Ultrasound Image Analysis in Breast Cancer: A Comparative Study of Decision Trees and Random Forests

Breast cancer remains a leading cause of cancer-related mortality among women globally, underscoring the critical need for early detection and accurate diagnosis. Ultrasound imaging serves as a non-invasive diagnostic tool for identifying breast abnormalities, yet the complexity of these images presents significant interpretation challenges. This study explores the application of Machine Learning (ML) models, specifically Decision Tree (DT) and Random Forest (RF) classifiers, for the classification of breast cancer ultrasound images into benign, malignant, and normal categories. Data augmentation techniques are employed to address class imbalance and enhance model generalization using the Breast Cancer Ultrasonic Image dataset. Among preprocessing steps, pixel values were normalized to provide a consistent input for the models. RF model performed better than DT with an accuracy of 88.75% against an accuracy of 86.25% and those masks for ultrasound images contribute a lot to the overall classification accuracy. In summary, the results of our study can provide support for grand challenges in health and emphasize implications such as the potentiality of ML models to advance breast cancer diagnosis and it implies a necessity for an even further expansion that will allow complete patient outcomes optimization.