[A multi-label fusion based level set method for multiple sclerosis lesion segmentation].

Area of Science:

• Medical Imaging
• Computer Vision
• Biomedical Engineering

Background:

• Multiple sclerosis (MS) lesion segmentation in magnetic resonance imaging (MRI) is crucial for diagnosis and treatment monitoring.
• Accurate segmentation is challenging due to lesion variability in shape, size, and intensity.
• Existing methods may lack robustness or require significant manual intervention.

Purpose of the Study:

• To develop and validate a novel multi-label based level set model for automated multiple sclerosis lesion segmentation.
• To improve the accuracy and robustness of lesion detection using MRI data.
• To reduce the workload for radiologists in clinical practice.

Main Methods:

• A fuzzy c-means model was employed for initial lesion region extraction.
• An intensity prior and label fusion term were integrated into a region-based level set model.
• The level set contour was evolved to achieve final lesion segmentation based on shape and position information.

Main Results:

• The proposed model demonstrated accurate and robust extraction of brain lesions from MRI.
• Experimental results confirmed the effectiveness of the integrated intensity prior and label fusion terms.
• The method showed significant potential for reducing radiologist workload.

Conclusions:

• The developed multi-label level set model offers an effective solution for multiple sclerosis lesion segmentation.
• The method's accuracy and robustness make it a valuable tool for clinical applications.
• This automated approach can assist radiologists in faster and more precise lesion identification.