ORIGINAL RESEARCH article
Front. Artif. Intell.
Sec. Medicine and Public Health
Volume 8 - 2025 | doi: 10.3389/frai.2025.1627876
An Artificial Intelligence Model for Early-Stage Breast Cancer Classification from Histopathological Biopsy Images
Provisionally accepted
Neil Chaudhary*
Zaynah Dhunny- Pangea Society, New Delhi, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Accurate identification of breast cancer subtypes is essential for guiding treatment decisions and improving patient outcomes. This study presents a deep learning-based model for classifying breast cancer from histopathological biopsy images, with an emphasis on distinguishing between subtypes. In current clinical practice, determining histological subtypes often requires additional invasive procedures, which can delay treatment initiation. The proposed model leverages a DenseNet121 backbone enhanced with a multi-scale feature fusion strategy, enabling it to integrate morphological cues across different levels of abstraction. Trained and evaluated on the publicly available BreaKHis dataset using 5-fold cross-validation, the model achieved an overall binary classification accuracy of 97.1%, and subtype classification accuracies of 93.8% for benign tumors and 92.0% for malignant tumors. These results highlight the model's strong potential as a decision-support tool in histopathological workflows, particularly in settings where diagnostic expertise or turnaround time is limited.
Keywords: breast cancer detection, artificial intelligence, Convolutional Neural Network, sub-classes of breast cancer, Breast Cancer Subtype Classification
Received: 13 May 2025; Accepted: 13 Aug 2025.
Copyright: © 2025 Chaudhary and Dhunny. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Neil Chaudhary, Pangea Society, New Delhi, India
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.