Reconstruction of Patient-Specific Confounders in AI-based Radiologic Image Interpretation using Generative Pretraining

TL;DR

This paper introduces DiffChest, a diffusion model that visualizes patient-specific confounders in chest radiographs, improving interpretability and robustness of AI diagnostics in healthcare.

Contribution

It presents a novel self-conditioned diffusion model trained on a large dataset to explain classifications and visualize confounders at a patient-specific level.

Findings

High agreement in confounder identification (Fleiss' Kappa ≥ 0.8)

Accurate capture of confounders with prevalence from 11.1% to 100%

Excellent diagnostic accuracy for multiple chest conditions

Abstract

Detecting misleading patterns in automated diagnostic assistance systems, such as those powered by Artificial Intelligence, is critical to ensuring their reliability, particularly in healthcare. Current techniques for evaluating deep learning models cannot visualize confounding factors at a diagnostic level. Here, we propose a self-conditioned diffusion model termed DiffChest and train it on a dataset of 515,704 chest radiographs from 194,956 patients from multiple healthcare centers in the United States and Europe. DiffChest explains classifications on a patient-specific level and visualizes the confounding factors that may mislead the model. We found high inter-reader agreement when evaluating DiffChest's capability to identify treatment-related confounders, with Fleiss' Kappa values of 0.8 or higher across most imaging findings. Confounders were accurately captured with 11.1% to 100% prevalence rates. Furthermore, our pretraining process optimized the model to capture the most relevant information from the input radiographs. DiffChest achieved excellent diagnostic accuracy when diagnosing 11 chest conditions, such as pleural effusion and cardiac insufficiency, and at least sufficient diagnostic accuracy for the remaining conditions. Our findings highlight the potential of pretraining based on diffusion models in medical image classification, specifically in providing insights into confounding factors and model robustness.