Computer-Assisted Diagnosis System for Breast Cancer in Computed Tomography Laser Mammography (CTLM).

Area of Science:

• Medical Imaging
• Radiology
• Artificial Intelligence in Medicine

Background:

• Computed tomography laser mammography (CTLM) is a non-invasive breast cancer diagnostic tool.
• Image interpretation in CTLM can be challenging due to technical factors and complexity, leading to potential missed diagnoses.

Purpose of the Study:

• To develop a computer-aided diagnosis (CAD) framework to improve radiologist performance in interpreting CTLM images.
• Enhance the accuracy and efficiency of breast cancer diagnosis using CTLM.

Main Methods:

• A CAD system was developed with three stages: segmentation, feature extraction, and classification.
• 3D Fuzzy segmentation was used for volume of interest (VOI) extraction.
• 3D compactness and 3D Grey Level Co-occurrence matrix (GLCM) features were extracted, followed by classification using a Multilayer Perceptron Neural Network (MLPNN).

Main Results:

• The proposed CAD system achieved high performance metrics.
• Accuracy: 95.2%
• Sensitivity: 92.4%
• Specificity: 98.1%
• Area Under Receiver Operating Characteristic Curve (AROC): 0.98%.

Conclusions:

• The developed CAD system significantly enhances the interpretation of CTLM images.
• The system demonstrates high accuracy, sensitivity, and specificity in differentiating benign and malignant lesions.
• This AI-driven approach shows promise in reducing diagnostic errors in breast cancer detection.