Towards Reliable Few-Shot Adaptation of Pathology Foundation Models via Conformal Prediction

Aditya Narendra, Subhankar Panda, Chandresh Kumar Maurya
Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, PMLR 317:181-190, 2026.

Abstract

Recent advances in foundation models have enabled their integration into high-stakes clinical settings, particularly in computational pathology, where domain-specialized FMs demonstrate strong generalization. However, real-world deployment is constrained by their poorly calibrated uncertainty awareness and degraded performance in low-data regimes requiring few-shot adaptation strategies, leading to unreliable and inefficient diagnostic workflows. Conformal Prediction (CP) is an uncertainty quantification framework that offers distribution-free, finite-sample coverage guarantees for ensuring safer deployment in such settings. In this work, we explore the integration of various CP methods with pathology foundation models using three few-shot adaption strategies for classification tasks across two datasets. To assess the clinical effectiveness of these approaches, we propose four novel metrics aimed at improving clinical reliability and alleviating diagnostic workload in few-shot settings. Our results demonstrate that Conformal Prediction methods enhance the reliability of pathology foundation models and offer actionable uncertainty estimates to enable safe and efficient deployment in few-shot pathological classification workflows, with the LAC method achieving the best overall performance. Code is available at https://github.com/AdiNarendra98/Few-Shot-PathCP.

Cite this Paper

BibTeX
@InProceedings{pmlr-v317-narendra26a, title = {Towards Reliable Few-Shot Adaptation of Pathology Foundation Models via Conformal Prediction}, author = {Narendra, Aditya and Panda, Subhankar and Maurya, Chandresh Kumar}, booktitle = {Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare}, pages = {181--190}, year = {2026}, editor = {Wu, Junde and Pan, Jiazhen and Zhu, Jiayuan and Luo, Luyang and Li, Yitong and Xu, Min and Jin, Yueming and Rueckert, Daniel}, volume = {317}, series = {Proceedings of Machine Learning Research}, month = {20--21 Jan}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v317/main/assets/narendra26a/narendra26a.pdf}, url = {https://proceedings.mlr.press/v317/narendra26a.html}, abstract = {Recent advances in foundation models have enabled their integration into high-stakes clinical settings, particularly in computational pathology, where domain-specialized FMs demonstrate strong generalization. However, real-world deployment is constrained by their poorly calibrated uncertainty awareness and degraded performance in low-data regimes requiring few-shot adaptation strategies, leading to unreliable and inefficient diagnostic workflows. Conformal Prediction (CP) is an uncertainty quantification framework that offers distribution-free, finite-sample coverage guarantees for ensuring safer deployment in such settings. In this work, we explore the integration of various CP methods with pathology foundation models using three few-shot adaption strategies for classification tasks across two datasets. To assess the clinical effectiveness of these approaches, we propose four novel metrics aimed at improving clinical reliability and alleviating diagnostic workload in few-shot settings. Our results demonstrate that Conformal Prediction methods enhance the reliability of pathology foundation models and offer actionable uncertainty estimates to enable safe and efficient deployment in few-shot pathological classification workflows, with the LAC method achieving the best overall performance. Code is available at https://github.com/AdiNarendra98/Few-Shot-PathCP.} }
Endnote
%0 Conference Paper %T Towards Reliable Few-Shot Adaptation of Pathology Foundation Models via Conformal Prediction %A Aditya Narendra %A Subhankar Panda %A Chandresh Kumar Maurya %B Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare %C Proceedings of Machine Learning Research %D 2026 %E Junde Wu %E Jiazhen Pan %E Jiayuan Zhu %E Luyang Luo %E Yitong Li %E Min Xu %E Yueming Jin %E Daniel Rueckert %F pmlr-v317-narendra26a %I PMLR %P 181--190 %U https://proceedings.mlr.press/v317/narendra26a.html %V 317 %X Recent advances in foundation models have enabled their integration into high-stakes clinical settings, particularly in computational pathology, where domain-specialized FMs demonstrate strong generalization. However, real-world deployment is constrained by their poorly calibrated uncertainty awareness and degraded performance in low-data regimes requiring few-shot adaptation strategies, leading to unreliable and inefficient diagnostic workflows. Conformal Prediction (CP) is an uncertainty quantification framework that offers distribution-free, finite-sample coverage guarantees for ensuring safer deployment in such settings. In this work, we explore the integration of various CP methods with pathology foundation models using three few-shot adaption strategies for classification tasks across two datasets. To assess the clinical effectiveness of these approaches, we propose four novel metrics aimed at improving clinical reliability and alleviating diagnostic workload in few-shot settings. Our results demonstrate that Conformal Prediction methods enhance the reliability of pathology foundation models and offer actionable uncertainty estimates to enable safe and efficient deployment in few-shot pathological classification workflows, with the LAC method achieving the best overall performance. Code is available at https://github.com/AdiNarendra98/Few-Shot-PathCP.
APA
Narendra, A., Panda, S. & Maurya, C.K.. (2026). Towards Reliable Few-Shot Adaptation of Pathology Foundation Models via Conformal Prediction. Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, in Proceedings of Machine Learning Research 317:181-190 Available from https://proceedings.mlr.press/v317/narendra26a.html.

Related Material