Pathology Foundation Models are Scanner Sensitive: Benchmark and Mitigation with Contrastive ScanGen Loss
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918107336933376 |
|---|---|
| author | Carloni, Gianluca Brattoli, Biagio Keum, Seongho Park, Jongchan Lee, Taebum Ahn, Chang Ho Pereira, Sergio |
| author_facet | Carloni, Gianluca Brattoli, Biagio Keum, Seongho Park, Jongchan Lee, Taebum Ahn, Chang Ho Pereira, Sergio |
| contents | Computational pathology (CPath) has shown great potential in mining actionable insights from Whole Slide Images (WSIs). Deep Learning (DL) has been at the center of modern CPath, and while it delivers unprecedented performance, it is also known that DL may be affected by irrelevant details, such as those introduced during scanning by different commercially available scanners. This may lead to scanner bias, where the model outputs for the same tissue acquired by different scanners may vary. In turn, it hinders the trust of clinicians in CPath-based tools and their deployment in real-world clinical practices. Recent pathology Foundation Models (FMs) promise to provide better domain generalization capabilities. In this paper, we benchmark FMs using a multi-scanner dataset and show that FMs still suffer from scanner bias. Following this observation, we propose ScanGen, a contrastive loss function applied during task-specific fine-tuning that mitigates scanner bias, thereby enhancing the models' robustness to scanner variations. Our approach is applied to the Multiple Instance Learning task of Epidermal Growth Factor Receptor (EGFR) mutation prediction from H\&E-stained WSIs in lung cancer. We observe that ScanGen notably enhances the ability to generalize across scanners, while retaining or improving the performance of EGFR mutation prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22092 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pathology Foundation Models are Scanner Sensitive: Benchmark and Mitigation with Contrastive ScanGen Loss Carloni, Gianluca Brattoli, Biagio Keum, Seongho Park, Jongchan Lee, Taebum Ahn, Chang Ho Pereira, Sergio Quantitative Methods Artificial Intelligence Computer Vision and Pattern Recognition Image and Video Processing Tissues and Organs I.2; I.2.6; I.4; I.4.7; I.5; J.3; J.6 Computational pathology (CPath) has shown great potential in mining actionable insights from Whole Slide Images (WSIs). Deep Learning (DL) has been at the center of modern CPath, and while it delivers unprecedented performance, it is also known that DL may be affected by irrelevant details, such as those introduced during scanning by different commercially available scanners. This may lead to scanner bias, where the model outputs for the same tissue acquired by different scanners may vary. In turn, it hinders the trust of clinicians in CPath-based tools and their deployment in real-world clinical practices. Recent pathology Foundation Models (FMs) promise to provide better domain generalization capabilities. In this paper, we benchmark FMs using a multi-scanner dataset and show that FMs still suffer from scanner bias. Following this observation, we propose ScanGen, a contrastive loss function applied during task-specific fine-tuning that mitigates scanner bias, thereby enhancing the models' robustness to scanner variations. Our approach is applied to the Multiple Instance Learning task of Epidermal Growth Factor Receptor (EGFR) mutation prediction from H\&E-stained WSIs in lung cancer. We observe that ScanGen notably enhances the ability to generalize across scanners, while retaining or improving the performance of EGFR mutation prediction. |
| title | Pathology Foundation Models are Scanner Sensitive: Benchmark and Mitigation with Contrastive ScanGen Loss |
| topic | Quantitative Methods Artificial Intelligence Computer Vision and Pattern Recognition Image and Video Processing Tissues and Organs I.2; I.2.6; I.4; I.4.7; I.5; J.3; J.6 |
| url | https://arxiv.org/abs/2507.22092 |