Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179763,
        author = {Prajakta Deshpande and Prajakta Narhare and Shweta Kenjale and Nikita Singh},
        title = {OncoSage : AI-Powered Breast Cancer Prediction Based Web Application},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {8613-8617},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179763},
        abstract = {Breast cancer remains a leading cause of 
mortality among women worldwide. Early detection 
through non-invasive imaging can significantly improve 
prognosis and treatment outcomes. In this paper, we 
present OncoSage, a robust, deep learning-based web 
application designed to assist radiologists and clinicians 
in classifying breast cancer types using ultrasound 
images. By leveraging transfer learning with the 
ResNet18 convolutional neural network (CNN) and 
advanced data augmentation techniques, our system 
achieves high accuracy in distinguishing between 
benign, malignant, and normal breast tissues. The 
model is integrated into a user-friendly Flask-based 
interface, which provides real-time predictions and 
confidence scores. We demonstrate the effectiveness of 
our approach through extensive training on the public 
BUSI dataset, yielding a classification accuracy of 98%. 
OncoSage aims to support clinical decision-making and 
enhance diagnostic efficiency in medical imaging.},
        keywords = {Breast Cancer, BUSI Dataset, CNN,  Machine Learning, Resnet18, Web Application},
        month = {May},
        }