[Study of mass segmentation algorithm for digital mammograms]

Area of Science:

• Medical Imaging
• Radiology
• Computer-Aided Diagnosis

Background:

• Digital mammography is crucial for breast cancer detection.
• Accurate segmentation of breast masses is vital for diagnosis.
• Tumor shape and edge features aid in differentiating malignant from benign masses.

Purpose of the Study:

• To enhance breast mass segmentation in digital mammograms.
• To provide radiologists with more informative mass features.
• To improve the accuracy of malignant vs. benign tumor discrimination.

Main Methods:

• Development of a novel region growing algorithm for mass segmentation.
• Parameter optimization for the region growing method.
• Evaluation of the method's effectiveness in preserving mass edge features.

Main Results:

• The enhanced mass segmentation method effectively isolates breast mass regions.
• The algorithm successfully preserves the detailed features of the mass edges.
• Improved segmentation accuracy is achieved compared to standard methods.

Conclusions:

• The presented region growing technique offers a valuable tool for breast mass segmentation.
• Preservation of mass edge features enhances diagnostic information for radiologists.
• This method has the potential to improve the accuracy of breast cancer diagnosis.