Evaluated multiple machine learning techniques, including Logistic Regression, Decision Trees, K-Nearest Neighbors, Support Vector Machines, and Convolutional Neural Networks, to determine the most accurate approach for breast cancer diagnosis. This analysis compared the efficacy of models trained on numeric features from breast mass cell nuclei with image-based models leveraging Ultrasound scans.
Presentation: https://drive.google.com/file/d/1KL8z6mvIDSsXghD4vnfAzoJqI8GBKBdo/view?usp=drive_link