Uncertainty-Aware Image Classification In Biomedical Imaging Using Spectral-normalized Neural Gaussian Processes

TL;DR

This paper introduces SNGP, a lightweight modification to neural networks that enhances uncertainty estimation and out-of-distribution detection in biomedical image classification, aiding safer clinical deployment.

Contribution

The paper proposes SNGP, combining spectral normalization and Gaussian process layers, to improve uncertainty calibration and OOD detection in biomedical imaging tasks.

Findings

SNGP achieves comparable accuracy to deterministic models on in-distribution data.

SNGP significantly improves out-of-distribution detection performance.

SNGP enhances uncertainty estimation, supporting safer clinical decision-making.

Abstract

Accurate histopathologic interpretation is key for clinical decision-making; however, current deep learning models for digital pathology are often overconfident and poorly calibrated in out-of-distribution (OOD) settings, which limit trust and clinical adoption. Safety-critical medical imaging workflows benefit from intrinsic uncertainty-aware properties that can accurately reject OOD input. We implement the Spectral-normalized Neural Gaussian Process (SNGP), a set of lightweight modifications that apply spectral normalization and replace the final dense layer with a Gaussian process layer to improve single-model uncertainty estimation and OOD detection. We evaluate SNGP vs. deterministic and MonteCarlo dropout on six datasets across three biomedical classification tasks: white blood cells, amyloid plaques, and colorectal histopathology. SNGP has comparable in-distribution performance while significantly improving uncertainty estimation and OOD detection. Thus, SNGP or related models offer a useful framework for uncertainty-aware classification in digital pathology, supporting safe deployment and building trust with pathologists.