Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution Shift

TL;DR

This paper introduces a novel test-time adaptation method with distribution calibration for medical image classification, effectively handling label distribution shifts to improve diagnostic accuracy.

Contribution

It proposes the first approach to address label shift in medical image classification by calibrating multiple classifiers and dynamically aggregating them during testing.

Findings

Significant performance improvement across various label shifts.

Effective handling of disease prevalence variations in medical diagnosis.

Validated on liver fibrosis and COVID-19 severity prediction tasks.

Abstract

Class distribution plays an important role in learning deep classifiers. When the proportion of each class in the test set differs from the training set, the performance of classification nets usually degrades. Such a label distribution shift problem is common in medical diagnosis since the prevalence of disease vary over location and time. In this paper, we propose the first method to tackle label shift for medical image classification, which effectively adapt the model learned from a single training label distribution to arbitrary unknown test label distribution. Our approach innovates distribution calibration to learn multiple representative classifiers, which are capable of handling different one-dominating-class distributions. When given a test image, the diverse classifiers are dynamically aggregated via the consistency-driven test-time adaptation, to deal with the unknown test label distribution. We validate our method on two important medical image classification tasks including liver fibrosis staging and COVID-19 severity prediction. Our experiments clearly show the decreased model performance under label shift. With our method, model performance significantly improves on all the test datasets with different label shifts for both medical image diagnosis tasks.