Using generative AI to investigate medical imagery models and datasets

Abstract

AI models have shown promise in many medical imaging tasks. However, our ability to explain what signals these models have learned is severely lacking. Explanations are needed in order to increase the trust in AI-based models, and could enable novel scientific discovery by uncovering signals in the data that are not yet known to experts. In this paper, we present a method for automatic visual explanations leveraging team-based expertise by generating hypotheses of what visual signals in the images are correlated with the task. We propose the following 4 steps: (i) Train a classifier to perform a given task (ii) Train a classifier guided StyleGAN-based image generator (StylEx) (iii) Automatically detect and visualize the top visual attributes that the classifier is sensitive towards (iv) Formulate hypotheses for the underlying mechanisms, to stimulate future research. Specifically, we present the discovered attributes to an interdisciplinary panel of experts so that hypotheses can account for social and structural determinants of health. We demonstrate results on eight prediction tasks across three medical imaging modalities: retinal fundus photographs, external eye photographs, and chest radiographs. We showcase examples of attributes that capture clinically known features, confounders that arise from factors beyond physiological mechanisms, and reveal a number of physiologically plausible novel attributes. Our approach has the potential to enable researchers to better understand, improve their assessment, and extract new knowledge from AI-based models. Importantly, we highlight that attributes generated by our framework can capture phenomena beyond physiology or pathophysiology, reflecting the real world nature of healthcare delivery and socio-cultural factors. Finally, we intend to release code to enable researchers to train their own StylEx models and analyze their predictive tasks.

43 pages, 1 figure

References in corpus (10)

• Predicting Cardiovascular Risk Factors from Retinal Fundus Photographs using Deep Learning
• SurfaceNet: Adversarial SVBRDF Estimation from a Single Image
• Reading Race: AI Recognises Patient's Racial Identity In Medical Images
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• A Bayesian machine scientist to aid in the solution of challenging scientific problems
• Deep learning-based algorithm for assessment of knee osteoarthritis severity in radiographs matches performance of radiologists
• GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning
• Detecting hidden signs of diabetes in external eye photographs
• Deep Learning for Distinguishing Normal versus Abnormal Chest Radiographs and Generalization to Unseen Diseases
• Deep Learning Discovery of Demographic Biomarkers in Echocardiography

Cited by in corpus (2)

• Artificial General Intelligence for Medical Imaging Analysis
• In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review