A Breast Cancer Image Classification Algorithm with 2c Multiclass Support Vector Machine

Area of Science:

• Oncology
• Medical Imaging
• Machine Learning

Background:

• Breast cancer is a leading cause of cancer death in women.
• Early detection through mammography is crucial for reducing mortality.
• Mammography uses X-rays to create detailed breast images for early abnormality detection.

Purpose of the Study:

• To evaluate the effectiveness of a novel Multiclass Support Vector Machine (MSVM) algorithm for breast cancer detection.
• To compare the performance of the MSVM approach against traditional decision tree models.
• To explore advancements in screening mammography technologies for improved accuracy and accessibility.

Main Methods:

• Utilized high-resolution digital mammography to capture breast images.
• Employed a Multiclass Support Vector Machine (MSVM) algorithm, specifically the 2C variant.
• Compared the diagnostic accuracy of the MSVM approach with a decision tree model.

Main Results:

• The proposed 2C algorithm with MSVM demonstrated superior accuracy compared to the decision tree model.
• The MSVM approach shows promising results for breast cancer classification.
• Findings suggest potential for developing advanced statistical characteristics for cancer prognostics.

Conclusions:

• The developed MSVM method offers enhanced accuracy in breast cancer detection via mammography.
• New screening mammography technologies can improve global accuracy and accessibility.
• This research may lead to more sophisticated cancer prognostic models.