Report on the AAPM Grand Challenge on deep generative modeling for learning medical image statistics

TL;DR

This paper reports on the 2023 AAPM Grand Challenge, which evaluated deep generative models for medical imaging by assessing image quality and domain-specific statistical reproducibility, highlighting the importance of tailored evaluation methods.

Contribution

It introduces a comprehensive evaluation framework for DGMs in medical imaging, including a new ranking method based on image statistics and artifact analysis, advancing domain-specific assessment.

Findings

Top models used conditional latent diffusion and GANs.

Evaluation rankings differed from FID scores.

Different models showed similar artifacts.

Abstract

The findings of the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics are reported in this Special Report. The goal of this challenge was to promote the development of deep generative models (DGMs) for medical imaging and to emphasize the need for their domain-relevant assessment via the analysis of relevant image statistics. As part of this Grand Challenge, a training dataset was developed based on 3D anthropomorphic breast phantoms from the VICTRE virtual imaging toolbox. A two-stage evaluation procedure consisting of a preliminary check for memorization and image quality (based on the Frechet Inception distance (FID)), and a second stage evaluating the reproducibility of image statistics corresponding to domain-relevant radiomic features was developed. A summary measure was employed to rank the submissions. Additional analyses of submissions was performed to assess DGM performance specific to individual feature families, and to identify various artifacts. 58 submissions from 12 unique users were received for this Challenge. The top-ranked submission employed a conditional latent diffusion model, whereas the joint runners-up employed a generative adversarial network, followed by another network for image superresolution. We observed that the overall ranking of the top 9 submissions according to our evaluation method (i) did not match the FID-based ranking, and (ii) differed with respect to individual feature families. Another important finding from our additional analyses was that different DGMs demonstrated similar kinds of artifacts. This Grand Challenge highlighted the need for domain-specific evaluation to further DGM design as well as deployment. It also demonstrated that the specification of a DGM may differ depending on its intended use.