Ensemble of Pathology Foundation Models for MIDOG 2025 Track 2: Atypical Mitosis Classification
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_ | 1866918143247515648 |
|---|---|
| author | Ochi, Mieko Yuan, Bae |
| author_facet | Ochi, Mieko Yuan, Bae |
| contents | Mitotic figures are classified into typical and atypical variants, with atypical counts correlating strongly with tumor aggressiveness. Accurate differentiation is therefore essential for patient prognostication and resource allocation, yet remains challenging even for expert pathologists. Here, we leveraged Pathology Foundation Models (PFMs) pre-trained on large histopathology datasets and applied parameter-efficient fine-tuning via low-rank adaptation. In addition, we incorporated ConvNeXt V2, a state-of-the-art convolutional neural network architecture, to complement PFMs. During training, we employed a fisheye transform to emphasize mitoses and Fourier Domain Adaptation using ImageNet target images. Finally, we ensembled multiple PFMs to integrate complementary morphological insights, achieving competitive balanced accuracy on the Preliminary Evaluation Phase dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02591 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ensemble of Pathology Foundation Models for MIDOG 2025 Track 2: Atypical Mitosis Classification Ochi, Mieko Yuan, Bae Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Mitotic figures are classified into typical and atypical variants, with atypical counts correlating strongly with tumor aggressiveness. Accurate differentiation is therefore essential for patient prognostication and resource allocation, yet remains challenging even for expert pathologists. Here, we leveraged Pathology Foundation Models (PFMs) pre-trained on large histopathology datasets and applied parameter-efficient fine-tuning via low-rank adaptation. In addition, we incorporated ConvNeXt V2, a state-of-the-art convolutional neural network architecture, to complement PFMs. During training, we employed a fisheye transform to emphasize mitoses and Fourier Domain Adaptation using ImageNet target images. Finally, we ensembled multiple PFMs to integrate complementary morphological insights, achieving competitive balanced accuracy on the Preliminary Evaluation Phase dataset. |
| title | Ensemble of Pathology Foundation Models for MIDOG 2025 Track 2: Atypical Mitosis Classification |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.02591 |