Early Detection of Breast Cancer Using Convolutional Neural Networks on Histopathology Images

DOI

10.2991/978-94-6463-866-0_16How to use a DOI?

Keywords

Breast Cancer; CNN; Histopathology; Explainable AI; Grad-CAM; SHAP; Mask-RCNN; Instance Segmentation

Abstract

Breast cancer remains one of the most prevalent and life-threatening diseases affecting women worldwide. Early diagnosis plays a critical role in enhancing patient survival outcomes. While histopathological analysis—examining tissue samples under a microscope—is the gold standard for diagnosis, it is often time-consuming and susceptible to human error. This study introduces an advanced system leveraging convolutional neural networks (CNNs) to facilitate early detection of breast cancer through the analysis of histopathology images. The proposed approach integrates multiple CNN architectures, including ResNet50, VGG16, and Inception-ResNet, for effective image classification, along with Mask R-CNN for precise tumor segmentation. To enhance transparency and reliability for clinical use, explainable AI techniques such as Grad-CAM and SHAP are employed to visualize the decision-making process of the models. The system achieved a classification accuracy of 96.8%, a segmentation Intersection over Union (IoU) score of 89.5%, and a Dice coefficient of 91.2%. These outcomes demonstrate that the proposed model surpasses existing methods and holds significant promise for adoption in clinical environments for early breast cancer diagnosis.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - A. Kalaivani
AU  - M. Ruth Jenifer
PY  - 2025
DA  - 2025/10/31
TI  - Early Detection of Breast Cancer Using Convolutional Neural Networks on Histopathology Images
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 165
EP  - 173
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_16
DO  - 10.2991/978-94-6463-866-0_16
ID  - Kalaivani2025
ER  -