Deep Generative Model-based Quality Control for Cardiac MRI Segmentation

TL;DR

This paper introduces a deep generative model-based framework for real-time quality control of cardiac MRI segmentation, effectively detecting poor segmentations and outperforming traditional methods.

Contribution

It presents a novel deep generative approach that learns a manifold of good-quality segmentations and assesses new segmentations by their deviation from this manifold, enhancing quality control.

Findings

High prediction accuracy on two datasets

Better generalisation than regression-based methods

Real-time, model-agnostic quality assessment

Abstract

In recent years, convolutional neural networks have demonstrated promising performance in a variety of medical image segmentation tasks. However, when a trained segmentation model is deployed into the real clinical world, the model may not perform optimally. A major challenge is the potential poor-quality segmentations generated due to degraded image quality or domain shift issues. There is a timely need to develop an automated quality control method that can detect poor segmentations and feedback to clinicians. Here we propose a novel deep generative model-based framework for quality control of cardiac MRI segmentation. It first learns a manifold of good-quality image-segmentation pairs using a generative model. The quality of a given test segmentation is then assessed by evaluating the difference from its projection onto the good-quality manifold. In particular, the projection is refined through iterative search in the latent space. The proposed method achieves high prediction accuracy on two publicly available cardiac MRI datasets. Moreover, it shows better generalisation ability than traditional regression-based methods. Our approach provides a real-time and model-agnostic quality control for cardiac MRI segmentation, which has the potential to be integrated into clinical image analysis workflows.