Myocardial Scar Enhancement in LGE Cardiac MRI Using Localized Diffusion

Marta Hasny, Omer B. Demirel, Amine Amyar, Shahrooz Faghihroohi, Reza Nezafat

Abstract: Late gadolinium enhancement (LGE) imaging is considered the gold-standard technique for evaluating myocardial scar/fibrosis. In LGE, an inversion pulse is played before imaging to create a contrast between healthy and scarred regions. However, several factors can impact the contrast quality, impacting diagnostic interpretation. Furthermore, the quantification of scar burden is highly dependent on image quality. Deep learning-based automated segmentation algorithms often fail when there is no clear boundary between healthy and scarred tissue. This study sought to develop a generative model for improving the contrast of healthy-scarred myocardium in LGE. We propose a localized conditional diffusion model, in which only a region-of-interest (ROI), in this case heart, is subjected to the noising process, adapting the learning process to the local nature of our proposed enhancement. The scar-enhanced images, used as training targets, are generated via tissue-specific gamma correction. A segmentation model is trained and used to extract the heart regions. The inference speed is improved by leveraging partial diffusion, applying noise only up to an intermediate step. Furthermore, utilizing the stochastic nature of diffusion models, repeated inference leads to improved scar enhancement of ambiguous regions. The proposed algorithm was evaluated using LGE images collected in 929 patients with hypertrophic cardiomyopathy, in a multi-center, multi-vendor study. Our results show visual improvements of scar-healthy myocardium contrast. To further demonstrate the strength of our method, we evaluate our performance against various image enhancement models where the proposed approach shows higher contrast enhancement. The code is available at: https://github.com/HMS-CardiacMR/Scar_enhancement.