Accelerated phase-contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural network
ABSTRACT: Background: Cardiovascular magnetic resonance (CMR) phase contrast is used to quantify blood flow. We sought to develop a complex-difference reconstruction for inline super-resolution of phase-contrast flow (CRISPFlow) to accelerate phase-contrast imaging. Methods: CRISPFlow was built on...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Journal of Cardiovascular Magnetic Resonance |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1097664724011554 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556927865159680 |
|---|---|
| author | Manuel A. Morales Fahime Ghanbari Ömer Burak Demirel Jordan A. Street Tess E. Wallace Rachel Davids Jennifer Rodriguez Scott Johnson Patrick Pierce Warren J. Manning Reza Nezafat |
| author_facet | Manuel A. Morales Fahime Ghanbari Ömer Burak Demirel Jordan A. Street Tess E. Wallace Rachel Davids Jennifer Rodriguez Scott Johnson Patrick Pierce Warren J. Manning Reza Nezafat |
| author_sort | Manuel A. Morales |
| collection | DOAJ |
| description | ABSTRACT: Background: Cardiovascular magnetic resonance (CMR) phase contrast is used to quantify blood flow. We sought to develop a complex-difference reconstruction for inline super-resolution of phase-contrast flow (CRISPFlow) to accelerate phase-contrast imaging. Methods: CRISPFlow was built on the super-resolution generative adversarial network. The model was trained and tested (4:1 ratio) using retrospectively identified phase-contrast images from 2020 patients (56 ± 16 years; 1131 men) referred for clinical 3T CMR at a single center from 2018 to 2023. For testing, ascending aortic flow images collected with 2.5 × 1.9 mm2 resolution using generalized autocalibrating partially parallel acquisitions (GRAPPA) were used to synthesize images with 7.5 × 1.9 mm2 resolution. CRISPFlow subsequently restored spatial resolution. In a prospective validation study of 38 participants (57 ± 15 years; 14 men) and 16 healthy individuals (42 ± 16 years; 6 men), CRISPFlow was applied to phase-contrast images collected with 7.5 × 1.9 mm2 resolution with use of GRAPPA and was compared to GRAPPA-accelerated images collected with 2.3 × 1.9 mm2 resolution. A blur metric was used to quantify sharpness. Aortic flow measurements were obtained semi-automatically. Statistical evaluation included analysis of variance, Bland-Altman analysis, and Pearson correlation coefficient (r). Results: CRISPFlow reconstruction was successful in all cases. CRISPFlow reduced blurring in retrospective (0.35 vs 0.47, P < 0.001) and prospective (0.34 vs 0.48, P < 0.001) images with 7.5 × 1.9 mm2 resolution. Blurring in CRISPFlow images was similar to blurring in images with 2.5 × 1.9 mm2 (0.35 vs 0.35, P = 0.4082) and 2.3 × 1.9 mm2 (0.34 vs 0.32, P < 0.001) resolution. Bland-Altman differences in forward volume (−2 mL [−8 to 3 mL]), regurgitant volume (0 mL [−3 to 2 mL]), and a fraction (0% [−5 to 4%]) showed good agreement between the two techniques in a retrospective cohort. Differences in forward volume (1 mL [−11 to 14 ml]) also showed good agreement in the prospective cohort. There was a strong correlation (all r > 0.90) between GRAPPA and CRISPFlow measurements of flow in both studies. Conclusion: We demonstrated the potential of CRISPFlow to accelerate phase contrast CMR. |
| format | Article |
| id | doaj-art-3cdca8dd8dae478b9d7a204c641ac1ab |
| institution | Kabale University |
| issn | 1097-6647 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Cardiovascular Magnetic Resonance |
| spelling | doaj-art-3cdca8dd8dae478b9d7a204c641ac1ab2025-01-07T04:17:11ZengElsevierJournal of Cardiovascular Magnetic Resonance1097-66472025-01-01271101128Accelerated phase-contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural networkManuel A. Morales0Fahime Ghanbari1Ömer Burak Demirel2Jordan A. Street3Tess E. Wallace4Rachel Davids5Jennifer Rodriguez6Scott Johnson7Patrick Pierce8Warren J. Manning9Reza Nezafat10Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USADepartment of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USADepartment of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USADepartment of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USASiemens Medical Solutions USA, Inc., Boston, Massachusetts, USASiemens Medical Solutions USA, Inc., Chicago, Illinois, USADepartment of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USADepartment of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USADepartment of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USADepartment of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA; Department of Radiology, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USADepartment of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts, USA; Corresponding author.ABSTRACT: Background: Cardiovascular magnetic resonance (CMR) phase contrast is used to quantify blood flow. We sought to develop a complex-difference reconstruction for inline super-resolution of phase-contrast flow (CRISPFlow) to accelerate phase-contrast imaging. Methods: CRISPFlow was built on the super-resolution generative adversarial network. The model was trained and tested (4:1 ratio) using retrospectively identified phase-contrast images from 2020 patients (56 ± 16 years; 1131 men) referred for clinical 3T CMR at a single center from 2018 to 2023. For testing, ascending aortic flow images collected with 2.5 × 1.9 mm2 resolution using generalized autocalibrating partially parallel acquisitions (GRAPPA) were used to synthesize images with 7.5 × 1.9 mm2 resolution. CRISPFlow subsequently restored spatial resolution. In a prospective validation study of 38 participants (57 ± 15 years; 14 men) and 16 healthy individuals (42 ± 16 years; 6 men), CRISPFlow was applied to phase-contrast images collected with 7.5 × 1.9 mm2 resolution with use of GRAPPA and was compared to GRAPPA-accelerated images collected with 2.3 × 1.9 mm2 resolution. A blur metric was used to quantify sharpness. Aortic flow measurements were obtained semi-automatically. Statistical evaluation included analysis of variance, Bland-Altman analysis, and Pearson correlation coefficient (r). Results: CRISPFlow reconstruction was successful in all cases. CRISPFlow reduced blurring in retrospective (0.35 vs 0.47, P < 0.001) and prospective (0.34 vs 0.48, P < 0.001) images with 7.5 × 1.9 mm2 resolution. Blurring in CRISPFlow images was similar to blurring in images with 2.5 × 1.9 mm2 (0.35 vs 0.35, P = 0.4082) and 2.3 × 1.9 mm2 (0.34 vs 0.32, P < 0.001) resolution. Bland-Altman differences in forward volume (−2 mL [−8 to 3 mL]), regurgitant volume (0 mL [−3 to 2 mL]), and a fraction (0% [−5 to 4%]) showed good agreement between the two techniques in a retrospective cohort. Differences in forward volume (1 mL [−11 to 14 ml]) also showed good agreement in the prospective cohort. There was a strong correlation (all r > 0.90) between GRAPPA and CRISPFlow measurements of flow in both studies. Conclusion: We demonstrated the potential of CRISPFlow to accelerate phase contrast CMR.http://www.sciencedirect.com/science/article/pii/S1097664724011554Super-resolutionPhase contrastFlowComplex differenceDeep learningAcceleration |
| spellingShingle | Manuel A. Morales Fahime Ghanbari Ömer Burak Demirel Jordan A. Street Tess E. Wallace Rachel Davids Jennifer Rodriguez Scott Johnson Patrick Pierce Warren J. Manning Reza Nezafat Accelerated phase-contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural network Journal of Cardiovascular Magnetic Resonance Super-resolution Phase contrast Flow Complex difference Deep learning Acceleration |
| title | Accelerated phase-contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural network |
| title_full | Accelerated phase-contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural network |
| title_fullStr | Accelerated phase-contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural network |
| title_full_unstemmed | Accelerated phase-contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural network |
| title_short | Accelerated phase-contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural network |
| title_sort | accelerated phase contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural network |
| topic | Super-resolution Phase contrast Flow Complex difference Deep learning Acceleration |
| url | http://www.sciencedirect.com/science/article/pii/S1097664724011554 |
| work_keys_str_mv | AT manuelamorales acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork AT fahimeghanbari acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork AT omerburakdemirel acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork AT jordanastreet acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork AT tessewallace acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork AT racheldavids acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork AT jenniferrodriguez acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork AT scottjohnson acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork AT patrickpierce acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork AT warrenjmanning acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork AT rezanezafat acceleratedphasecontrastmagneticresonanceimagingwithuseofresolutionenhancementgenerativeadversarialneuralnetwork |