aiqbench analysis
This research introduces a scalable Bayesian Gaussian Process framework that significantly improves uncertainty calibration for cancer diagnosis models under distribution shifts, addressing critical reliability issues when applying models across different hospitals. By combining low-rank kernel factorization with Hamiltonian Monte Carlo sampling, the method handles large-scale pathology datasets while reducing false negative rates and overconfidence compared to standard neural network baselines.
Scalable Bayesian Gaussian Process Classification for Cancer Histopathology: Calibrated Uncertainty Under Distribution Shift
arXiv:2611.07127v1 Announce Type: new Abstract: Reliable uncertainty quantification is essential for clinical deployment of cancer diagnosis models, yet neural networks and variational Gaussian process methods can produce overconfident predictions, particularly under the distribution shifts that arise when models trained at one hospital are applied at another. We present a scalable Bayesian Gaussian Process Classification (GPC) framework that operates on frozen pathology foundation model embeddings (Phikon) and combines accelerated Randomly Pivoted Cholesky (RPCholesky) for low-rank kernel factorization, Hamiltonian Monte Carlo (HMC) with non-centered parameterization for posterior sampling, and a pivots-as-inducing-points scheme for prediction. This makes HMC posterior sampling in the low-rank latent representation tractable at N approximately 300,000 training points, enabling HC-based low-rank GPC on substantially larger datasets than prior MCMC-based demonstrations. We evaluate on two histopathology benchmarks for breast cancer metastasis detection: PCam and CAMELYON17-WILDS, where the latter tests calibration under hospital-level distribution shift. Compared to stochastic variational GP and neural network baselines, our method improves calibration and predictive performance - reducing expected calibration error by up to 88% and false negative rate by up to 90% - with the largest gains appearing under distribution shift, suggesting that HMC-based posterior sampling provides more trustworthy uncertainty estimates for cross-site pathology classification.
Abstract:Reliable uncertainty quantification is essential for clinical deployment of cancer diagnosis models, yet neural networks and variational Gaussian process methods can produce overconfident predictions, particularly under the distribution shifts that arise when models trained at one hospital are applied at another. We present a scalable Bayesian Gaussian Process Classification (GPC) framework that operates on frozen pathology foundation model embeddings (Phikon) and combines accelerated Randomly Pivoted Cholesky (RPCholesky) for low-rank kernel factorization, Hamiltonian Monte Carlo (HMC) with non-centered parameterization for posterior sampling, and a pivots-as-inducing-points scheme for prediction. This makes HMC posterior sampling in the low-rank latent representation tractable at N approximately 300,000 training points, enabling HC-based low-rank GPC on substantially larger datasets than prior MCMC-based demonstrations. We evaluate on two histopathology benchmarks for breast cancer metastasis detection: PCam and CAMELYON17-WILDS, where the latter tests calibration under hospital-level distribution shift. Compared to stochastic variational GP and neural network baselines, our method improves calibration and predictive performance - reducing expected calibration error by up to 88% and false negative rate by up to 90% - with the largest gains appearing under distribution shift, suggesting that HMC-based posterior sampling provides more trustworthy uncertainty estimates for cross-site pathology classification.
Machine Learning (cs.LG)
arXiv:2611.07127 [cs.LG]
(or arXiv:2611.07127v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2611.07127 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 289 words
Related coverage
MagViT: Interpretable Multi-Magnification Transformers with Patient-Level Model Selection for Breast Histopathology
arXiv · Aug 20, 2026
FedHisto-PAST: Parameter-Efficient Stain-Aware Federated Learning for Cross-Site Lung Histopathology Classification
arXiv · Sep 28, 2026
Continued Pretraining of FinBERT on Finnish Histopathological Reports: Train-Time Signals and Proxy Downstream Correlations
arXiv · Sep 25, 2026
A Comparative Evaluation of Pre-trained Convolutional Neural Networks for Melanoma Detection
arXiv · Sep 12, 2026