RadGazeGen: Radiomics and Gaze-guided Medical Image Generation using Diffusion Models

TL;DR

RadGazeGen introduces a novel method combining radiologists' eye gaze patterns and radiomic features to guide diffusion models for generating high-fidelity, disease-aware medical images with potential clinical applications.

Contribution

This work presents RadGazeGen, a new framework integrating gaze patterns and radiomics as controls for diffusion models in medical image synthesis.

Findings

High-quality, diverse image generation demonstrated on REFLACX dataset.

Improved classification accuracy on generated images in CheXpert test set.

Enhanced long-tailed learning performance on MIMIC-CXR-LT dataset.

Abstract

In this work, we present RadGazeGen, a novel framework for integrating experts' eye gaze patterns and radiomic feature maps as controls to text-to-image diffusion models for high fidelity medical image generation. Despite the recent success of text-to-image diffusion models, text descriptions are often found to be inadequate and fail to convey detailed disease-specific information to these models to generate clinically accurate images. The anatomy, disease texture patterns, and location of the disease are extremely important to generate realistic images; moreover the fidelity of image generation can have significant implications in downstream tasks involving disease diagnosis or treatment repose assessment. Hence, there is a growing need to carefully define the controls used in diffusion models for medical image generation. Eye gaze patterns of radiologists are important visuo-cognitive information, indicative of subtle disease patterns and spatial location. Radiomic features further provide important subvisual cues regarding disease phenotype. In this work, we propose to use these gaze patterns in combination with standard radiomics descriptors, as controls, to generate anatomically correct and disease-aware medical images. RadGazeGen is evaluated for image generation quality and diversity on the REFLACX dataset. To demonstrate clinical applicability, we also show classification performance on the generated images from the CheXpert test set (n=500) and long-tailed learning performance on the MIMIC-CXR-LT test set (n=23550).