Automated Breast Cancer Lesion Segmentation and Diameter Detection in Mammogram Images Using Active Contour Lankton with MATLAB GUI

Breast cancer is the most commonly diagnosed cancer among women worldwide and remains one of the leading causes of cancer-related deaths, accounting for approximately 10 million deaths in 2020. Diagnosis is generally performed through routine examinations or when symptoms appear; however, physical examination alone is often insufficient. Image segmentation techniques are increasingly utilized to enhance diagnostic accuracy. This study aims to develop a MATLAB-based program using the Graphical User Interface (GUI) and the Active Contour Lankton method to perform segmentation on mammogram images for breast cancer detection. The process involves several stages: acquiring the original mammogram image, enhancing the image using intensity adjustment, applying the Active Contour Lankton segmentation technique, and measuring the diameter of suspected cancerous regions in 15 sample images. The results show that the program was able to identify breast cancer in several cases with good sensitivity and also demonstrated potential in reducing false-positive findings in images from patients confirmed to be cancer-free. Nevertheless, several false-positive errors were still observed, indicating that the segmentation accuracy requires further improvement. This study advances computer-aided diagnostic tools by integrating the Active Contour Lankton method into a user-friendly MATLAB GUI framework. The proposed approach offers a practical and accessible solution for supporting early breast cancer detection and minimizing diagnostic errors in clinical practice.