1
|
You SH, Cho Y, Kim B, Yang KS, Kim I, Kim BK, Pak A, Park SE. Deep Learning-Based Synthetic TOF-MRA Generation Using Time-Resolved MRA in Fast Stroke Imaging. AJNR Am J Neuroradiol 2023; 44:1391-1398. [PMID: 38049991 PMCID: PMC10714844 DOI: 10.3174/ajnr.a8063] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Accepted: 10/17/2023] [Indexed: 12/06/2023]
Abstract
BACKGROUND AND PURPOSE Time-resolved MRA enables collateral evaluation in acute ischemic stroke with large-vessel occlusion; however, a low SNR and spatial resolution impede the diagnosis of vascular occlusion. We developed a CycleGAN-based deep learning model to generate high-resolution synthetic TOF-MRA images using time-resolved MRA and evaluated its image quality and clinical efficacy. MATERIALS AND METHODS This retrospective, single-center study included 397 patients who underwent both TOF- and time-resolved MRA between April 2021 and January 2022. Patients were divided into 2 groups for model development and image-quality validation. Image quality was evaluated qualitatively and quantitatively with 3 sequences. A multireader diagnostic optimality evaluation was performed by 16 radiologists. For clinical validation, we evaluated 123 patients who underwent fast stroke MR imaging to assess acute ischemic stroke. The diagnostic confidence level and decision time for large-vessel occlusion were also evaluated. RESULTS Median values of overall image quality, noise, sharpness, venous contamination, and SNR for M1, M2, the basilar artery, and posterior cerebral artery are better with synthetic TOF than with time-resolved MRA. However, with respect to real TOF, synthetic TOF presents worse median values of overall image quality, sharpness, vascular conspicuity, and SNR for M3, the basilar artery, and the posterior cerebral artery. During the multireader evaluation, radiologists could not discriminate synthetic TOF images from TOF images. During clinical validation, both readers demonstrated increases in diagnostic confidence levels and decreases in decision time. CONCLUSIONS A CycleGAN-based deep learning model was developed to generate synthetic TOF from time-resolved MRA. Synthetic TOF can potentially assist in the detection of large-vessel occlusion in stroke centers using time-resolved MRA.
Collapse
Affiliation(s)
- Sung-Hye You
- From the Department of Radiology, (S.-H.Y., B.K., B.K.K., A.P., S.E.P.), Anam Hospital, Korea University College of Medicine, Seoul, Korea
| | - Yongwon Cho
- Biomedical Research Center (Y.C.), Korea University College of Medicine, Seoul, Korea
| | - Byungjun Kim
- From the Department of Radiology, (S.-H.Y., B.K., B.K.K., A.P., S.E.P.), Anam Hospital, Korea University College of Medicine, Seoul, Korea
| | - Kyung-Sook Yang
- Department of Biostatistics (K.-S.Y.), Korea University College of Medicine, Seoul, Korea
| | | | - Bo Kyu Kim
- From the Department of Radiology, (S.-H.Y., B.K., B.K.K., A.P., S.E.P.), Anam Hospital, Korea University College of Medicine, Seoul, Korea
| | - Arim Pak
- From the Department of Radiology, (S.-H.Y., B.K., B.K.K., A.P., S.E.P.), Anam Hospital, Korea University College of Medicine, Seoul, Korea
| | - Sang Eun Park
- From the Department of Radiology, (S.-H.Y., B.K., B.K.K., A.P., S.E.P.), Anam Hospital, Korea University College of Medicine, Seoul, Korea
| |
Collapse
|