Complete, Fully Automatic Detection and Classification of Benign and Malignant Breast Tumors Based on CT Images Using...

Area of Science:

• Medical Imaging
• Oncology
• Computer-Aided Diagnosis

Background:

• Breast cancer is a leading cause of cancer mortality in women.
• Early detection of breast cancer is critical for improving patient outcomes.
• Automated systems can enhance the efficiency and accuracy of breast tumor diagnosis.

Purpose of the Study:

• To develop and evaluate an automated system for detecting and classifying breast tumors in CT scan images.
• To differentiate between benign and malignant breast tumors using advanced image analysis techniques.
• To improve the speed and reliability of clinical breast cancer diagnosis.

Main Methods:

• Extraction of chest wall contours from computed chest tomography (CT) images.
• Application of active contours (without edge and geodesic) for tumor detection and localization.
• Feature extraction and classification of tumors using a greedy algorithm and a support vector machine (SVM).
• Utilized 174 breast tumors for training and validation with 10-fold cross-validation.

Main Results:

• The system demonstrated high performance metrics: 99.43% accuracy, 98.82% sensitivity, 100% specificity, 100% positive predictive value, and 98.89% negative predictive value.
• The automated system successfully detected, located, and classified breast tumors.
• The classification distinguished effectively between benign and malignant breast tumors.

Conclusions:

• The developed computer-assisted diagnostic system offers rapid and accurate extraction and classification of breast tumors.
• This automated approach can significantly support physicians in improving clinical diagnosis of breast cancer.
• The system's high performance suggests its potential for integration into clinical workflows for enhanced breast cancer screening and diagnosis.