Multimodal Posterior Sampling-based Uncertainty in PD-L1 Segmentation from H&E Images
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914158682832896 |
|---|---|
| author | Kinakh, Roman Ríos-Muñoz, Gonzalo R. Muñoz-Barrutia, Arrate |
| author_facet | Kinakh, Roman Ríos-Muñoz, Gonzalo R. Muñoz-Barrutia, Arrate |
| contents | Accurate assessment of PD-L1 expression is critical for guiding immunotherapy, yet current immunohistochemistry (IHC) based methods are resource-intensive. We present nnUNet-B: a Bayesian segmentation framework that infers PD-L1 expression directly from H&E-stained histology images using Multimodal Posterior Sampling (MPS). Built upon nnUNet-v2, our method samples diverse model checkpoints during cyclic training to approximate the posterior, enabling both accurate segmentation and epistemic uncertainty estimation via entropy and standard deviation. Evaluated on a dataset of lung squamous cell carcinoma, our approach achieves competitive performance against established baselines with mean Dice Score and mean IoU of 0.805 and 0.709, respectively, while providing pixel-wise uncertainty maps. Uncertainty estimates show strong correlation with segmentation error, though calibration remains imperfect. These results suggest that uncertainty-aware H&E-based PD-L1 prediction is a promising step toward scalable, interpretable biomarker assessment in clinical workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11486 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multimodal Posterior Sampling-based Uncertainty in PD-L1 Segmentation from H&E Images Kinakh, Roman Ríos-Muñoz, Gonzalo R. Muñoz-Barrutia, Arrate Computer Vision and Pattern Recognition Quantitative Methods I.4.6 Accurate assessment of PD-L1 expression is critical for guiding immunotherapy, yet current immunohistochemistry (IHC) based methods are resource-intensive. We present nnUNet-B: a Bayesian segmentation framework that infers PD-L1 expression directly from H&E-stained histology images using Multimodal Posterior Sampling (MPS). Built upon nnUNet-v2, our method samples diverse model checkpoints during cyclic training to approximate the posterior, enabling both accurate segmentation and epistemic uncertainty estimation via entropy and standard deviation. Evaluated on a dataset of lung squamous cell carcinoma, our approach achieves competitive performance against established baselines with mean Dice Score and mean IoU of 0.805 and 0.709, respectively, while providing pixel-wise uncertainty maps. Uncertainty estimates show strong correlation with segmentation error, though calibration remains imperfect. These results suggest that uncertainty-aware H&E-based PD-L1 prediction is a promising step toward scalable, interpretable biomarker assessment in clinical workflows. |
| title | Multimodal Posterior Sampling-based Uncertainty in PD-L1 Segmentation from H&E Images |
| topic | Computer Vision and Pattern Recognition Quantitative Methods I.4.6 |
| url | https://arxiv.org/abs/2511.11486 |