Conditional diffusion-generated super-resolution for myocardial perfusion MRI
IntroductionMyocardial perfusion MRI is important for diagnosing coronary artery disease, but current clinical methods face challenges in balancing spatial resolution, temporal resolution, and slice coverage. Achieving broader slice coverage and higher temporal resolution is essential for accurately...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2025.1499593/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589820204941312 |
|---|---|
| author | Changyu Sun Changyu Sun Neha Goyal Yu Wang Darla L. Tharp Senthil Kumar Talissa A. Altes |
| author_facet | Changyu Sun Changyu Sun Neha Goyal Yu Wang Darla L. Tharp Senthil Kumar Talissa A. Altes |
| author_sort | Changyu Sun |
| collection | DOAJ |
| description | IntroductionMyocardial perfusion MRI is important for diagnosing coronary artery disease, but current clinical methods face challenges in balancing spatial resolution, temporal resolution, and slice coverage. Achieving broader slice coverage and higher temporal resolution is essential for accurately detecting abnormalities across different slice locations but remains difficult due to constraints in acquisition speed and heart rate variability. While techniques like parallel imaging and compressed sensing have significantly advanced perfusion imaging, they still suffer from noise amplification, residual artifacts, and potential temporal blurring due to the rapid transit of dynamic contrast vs. the temporal constraints of the reconstruction.MethodsThis study introduces a conditional diffusion-based generative model for myocardial perfusion MRI super resolution, addressing the trade-offs between spatiotemporal resolution and slice coverage. We adapted Denoising Diffusion Probabilistic Models (DDPM) to enhance low-resolution perfusion images into high-resolution outputs without requiring temporal regularization. The forward diffusion process introduces Gaussian noise incrementally, while the reverse process employs a U-Net architecture to progressively denoise the images, conditioned on the low-resolution input image.ResultsWe trained and validated the model on a retrospective dataset of dynamic contrast-enhanced (DCE) perfusion MRI, consisting of both stress and rest images from 47 patients with heart disease. Our results showed significant image quality improvements, with a 5.1% reduction in nRMSE, a 1.1% increase in PSNR, and a 2.2% boost in SSIM compared to GAN-based super-resolution method (P < 0.05 for all metrics using paired t-test) in retrospective study. For the 9 prospective subjects, we achieved a total nominal acceleration of 8.5-fold across 5–6 slices through a combination of low-resolution acquisition and GRAPPA. PerfGen outperformed GAN-based approach in sharpness (4.36 ± 0.38 vs. 4.89 ± 0.22) and overall image quality (4.14 ± 0.28 vs. 4.89 ± 0.22), as assessed by two experts in a blinded evaluation (P < 0.05) in prospective study.DiscussionThis work demonstrates the capability of diffusion-based generative models in generating high-resolution myocardial perfusion MRI from conditional low-resolution images. This approach has shown the potentials to accelerate myocardial perfusion MRI while enhancing slice coverage and temporal resolution, offering a promising alternative to existing methods. |
| format | Article |
| id | doaj-art-1b7805e4948b4eaea3f443003b9705be |
| institution | Kabale University |
| issn | 2297-055X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj-art-1b7805e4948b4eaea3f443003b9705be2025-01-24T07:13:41ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2025-01-011210.3389/fcvm.2025.14995931499593Conditional diffusion-generated super-resolution for myocardial perfusion MRIChangyu Sun0Changyu Sun1Neha Goyal2Yu Wang3Darla L. Tharp4Senthil Kumar5Talissa A. Altes6Department of Chemical and Biomedical Engineering, University of Missouri, Columbia, MO, United StatesDepartment of Radiology, University of Missouri, Columbia, MO, United StatesDepartment of Medicine, University of Missouri, Columbia, MO, United StatesDepartment of Chemical and Biomedical Engineering, University of Missouri, Columbia, MO, United StatesDepartment of Biomedical Sciences, University of Missouri, Columbia, MO, United StatesDepartment of Medicine, University of Missouri, Columbia, MO, United StatesDepartment of Radiology, University of Missouri, Columbia, MO, United StatesIntroductionMyocardial perfusion MRI is important for diagnosing coronary artery disease, but current clinical methods face challenges in balancing spatial resolution, temporal resolution, and slice coverage. Achieving broader slice coverage and higher temporal resolution is essential for accurately detecting abnormalities across different slice locations but remains difficult due to constraints in acquisition speed and heart rate variability. While techniques like parallel imaging and compressed sensing have significantly advanced perfusion imaging, they still suffer from noise amplification, residual artifacts, and potential temporal blurring due to the rapid transit of dynamic contrast vs. the temporal constraints of the reconstruction.MethodsThis study introduces a conditional diffusion-based generative model for myocardial perfusion MRI super resolution, addressing the trade-offs between spatiotemporal resolution and slice coverage. We adapted Denoising Diffusion Probabilistic Models (DDPM) to enhance low-resolution perfusion images into high-resolution outputs without requiring temporal regularization. The forward diffusion process introduces Gaussian noise incrementally, while the reverse process employs a U-Net architecture to progressively denoise the images, conditioned on the low-resolution input image.ResultsWe trained and validated the model on a retrospective dataset of dynamic contrast-enhanced (DCE) perfusion MRI, consisting of both stress and rest images from 47 patients with heart disease. Our results showed significant image quality improvements, with a 5.1% reduction in nRMSE, a 1.1% increase in PSNR, and a 2.2% boost in SSIM compared to GAN-based super-resolution method (P < 0.05 for all metrics using paired t-test) in retrospective study. For the 9 prospective subjects, we achieved a total nominal acceleration of 8.5-fold across 5–6 slices through a combination of low-resolution acquisition and GRAPPA. PerfGen outperformed GAN-based approach in sharpness (4.36 ± 0.38 vs. 4.89 ± 0.22) and overall image quality (4.14 ± 0.28 vs. 4.89 ± 0.22), as assessed by two experts in a blinded evaluation (P < 0.05) in prospective study.DiscussionThis work demonstrates the capability of diffusion-based generative models in generating high-resolution myocardial perfusion MRI from conditional low-resolution images. This approach has shown the potentials to accelerate myocardial perfusion MRI while enhancing slice coverage and temporal resolution, offering a promising alternative to existing methods.https://www.frontiersin.org/articles/10.3389/fcvm.2025.1499593/fullsuper-resolutionmyocardial perfusion MRIdeep learningdiffusion probabilistic models (DDPM)conditional generative modeldynamic contrast-enhanced MRI (DCE MRI) |
| spellingShingle | Changyu Sun Changyu Sun Neha Goyal Yu Wang Darla L. Tharp Senthil Kumar Talissa A. Altes Conditional diffusion-generated super-resolution for myocardial perfusion MRI Frontiers in Cardiovascular Medicine super-resolution myocardial perfusion MRI deep learning diffusion probabilistic models (DDPM) conditional generative model dynamic contrast-enhanced MRI (DCE MRI) |
| title | Conditional diffusion-generated super-resolution for myocardial perfusion MRI |
| title_full | Conditional diffusion-generated super-resolution for myocardial perfusion MRI |
| title_fullStr | Conditional diffusion-generated super-resolution for myocardial perfusion MRI |
| title_full_unstemmed | Conditional diffusion-generated super-resolution for myocardial perfusion MRI |
| title_short | Conditional diffusion-generated super-resolution for myocardial perfusion MRI |
| title_sort | conditional diffusion generated super resolution for myocardial perfusion mri |
| topic | super-resolution myocardial perfusion MRI deep learning diffusion probabilistic models (DDPM) conditional generative model dynamic contrast-enhanced MRI (DCE MRI) |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2025.1499593/full |
| work_keys_str_mv | AT changyusun conditionaldiffusiongeneratedsuperresolutionformyocardialperfusionmri AT changyusun conditionaldiffusiongeneratedsuperresolutionformyocardialperfusionmri AT nehagoyal conditionaldiffusiongeneratedsuperresolutionformyocardialperfusionmri AT yuwang conditionaldiffusiongeneratedsuperresolutionformyocardialperfusionmri AT darlaltharp conditionaldiffusiongeneratedsuperresolutionformyocardialperfusionmri AT senthilkumar conditionaldiffusiongeneratedsuperresolutionformyocardialperfusionmri AT talissaaaltes conditionaldiffusiongeneratedsuperresolutionformyocardialperfusionmri |