MitoDetect++: A Domain-Robust Pipeline for Mitosis Detection and Atypical Subtyping
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916934254067712 |
|---|---|
| author | Nasir, Esha Sadia Lv, Jiaqi Jahanifar, Mostafa Raza, Shan E Ahmed |
| author_facet | Nasir, Esha Sadia Lv, Jiaqi Jahanifar, Mostafa Raza, Shan E Ahmed |
| contents | Automated detection and classification of mitotic figures especially distinguishing atypical from normal remain critical challenges in computational pathology. We present MitoDetect++, a unified deep learning pipeline designed for the MIDOG 2025 challenge, addressing both mitosis detection and atypical mitosis classification. For detection (Track 1), we employ a U-Net-based encoder-decoder architecture with EfficientNetV2-L as the backbone, enhanced with attention modules, and trained via combined segmentation losses. For classification (Track 2), we leverage the Virchow2 vision transformer, fine-tuned efficiently using Low-Rank Adaptation (LoRA) to minimize resource consumption. To improve generalization and mitigate domain shifts, we integrate strong augmentations, focal loss, and group-aware stratified 5-fold cross-validation. At inference, we deploy test-time augmentation (TTA) to boost robustness. Our method achieves a balanced accuracy of 0.892 across validation domains, highlighting its clinical applicability and scalability across tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02586 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MitoDetect++: A Domain-Robust Pipeline for Mitosis Detection and Atypical Subtyping Nasir, Esha Sadia Lv, Jiaqi Jahanifar, Mostafa Raza, Shan E Ahmed Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Automated detection and classification of mitotic figures especially distinguishing atypical from normal remain critical challenges in computational pathology. We present MitoDetect++, a unified deep learning pipeline designed for the MIDOG 2025 challenge, addressing both mitosis detection and atypical mitosis classification. For detection (Track 1), we employ a U-Net-based encoder-decoder architecture with EfficientNetV2-L as the backbone, enhanced with attention modules, and trained via combined segmentation losses. For classification (Track 2), we leverage the Virchow2 vision transformer, fine-tuned efficiently using Low-Rank Adaptation (LoRA) to minimize resource consumption. To improve generalization and mitigate domain shifts, we integrate strong augmentations, focal loss, and group-aware stratified 5-fold cross-validation. At inference, we deploy test-time augmentation (TTA) to boost robustness. Our method achieves a balanced accuracy of 0.892 across validation domains, highlighting its clinical applicability and scalability across tasks. |
| title | MitoDetect++: A Domain-Robust Pipeline for Mitosis Detection and Atypical Subtyping |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.02586 |