EUVIMEDEUVIMED entdecken
Multizentrische Studie

Deep learning synthesis of virtual T2-weighted fat-suppressed MR images: a multi-center study

Chenxi Wang, Jun Xu, Meng Zhang, Dapeng Hao, Senpeng Zhang, Ning Lang

European Journal of Radiology · 2026-06 · 199 · 112797

DOI: 10.1016/j.ejrad.2026.112797 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift European Journal of Radiology, 2026-06. Verfasst von Chenxi Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, State Key Laboratory of Vascular Homeostasis and Remodeling, Peking University Third Hospital, Beijing 100191, China. Electr…. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Deep Learning, Image Interpretation, Computer-Assisted, Spinal Neoplasms. Die Arbeit nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES To develop a Generative Adversarial Network (GAN) for generating virtual T2 fat-suppressed (T2FS) sequences from standard T1- and T2-weighted images, with the clinical objective of reducing MRI scan time without compromising diagnostic value for spinal tumor assessment. MATERIALS AND METHODS This retrospective study included 1,389 consecutive patients with spinal tumors from two institutions, divided into training (n = 1,026; 49.2 ± 16.4 years; 540 males), internal validation (n = 257; 48.2 ± 17.2 years; 140 males), and external test (n = 106; 52.8 ± 17.0 years; 59 males) sets. The model used T1- and T2-weighted images as input to generate T2FS images. Quantitative image fidelity evaluations included mean squared error (MSE), structural similarity index measure (SSIM), and peak signal-to-noise ratio (PSNR). The Dice similarity coefficient (DSC) assessed lesion segmentation. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) measured objective quality. Two experienced radiologists independently rated the images on a 5-point scale, evaluating overall quality, tumor detail preservation, fat suppression performance, and artifacts. RESULTS The external test set exhibited an MSE of 0.0060 ± 0.0038, SSIM of 0.667 ± 0.120, and PSNR of 23.368 ± 4.298 dB. The real and synthetic images agreed strongly in lesion segmentation, with mean DSC of 0.820 ± 0.176 (internal) and 0.807 ± 0.188 (external). SNR and CNR were comparable between real and synthetic images in both datasets. Qualitative assessments indicated equivalent overall image quality and artifacts. Synthetic images showed superior fat suppression, while real images offered better tumor internal detail. CONCLUSIONS The proposed GAN-based method generated diagnostically valuable virtual T2FS images. KEY POINTS 1. The proposed deep learning model successfully generated virtual T2FS images from standard T1/T2 MRI, demonstrating favorable quantitative agreement (MSE 0.0060, SSIM 0.667). 2. Synthetic and real images demonstrated strong consistency in lesion segmentation (DSC 0.809-0.824) and comparable SNR/CNR values. 3. While synthetic images provided superior fat suppression, real images maintained slightly better tumor internal detail visualization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingDeep LearningImage Interpretation, Computer-AssistedSpinal NeoplasmsHumansMaleMiddle AgedFemaleGenerative Adversarial NetworksRetrospective StudiesReproducibility of ResultsImage EnhancementSensitivity and SpecificityGenerative Artificial IntelligenceAdipose TissueAdult

Stichwörter der Autor:innen

Artificial intelligenceDeep learningFat suppressionMagnetic resonance imagingSpine

Autor:innen und Institutionen

  • Department of Radiology, State Key Laboratory of Vascular Homeostasis and Remodeling, Peking University Third Hospital, Beijing 100191, China. Electronic address: wangchenxi@pku.edu.cn.
  • Department of Radiology, State Key Laboratory of Vascular Homeostasis and Remodeling, Peking University Third Hospital, Beijing 100191, China. Electronic address: xj18863609153@163.com.
  • Department of Radiology, the Affiliated Hospital of Qingdao University, Qingdao, Shandong, China. Electronic address: zmqd1106@163.com.
  • Department of Radiology, the Affiliated Hospital of Qingdao University, Qingdao, Shandong, China. Electronic address: haodp2021@qdu.edu.cn.
  • Department of Biomedical Informatics, State Key Laboratory of Vascular Homeostasis and Remodeling, School of Basic Medical Sciences, Peking University, 38 Xueyuan Road, Beijing 100191, China. Electronic address: zhangse…
  • Department of Radiology, State Key Laboratory of Vascular Homeostasis and Remodeling, Peking University Third Hospital, Beijing 100191, China. Electronic address: langning800129@126.com.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, C., Xu, J., Zhang, M., Hao, D., Zhang, S., & Lang, N. (2026). Deep learning synthesis of virtual T2-weighted fat-suppressed MR images: a multi-center study. European Journal of Radiology, 199, 112797. https://doi.org/10.1016/j.ejrad.2026.112797

Vancouver

Wang C, Xu J, Zhang M, Hao D, Zhang S, Lang N. Deep learning synthesis of virtual T2-weighted fat-suppressed MR images: a multi-center study. European Journal of Radiology. 2026;199:112797. doi:10.1016/j.ejrad.2026.112797

BibTeX
@article{Wang2026,
  author = {Wang, Chenxi and Xu, Jun and Zhang, Meng and Hao, Dapeng and Zhang, Senpeng and Lang, Ning},
  title = {Deep learning synthesis of virtual T2-weighted fat-suppressed MR images: a multi-center study},
  journal = {European Journal of Radiology},
  year = {2026},
  volume = {199},
  pages = {112797},
  doi = {10.1016/j.ejrad.2026.112797}
}
Kostenlos starten →