inhomogeneity.

Conclusions:

• The novel active contour model offers a more accurate and robust approach for retinal vessel segmentation.
• The integration of multi-feature information significantly improves segmentation performance.
• This method holds potential for clinical applications in ophthalmology.