Variational Knowledge Distillation for Disease Classification in Chest X-Rays

TL;DR

This paper introduces variational knowledge distillation, a probabilistic framework that leverages EHR data to improve disease classification accuracy from chest X-ray images, outperforming existing methods.

Contribution

The paper proposes a novel variational knowledge distillation approach that integrates EHR information into X-ray disease classification using a conditional latent variable model.

Findings

Consistently improves classification performance on benchmark datasets.

Significantly surpasses current state-of-the-art methods.

Effectively leverages EHR data to enhance visual feature extraction.

Abstract

Disease classification relying solely on imaging data attracts great interest in medical image analysis. Current models could be further improved, however, by also employing Electronic Health Records (EHRs), which contain rich information on patients and findings from clinicians. It is challenging to incorporate this information into disease classification due to the high reliance on clinician input in EHRs, limiting the possibility for automated diagnosis. In this paper, we propose \textit{variational knowledge distillation} (VKD), which is a new probabilistic inference framework for disease classification based on X-rays that leverages knowledge from EHRs. Specifically, we introduce a conditional latent variable model, where we infer the latent representation of the X-ray image with the variational posterior conditioning on the associated EHR text. By doing so, the model acquires the ability to extract the visual features relevant to the disease during learning and can therefore perform more accurate classification for unseen patients at inference based solely on their X-ray scans. We demonstrate the effectiveness of our method on three public benchmark datasets with paired X-ray images and EHRs. The results show that the proposed variational knowledge distillation can consistently improve the performance of medical image classification and significantly surpasses current methods.