View on Pubmed.gov 42525326 | View on doi.org 10.1007/s13246-...
Evaluation of generative adversarial network-based postprocessing super-resolution for lumbar spine magnetic resonance imaging.
- Graduate School of Medical Sciences, Fujita Health University, 1-98, Dengakugakubo, Kutsukake-cho, Toyoake, Aichi, 470-1192, Japan. yasuo.takatsu@fujita-hu.ac.jp.
- Department of Molecular Imaging, Clinical Collaboration Unit, School of Medical Sciences, Fujita Health University, 1-98, Dengakugakubo, Kutsukake-cho, Toyoake, Aichi, 470-1192, Japan. yasuo.takatsu@fujita-hu.ac.jp.
- Division of Health Sciences, Graduate School of Medical Sciences, Kanazawa University, 5-11-80 Kodatsuno, Kanazawa, Ishikawa, 920-0942, Japan. yasuo.takatsu@fujita-hu.ac.jp.
- Department of Molecular Imaging, Clinical Collaboration Unit, School of Medical Sciences, Fujita Health University, 1-98, Dengakugakubo, Kutsukake-cho, Toyoake, Aichi, 470-1192, Japan.
- Graduate School of Medical Sciences, Fujita Health University, 1-98, Dengakugakubo, Kutsukake-cho, Toyoake, Aichi, 470-1192, Japan.
- Department of Radiology, Fujita Health University Hospital, 1-98, Dengakugakubo, Kutsukake-cho, Toyoake, Aichi, 470-1192, Japan.
- Department of Radiological Technology, Faculty of Health and Welfare, Tokushima Bunri University, 8-53 Hamanocho, Takamatsu city, Kagawa, 760-8542, Japan.
- Medical Imaging Center of Manryoukai, 1-8-3, Sanno, Nishinari-ku, Osaka, 557-0001, Japan.
- Division of Health Sciences, Graduate School of Medical Sciences, Kanazawa University, 5-11-80 Kodatsuno, Kanazawa, Ishikawa, 920-0942, Japan.
- Department of Applied Medical Imaging, Gunma University Graduate School of Medicine, 3‑39‑22 Showa‑machi, Maebashi, Gunma, 371‑8511, Japan.
Abstract
This study evaluated the feasibility of generative adversarial network (GAN)-based postprocessing super-resolution for T2-weighted lumbar spine magnetic resonance imaging (MRI) using both objective resolution metrics and perceptual assessment. Sagittal lumbar spine MRI datasets from healthy volunteers were analyzed. An enhanced super-resolution GAN (ESRGAN) was trained on downsampled images, while zero-filling, bicubic, and bilinear interpolation, as well as enhanced deep residual networks for single image super-resolution (EDSR), were used as comparators. Image quality was assessed by comparing upscaled images from 256 × 256 acquisitions with corresponding 512 × 512 reference images, using full width at half maximum (FWHM) and normalized integrated power spectrum (NIPS), along with similarity metrics including structural similarity index, peak signal-to-noise ratio, and root mean square error. Subjective image quality was evaluated using a ranking method. An additional analysis using 320 × 320 and 640 × 640 image pairs was conducted to assess consistency across resolution settings. Statistical comparisons were performed using the Friedman test with Bonferroni correction. ESRGAN showed no significant differences from the original high-resolution images in FWHM and NIPS, whereas interpolation methods and EDSR demonstrated inferior performance (P < 0.05). Although interpolation methods achieved higher scores in pixel-wise metrics, ESRGAN obtained the highest subjective ratings and interrater agreement. These findings indicate that ESRGAN better restores high-frequency structural information not captured by conventional similarity metrics. GAN-based postprocessing super-resolution may improve image quality in lumbar spine MRI and warrants further investigation of its clinical impact.
References
de Leeuw den Bouter ML, Ippolito G, O’Reilly TPA, Remis RF, Gijzen MB, Webb AG (2022) Deep learning-based single image super-resolution for low-field MR brain images. Sci Rep 12:6362. doi.org
Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38:295–307. doi.org
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1646–1654
Zhang Y, Li K, Li K, Wang L, Zhong B, Fu Y (2018) Image super-resolution using very deep residual channel attention networks. In: Proceedings of the European conference on computer vision (ECCV), pp 286–301
Conflict of interest statement
Declarations. Competing interests: Soma Kumasaka is affiliated with the Department of Applied Medical Imaging, an endowed department supported by Siemens Healthineers and KURIBARA Roentgen. The sponsors had no role in the design, conduct, analysis, interpretation, or preparation of this study. The other authors declare no competing interests. Ethics approval: This study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the Ethics Committee of the Medical Imaging Center of Manryokai (Approval No. B-28) as well as by the Ethics Committee of Fujita Health University (Approval No. EN25-103). Consent to participate: Informed consent was obtained from all healthy volunteers. For previously acquired patient images used in this retrospective analysis, informed consent was waived, and an opt-out approach was implemented in accordance with institutional guidelines. Consent to publish: The authors affirm that human research participants provided informed consent for publication of the images in Figs. 1, 2 and 3.
MeSH
- •
- •
Specialties
- •
- •
Copyright
© 2026. Australasian College of Physical Scientists and Engineers in Medicine.