Classifying Mitotic Figures in the MIDOG25 Challenge with Deep Ensemble Learning and Rule Based Refinement
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909758145953792 |
|---|---|
| author | Krauss, Sara Spieß, Ellena Hieber, Daniel Kramer, Frank Schobel, Johannes Müller, Dominik |
| author_facet | Krauss, Sara Spieß, Ellena Hieber, Daniel Kramer, Frank Schobel, Johannes Müller, Dominik |
| contents | Mitotic figures (MFs) are relevant biomarkers in tumor grading. Differentiating atypical MFs (AMFs) from normal MFs (NMFs) remains difficult, as manual annotation is time-consuming and subjective. In this work an ensemble of ConvNeXtBase models was trained with AUCMEDI and extend with a rule-based refinement (RBR) module. On the MIDOG25 preliminary test set, the ensemble achieved a balanced accuracy of 84.02%. While the RBR increased specificity, it reduced sensitivity and overall performance. The results show that deep ensembles perform well for AMF classification. RBR can increase specific metrics but requires further research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_20919 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Classifying Mitotic Figures in the MIDOG25 Challenge with Deep Ensemble Learning and Rule Based Refinement Krauss, Sara Spieß, Ellena Hieber, Daniel Kramer, Frank Schobel, Johannes Müller, Dominik Computer Vision and Pattern Recognition Mitotic figures (MFs) are relevant biomarkers in tumor grading. Differentiating atypical MFs (AMFs) from normal MFs (NMFs) remains difficult, as manual annotation is time-consuming and subjective. In this work an ensemble of ConvNeXtBase models was trained with AUCMEDI and extend with a rule-based refinement (RBR) module. On the MIDOG25 preliminary test set, the ensemble achieved a balanced accuracy of 84.02%. While the RBR increased specificity, it reduced sensitivity and overall performance. The results show that deep ensembles perform well for AMF classification. RBR can increase specific metrics but requires further research. |
| title | Classifying Mitotic Figures in the MIDOG25 Challenge with Deep Ensemble Learning and Rule Based Refinement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.20919 |