سامانه همایش های دانشگاه آزاد اسلامی واحد نجف آباد

صفحه اصلی / اولین همایش بین المللی تحول خدمات سلامت: تلفیق مراقبت، درمان، بازتوانی و امیدبخشی

Machine Learning-Based Breast Cancer Diagnosis Using Cytological Features Derived from Optical Microscopy Data

نویسندگان :

Amirhossein Rezaei Latifi¹ َAli Rezaei-Latifi²

1- دانشگاه علوم پزشکی هرمزگان 2- دانشگاه هرمزگان

کلمات کلیدی :

Breast Cancer،Machine Learning،Random Forest،Medical Imaging،Optical Imaging

چکیده :

Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide, making early and accurate diagnosis a critical task in modern healthcare systems. In this study, a machine learning-based approach is proposed for breast cancer classification using the Wisconsin Breast Cancer Diagnostic dataset. The dataset consists of morphological features extracted from digitized images of fine needle aspirates, which are inherently derived from optical imaging techniques. A Random Forest classifier was employed to distinguish between benign and malignant tumors based on 30 cellular features describing the shape, size, and texture of cell nuclei. The model was trained and evaluated using an 80/20 train-test split, and its performance was assessed using standard evaluation metrics including accuracy, precision, recall, F1-score, confusion matrix, and ROC curve analysis. The results demonstrate a strong classification performance, achieving an overall accuracy of 96%. The model showed high precision and recall values for both classes, with particularly strong sensitivity in detecting malignant cases. Feature importance analysis revealed that morphological attributes such as area, perimeter, concavity, and radius-related features significantly contributed to the classification process. The findings highlight the effectiveness of combining machine learning techniques with optically derived biomedical features for breast cancer diagnosis. This approach demonstrates the potential of integrating optical imaging data with intelligent algorithms to support early detection and improve clinical decision-making in healthcare systems.