Li, Jie
Xu, Meiling
Jiang, Baiyang
Dong, Qian
Xia, Yi
Zhou, Taohu
Lin, Xiaoqing
Ma, Yanqing
Jiang, Song
Zhang, Zhihao
Xiang, Lei
Fan, Li https://orcid.org/0000-0003-4722-3933
Liu, Shiyuan
Funding for this research was provided by:
National Key Research and Development Program of China (2022YFC2010002, 2022YFC2010006)
National Key Research and Development Program of China (2022YFC2010000)
National Natural Science Foundation of China (82171926, 81930049, 82430065)
Medical Imaging Database Construction Program of National Health Commission (YXFSC2022JJSJ002)
Clinical Innovative Project of Shanghai Changzheng Hospital (2020YLCYJY24)
Program of Science and Technology Commission of Shanghai Municipality (21DZ2202600)
the Shanghai Sailing Program (20YF1449000)
Article History
Received: 1 February 2025
Revised: 20 May 2025
Accepted: 14 June 2025
First Online: 18 July 2025
Compliance with ethical standards
:
: The scientific guarantor of this publication is Li Fan.
: Z.Z. and L.X. are affiliated with Shentou Medical Inc. The remaining authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article. Dr. Christopher F. Beaulieu is a paid consultant of Subtle Medical Inc.
: Not applicable.
: Only if the study is on human subjects: Written informed consent was obtained from all subjects (patients) in this study.
: Institutional Review Board approval was obtained.
: In this study, all 199 patients have been reported in a previous article, which evaluated the application of deep learning reconstruction (DL) techniques in accelerating and optimizing the quality of spine MRI. In this manuscript, we generate STIR images from T1 and T2 sequences and compare them with standard STIR images to validate the value of generating STIR for application in shortening scan time, improving image quality, and meeting clinical diagnostic requirements.
: