Evaluating and Improving the Effectiveness of Synthetic Chest X-Rays for Medical Image Analysis

TL;DR

This study investigates methods to generate and utilize synthetic chest X-ray images to enhance deep learning model performance in medical image classification and segmentation tasks, demonstrating significant improvements through optimized synthetic data augmentation.

Contribution

It introduces a latent diffusion model conditioned on text and segmentation masks for synthetic X-ray generation, and evaluates best practices for dataset augmentation in medical imaging.

Findings

Synthetic data improved classification F1 scores by up to 0.15

Segmentation Dice scores increased by up to 0.146

Using proxy models and radiologist feedback enhances synthetic image quality

Abstract

Purpose: To explore best-practice approaches for generating synthetic chest X-ray images and augmenting medical imaging datasets to optimize the performance of deep learning models in downstream tasks like classification and segmentation. Materials and Methods: We utilized a latent diffusion model to condition the generation of synthetic chest X-rays on text prompts and/or segmentation masks. We explored methods like using a proxy model and using radiologist feedback to improve the quality of synthetic data. These synthetic images were then generated from relevant disease information or geometrically transformed segmentation masks and added to ground truth training set images from the CheXpert, CANDID-PTX, SIIM, and RSNA Pneumonia datasets to measure improvements in classification and segmentation model performance on the test sets. F1 and Dice scores were used to evaluate classification and segmentation respectively. One-tailed t-tests with Bonferroni correction assessed the statistical significance of performance improvements with synthetic data. Results: Across all experiments, the synthetic data we generated resulted in a maximum mean classification F1 score improvement of 0.150453 (CI: 0.099108-0.201798; P=0.0031) compared to using only real data. For segmentation, the maximum Dice score improvement was 0.14575 (CI: 0.108267-0.183233; P=0.0064). Conclusion: Best practices for generating synthetic chest X-ray images for downstream tasks include conditioning on single-disease labels or geometrically transformed segmentation masks, as well as potentially using proxy modeling for fine-tuning such generations.