Normal and Atypical Mitosis Image Classifier using Efficient Vision Transformer
This work addresses a domain-specific problem for medical imaging researchers by providing a competitive method for mitosis classification, though it is incremental as it applies an existing hybrid architecture to new data.
The paper tackled the classification of normal versus atypical mitosis images in the MIDOG 2025 challenge using an EfficientViT-L2 model, achieving a balanced accuracy of 0.859 and ROC AUC of 0.942 in preliminary evaluations.
We tackle atypical versus normal mitosis classification in the MIDOG 2025 challenge using EfficientViT-L2, a hybrid CNN--ViT architecture optimized for accuracy and efficiency. A unified dataset of 13,938 nuclei from seven cancer types (MIDOG++ and AMi-Br) was used, with atypical mitoses comprising ~15. To assess domain generalization, we applied leave-one-cancer-type-out cross-validation with 5-fold ensembles, using stain-deconvolution for image augmentation. For challenge submissions, we trained an ensemble with the same 5-fold split but on all cancer types. In the preliminary evaluation phase, this model achieved balanced accuracy of 0.859, ROC AUC of 0.942, and raw accuracy of 0.85, demonstrating competitive and well-balanced performance across metrics.