Interpretable Deep Transfer Learning Framework for Breast Cancer Histopathology Classification
Bibliographic record
Abstract
Breast cancer is one of the most common and serious diseases affecting women, making early and accurate diagnosis very crucial. This paper presents a deep learning framework for histopathology image analysis that integrates Explainable AI (XAI) to ensure transparency and reliability. We evaluated three architectures, MaxViT, CoAtNet-0, and BEiT, using the BreakHis dataset across four magnification levels ($40 \mathrm{X}, 100 \mathrm{X}, 200 \mathrm{X}, 400 \mathrm{X}$). MaxViT produced excellent results, achieving 91.45% accuracy at $40 \mathrm{X}, 89.02 \%$ at $100 \mathrm{X}, 83.26 \%$ at $200 \mathrm{X}, 88.21 \%$ at 400 X, and an overall test accuracy of $\mathbf{8 7. 7 5 \%}$, with AUC-ROC scores up to 0.9589. To improve interpretability, we applied XAI methods such as Grad-CAM, LIME, Layer-wise Relevance Propagation (LRP), Integrated Gradients (IG), and Saliency Maps. These methods highlighted diagnostically important tissue regions and provided valuable support for pathologists in decision-making. Although the proposed approach demonstrates strong performance in controlled experiments, further clinical validation is needed. Future work will focus on integration into clinical practice and device-level deployment to enable reliable and practical breast cancer diagnosis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".