Conditional mask diffusion tested for left atrial scar segmentation in MRI
CMDiff: Left Atrial Scar Segmentation from 3D LGE MRI Using Conditional Mask Diffusion Model: A Feasibility Study
Computer Vision and Pattern Recognition
Summary
Segmenting scars in the heart's left atrium using MRI images is hard because scars are small and hard to see clearly. The authors tested a new method called CMDiff that tries to improve this by generating clearer masks of scars in 3D images. They compared CMDiff to a traditional method and found it was possible to use CMDiff but it did not perform better. This means CMDiff is an alternative way to do the task, but it doesn't yet improve accuracy or reliability.
What this means in practice
- •For medical image analysts: Use CMDiff as an alternative method to segment left atrial scars in 3D cardiac MRI despite no current accuracy improvement over standard methods.
- •For clinical imaging software developers: Integrate CMDiff code to experiment with conditional diffusion mask models for segmenting atrial scars in cardiac MRI datasets.
Authors
Jing Zhang, Bastien Bergere, Jonas Leite, Emilie Bollache, Mikaël Laredo, Alban Redheuil, Nadjia Kachenoura
Abstract
Late gadolinium enhancement (LGE) cardiac MRI enables non-invasive assessment of left atrial (LA) scar, an imaging marker associated with atrial fibrillation ablation outcome. However, automatic scar segmentation is hindered by low contrast, the thin atrial wall, scarce labels, and extreme class imbalance. Conditional diffusion offers iterative mask generation, but its suitability for sparse 3D LA scar segmentation remains unclear. To address this gap, we propose Conditional Mask Diffusion (CMDiff), which predicts clean masks using a dynamic-encoder-conditioned 3D sinusoidal UNet. We compared CMDiff with a deterministic baseline on identical cases in five-fold cross-validation of 60 scar-labelled public LASCARQS subjects, with 48 training and 12 held-out cases per fold. CMDiff achieved a scar DSC of 0.47 $\pm$ 0.08, HD95 of 12.89 $\pm$ 6.39 mm, and ASD of 1.91 $\pm$ 0.96 mm, compared with deterministic baseline values of 0.51 $\pm$ 0.08, 10.86 $\pm$ 5.39 mm, and 1.58 $\pm$ 1.03 mm, respectively. Under the same implementation, clean-mask prediction performed substantially better than the noise-prediction configuration evaluated in this study. Thus, CMDiff was technically feasible but did not improve segmentation performance: DSC was lower, and both HD95 and ASD were higher. Direct mask diffusion therefore provides an analytical alternative, but not a competitive performance advance for this task. The source code is publicly available at https://github.com/jizhang02/CMDiff.