Multi-view collaborative segmentation for prostate MRI images.

Area of Science:

• Medical Imaging
• Computer Vision
• Machine Learning

Background:

• Prostate delineation from MRI is challenging due to patient variability and disease progression.
• Existing methods often rely on handcrafted features or are sensitive to initial seed selection.

Purpose of the Study:

• To develop an automated and robust prostate MRI segmentation method.
• To overcome the limitations of manual segmentation and improve accuracy.

Main Methods:

• Extracted multiple label-relevance maps to represent pixel affinities without handcrafted features.
• Employed collaborative clustering with adaptive weights for optimal segmentation.
• Evaluated performance using Dice Similarity Coefficient (DSC), Absolute Relative Volume Difference (ARVD), and Average Symmetric Surface Distance (ASSD) on 22 prostate MRI datasets.

Main Results:

• The proposed collaborative method demonstrated improved segmentation accuracy and robustness.
• Statistical analysis (t-Test) confirmed the significant improvement over existing techniques.
• The method effectively addressed seed selection sensitivity issues.

Conclusions:

• The novel collaborative approach offers a significant advancement in automated prostate MRI segmentation.
• This method provides a more accurate and reliable tool for clinical applications.
• Future work could explore its application to other anatomical structures or imaging modalities.