This study explores the application of Convolutional Neural Network (CNN) models in predicting neoadjuvant chemotherapy (NAC) responses through Magnetic Resonance Imaging (MRI) data in breast cancer patients. It aims to enhance prognosis monitoring by leveraging AI-driven image analysis, providing a computational interface for detailed radiological data analysis. Utilizing a dataset encompassing patients' radiological responses post-NAC, a CNN-based model has been developed using the YOLO algorithm. The model's predictive success with new data aimed to refine and improve its performance. The study demonstrates the potential of AI-driven deep learning models, particularly CNNs, in effectively predicting treatment responses through radiological data analysis. This approach combines detailed analysis of radiological data with a computational interface, aiming to aid physicians in their research efforts. The developed CNN model, utilizing the YOLO algorithm, achieved notable performance metrics in predicting neoadjuvant chemotherapy (NAC) responses in breast cancer patients. The developed CNN model, leveraging the YOLO algorithm, achieved significant performance metrics in predicting neoadjuvant chemotherapy (NAC) responses in breast cancer patients with an average precision of 71%, an average accuracy of 70.51%, and an Intersection over Union (IoU) value of 67.00%. The developed interface, implemented using the Python Tkinter library, provided rapid prediction results for new MRI images, completing predictions in under one second. This interface integrated the trained model's weight file, facilitating prediction in various hospital systems with minimal hardware capacities. This research underlines the significance of machine learning and deep learning in interpreting heterogeneous medical data, particularly in medical imaging analysis. The utilization of AI-based models doesn't aim to replace clinicians but serves as a collaborative tool to reduce workload and enhance diagnostic accuracy. While medical imaging methods have significantly advanced, this study emphasizes the potential of AI-driven models in exploiting invisible image features to improve predictive capabilities.