Magnification-Invariant Image Classification via Domain Generalization and Stable Sparse Embedding Signatures
For computational pathology, this work demonstrates that compact, transferable representations can be learned without architectural complexity, improving robustness across imaging scales.
The paper tackles magnification shift in histopathology image classification, showing that a gradient-reversal domain-general model outperforms baselines and GAN augmentation on BreaKHis, achieving a Brier score of 0.063 vs 0.089 and reducing signature size from 1,074 to 306 dimensions while maintaining AUC ~0.967 and F1 ~0.930.
Magnification shift is a major obstacle to robust histopathology classification, because models trained on one imaging scale often generalize poorly to another. Here, we evaluated this problem on the BreaKHis dataset using a strict patient-disjoint leave-one-magnification-out protocol, comparing supervised baseline, baseline augmented with DCGAN-generated patches, and a gradient-reversal domain-general model designed to preserve discriminative information while suppressing magnification-specific variation. Across held-out magnifications, the domain-general model achieved the strongest overall discrimination and its clearest gain was observed when 200X was held out. By contrast, GAN augmentation produced inconsistent effects, improving some folds but degrading others, particularly at 400X. The domain-general model also yielded the lowest Brier score at 0.063 vs 0.089 at baseline. Sparse embedding analysis further revealed that domain-general training reduced average signature size more than three-fold (306 versus 1,074 dimensions) while preserving equivalent predictive performance (AUC: 0.967 vs 0.965; F1: 0.930 vs 0.931). It also increased cross-fold signature reproducibility from near-zero Jaccard overlap in the baseline to 0.99 between the 100X and 200X folds. These findings show that calibrated, compact, and transferable representations can be learned without added architectural complexity, with clear implications for the reliable deployment of computational pathology models across heterogeneous acquisition settings.