Academic Journal
Deep-Learning-Based Image Reconstruction to Improve End-Diastolic and Systolic Cardiac T1 Mapping.
| Τίτλος: | Deep-Learning-Based Image Reconstruction to Improve End-Diastolic and Systolic Cardiac T1 Mapping. |
|---|---|
| Συγγραφείς: | Amsel D; Medical Image and Data Analysis (MIDAS.lab), Department of Diagnostic and Interventional Radiology, University of Tuebingen, Tuebingen, Germany.; Research & Clinical Translation, Magnetic Resonance, Siemens Healthineers AG, Erlangen, Germany., Wetzl J; Research & Clinical Translation, Magnetic Resonance, Siemens Healthineers AG, Erlangen, Germany., Giese D; Research & Clinical Translation, Magnetic Resonance, Siemens Healthineers AG, Erlangen, Germany., Tillmanns C; Diagnostikum, Berlin, Germany., Gebker R; Diagnostikum, Berlin, Germany., Chow K; Cardiovascular MR R&D, Siemens Healthcare Ltd, Calgary, Canada., Schmidt M; Research & Clinical Translation, Magnetic Resonance, Siemens Healthineers AG, Erlangen, Germany., Lingg A; Department of Radiology, University Hospital Tuebingen, Tuebingen, Germany., Kübler J; Department of Radiology, University Hospital Tuebingen, Tuebingen, Germany., Krumm P; Department of Radiology, University Hospital Tuebingen, Tuebingen, Germany., Küstner T; Medical Image and Data Analysis (MIDAS.lab), Department of Diagnostic and Interventional Radiology, University of Tuebingen, Tuebingen, Germany. |
| Πηγή: | Magnetic resonance in medicine [Magn Reson Med] 2026 Aug; Vol. 96 (2), pp. 892-907. Date of Electronic Publication: 2026 Mar 19. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Wiley Country of Publication: United States NLM ID: 8505245 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1522-2594 (Electronic) Linking ISSN: 07403194 NLM ISO Abbreviation: Magn Reson Med Subsets: MEDLINE |
| Imprint Name(s): | Publication: 1999- : New York, NY : Wiley Original Publication: San Diego : Academic Press |
| Ιατρικοί όροι (MeSH): | Image Processing, Computer-Assisted*/methods , Heart*/diagnostic imaging , Magnetic Resonance Imaging*/methods , Deep Learning*, Image Interpretation, Computer-Assisted/methods ; Humans ; Systole ; Algorithms ; Diastole ; Retrospective Studies ; Prospective Studies |
| Περίληψη: | Purpose: To develop an image reconstruction method that enables increased spatial resolution cardiac T1 mapping in both the end-diastolic and systolic phase, that shows high T1 agreement with the clinical standard. The resolution gain is achieved by increasing the acceleration rate of MOLLI single-shot images to R = 4, while maintaining a sufficiently short acquisition window. Methods: A modified end-to-end variational network (MappingVN) is proposed. The modifications include a re-ordered sheared-grid sampling pattern, 2D + contrast convolutions and the use of patchwise squeeze-and-excitation layers. The method was evaluated in terms of image quality and T1 agreement with reference MOLLI T1 maps using retrospectively undersampled patient data. Furthermore, the method was additionally evaluated in a prospective setting comparing high-resolution T1 maps (1.14 × 1.14 mm2) to reference T1 maps in standard resolution (1.41 × 2.13 mm2). Finally, the applicability for systolic T1 mapping was explored using increased acceleration to shorten the acquisition window. Results: The MappingVN showed improved SSIM scores of 0.95 and 0.98 on 1.5T and 3 T compared to 0.93 and 0.96 for GRAPPA. In high-resolution end-diastolic T1 maps stronger T1 agreement (MappingVN: -3 ± 69 ms on 1.5T, -11 ± 70 ms on 3T, GRPPA: -9 ± 129 ms on 1.5T, 14 ± 106 ms) could be observed. For systolic T1 mapping the MappingVN reduced the occurrence of motion artifacts. Conclusion: The proposed method enables high spatial resolution cardiac T1 mapping in both end-diastolic and systolic phases. Resulting maps show good T1 agreement with the clinical standard and may improve the visibility of small focal lesions while reducing partial volume effects. (© 2026 The Author(s). Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.) |
| References: | J Cardiovasc Magn Reson. 2017 Oct 9;19(1):75. (PMID: 28992817) Magn Reson Med. 2021 Sep;86(3):1647-1661. (PMID: 33821529) Magn Reson Med. 2025 Jan;93(1):138-150. (PMID: 39188085) Magn Reson Med. 1999 Nov;42(5):952-62. (PMID: 10542355) Phys Med Biol. 2020 Nov 24;65(22):225024. (PMID: 33045693) Magn Reson Med. 2014 Mar;71(3):990-1001. (PMID: 23649942) J Cardiovasc Magn Reson. 2015 Aug 28;17:77. (PMID: 26315682) Magn Reson Med. 2021 Nov;86(5):2837-2852. (PMID: 34240753) Circulation. 2002 Jan 29;105(4):539-42. (PMID: 11815441) Phys Med Biol. 2015 Nov 7;60(21):R297-322. (PMID: 26448064) IEEE Trans Med Imaging. 2022 Nov;41(11):3320-3331. (PMID: 35714093) Magn Reson Med. 2004 Jul;52(1):141-6. (PMID: 15236377) Diagnostics (Basel). 2026 Jan 21;16(2):. (PMID: 41594324) Sci Rep. 2018 Mar 27;8(1):5251. (PMID: 29588504) Eur J Radiol. 2018 Dec;109:223-234. (PMID: 30539758) Magn Reson Med. 2002 Jun;47(6):1202-10. (PMID: 12111967) Magn Reson Med. 2014 Jun;71(6):2082-95. (PMID: 23881866) J Magn Reson Imaging. 2025 Mar;61(3):1388-1401. (PMID: 39143028) J Cardiovasc Magn Reson. 2013 Jun 18;15:53. (PMID: 23777327) IEEE Signal Process Mag. 2023 Jan;40(1):98-114. (PMID: 37304755) J Cardiovasc Magn Reson. 2022 Jan 6;24(1):6. (PMID: 34986850) Magn Reson Med. 2012 Oct;68(4):1127-34. (PMID: 22161952) J Cardiovasc Magn Reson. 2013 Oct 14;15:92. (PMID: 24124732) J Cardiovasc Magn Reson. 2016 Nov 30;18(1):89. (PMID: 27899132) Magn Reson Med. 2015 Mar;73(3):1125-36. (PMID: 24760724) Phys Med Biol. 2022 Dec 09;67(24):. (PMID: 36265478) Med Image Anal. 2021 May;70:102017. (PMID: 33721693) Int J Cardiovasc Imaging. 2015 Jun;31(5):1001-10. (PMID: 25764279) J Cardiovasc Magn Reson. 2010 Nov 19;12:69. (PMID: 21092095) Circ J. 2015;79(3):487-94. (PMID: 25746524) MAGMA. 2024 Jul;37(3):335-368. (PMID: 39042206) IEEE J Sel Top Signal Process. 2020 Oct;14(6):1151-1162. (PMID: 33613806) Eur Heart J Cardiovasc Imaging. 2017 Sep 01;18(9):1034-1040. (PMID: 27590835) Magn Reson Med. 2010 Oct;64(4):1114-20. (PMID: 20564599) IEEE Trans Med Imaging. 2019 Feb;38(2):394-405. (PMID: 30106719) IEEE Trans Med Imaging. 2018 Feb;37(2):491-503. (PMID: 29035212) Magn Reson Med. 2024 Jul;92(1):98-111. (PMID: 38342980) Magn Reson Med. 2014 Mar;71(3):1024-34. (PMID: 23650078) J Cardiovasc Magn Reson. 2014 Jan 04;16:2. (PMID: 24387626) Int J Cardiovasc Imaging. 2022 Oct;38(10):2219-2225. (PMID: 37726459) Magn Reson Imaging. 2024 Apr;107:33-46. (PMID: 38184093) Magn Reson Med. 2005 Nov;54(5):1172-84. (PMID: 16193468) Med Image Anal. 2025 Apr;101:103485. (PMID: 39946779) Magn Reson Med. 2005 Jun;53(6):1372-82. (PMID: 15906282) Comput Med Imaging Graph. 2020 Mar;80:101698. (PMID: 31935666) Radiology. 2014 Sep;272(3):683-9. (PMID: 24702727) |
| Contributed Indexing: | Keywords: deep learning reconstruction; myocardial T1 mapping; quantitative MRI |
| Entry Date(s): | Date Created: 20260320 Date Completed: 20260615 Latest Revision: 20260813 |
| Update Code: | 20260813 |
| PubMed Central ID: | PMC13269227 |
| DOI: | 10.1002/mrm.70353 |
| PMID: | 41856949 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1522-2594 |
|---|---|
| DOI: | 10.1002/mrm.70353 |