Papers › Breast cancer histology classification using Deep Residual Networks
Breast cancer histology classification using Deep Residual Networks
Kamalakkannan Ravi, Sakthivel Selvaraj, JM Poorneshwaran, Keerthi Ram, Mohanasankar Sivaprakasam
In this work, in order to improve the computer aided diagnosis systems’ performance on histopathological image analysis, we have proposed an approach with image pre-processing followed by a deep learning method to classify the breast cancer histology images into four classes; (i) normal tissue, (ii) benign lesion, (iii) in-situ carcinoma, and (iv) invasive carcinoma. The images are preprocessed for intensity and stain normalization using histogram equalization method. The Fine-tuning ConvNet transfer learning method is used with ResNet152 to train and classify the images. This proposed approach yields an average fivefold cross validation accuracy of 83%, a substantial improvement over the state-of-the-art.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Breast Cancer Histology Image Classification | ICIAR 2018 Grand Challenge on Breast Cancer Histology Images | ResNet-152 | Accuracy (% ) | 83 | #1 of 1 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections