Commercially Available Deep-learning-reconstruction of MR Imaging of the Knee at 1.5T Has Higher Image Quality Than Conventionally-reconstructed Imaging at 3T: A Normal Volunteer Study

Overview

Journal Magn Reson Med Sci

Specialty Radiology

Date 2022 Jul 10

PMID 35811127

Authors

Hiroyuki Akai

Koichiro Yasaka

Haruto Sugawara

Taku Tajima

Masaaki Akahane

Naoki Yoshioka

Kuni Ohtomo

Osamu Abe

Shigeru Kiryu

Affiliations

Soon will be listed here.

Abstract

Purpose: This study aimed to evaluate whether the image quality of 1.5T magnetic resonance imaging (MRI) of the knee is equal to or higher than that of 3T MRI by applying deep learning reconstruction (DLR).

Methods: Proton density-weighted images of the right knee of 27 healthy volunteers were obtained by 3T and 1.5T MRI scanners using similar imaging parameters (21 for high resolution image and 6 for normal resolution image). Commercially available DLR was applied to the 1.5T images to obtain 1.5T/DLR images. The 3T and 1.5T/DLR images were compared subjectively for visibility of structures, image noise, artifacts, and overall diagnostic acceptability and objectively. One-way ANOVA and Friedman tests were used for the statistical analyses.

Results: For the high resolution images, all of the anatomical structures, except for bone, were depicted significantly better on the 1.5T/DLR compared with 3T images. Image noise scored statistically lower and overall diagnostic acceptability scored higher on the 1.5T/DLR images. The contrast between lateral meniscus and articular cartilage of the 1.5T/DLR images was significantly higher (5.89 ± 1.30 vs. 4.34 ± 0.87, P < 0.001), and also the contrast between medial meniscus and articular cartilage of the 1.5T/DLR images was significantly higher (5.12 ± 0.93 vs. 3.87 ± 0.56, P < 0.001). Similar image quality improvement by DLR was observed for the normal resolution images.

Conclusion: The 1.5T/DLR images can achieve less noise, more precise visualization of the meniscus and ligaments, and higher overall image quality compared with the 3T images acquired using a similar protocol.

Citing Articles

Advancing clinical MRI exams with artificial intelligence: Japan's contributions and future prospects.

Fujita S, Fushimi Y, Ito R, Matsui Y, Tatsugami F, Fujioka T Jpn J Radiol. 2024; 43(3):355-364.

PMID: 39548049 PMC: 11868336. DOI: 10.1007/s11604-024-01689-y.

Efficacy of compressed sensing and deep learning reconstruction for adult female pelvic MRI at 1.5 T.

Ueda T, Yamamoto K, Yazawa N, Tozawa I, Ikedo M, Yui M Eur Radiol Exp. 2024; 8(1):103.

PMID: 39254920 PMC: 11387279. DOI: 10.1186/s41747-024-00506-5.

Verification of image quality improvement by deep learning reconstruction to 1.5 T MRI in T2-weighted images of the prostate gland.

Sato Y, Ohkuma K Radiol Phys Technol. 2024; 17(3):756-764.

PMID: 38850389 DOI: 10.1007/s12194-024-00819-5.

Applications of Artificial Intelligence for Pediatric Cancer Imaging.

Singh S, Sarrami A, Gatidis S, Varniab Z, Chaudhari A, Daldrup-Link H AJR Am J Roentgenol. 2024; 223(2):e2431076.

PMID: 38809123 PMC: 11874589. DOI: 10.2214/AJR.24.31076.

Super-resolution Deep Learning Reconstruction Cervical Spine 1.5T MRI: Improved Interobserver Agreement in Evaluations of Neuroforaminal Stenosis Compared to Conventional Deep Learning Reconstruction.

Yasaka K, Uehara S, Kato S, Watanabe Y, Tajima T, Akai H J Imaging Inform Med. 2024; 37(5):2466-2473.

PMID: 38671337 PMC: 11522216. DOI: 10.1007/s10278-024-01112-y.

References

Lustig M, Donoho D, Pauly J . Sparse MRI: The application of compressed sensing for rapid MR imaging. Magn Reson Med. 2007; 58(6):1182-95. DOI: 10.1002/mrm.21391. View

Johnson P, Recht M, Knoll F . Improving the Speed of MRI with Artificial Intelligence. Semin Musculoskelet Radiol. 2020; 24(1):12-20. PMC: 7416509. DOI: 10.1055/s-0039-3400265. View

Cao L, Shi R, Ge Y, Xing L, Zuo P, Jia Y . Fully automatic segmentation of type B aortic dissection from CTA images enabled by deep learning. Eur J Radiol. 2019; 121:108713. DOI: 10.1016/j.ejrad.2019.108713. View

Cheng Q, Zhao F . Comparison of 1.5- and 3.0-T magnetic resonance imaging for evaluating lesions of the knee: A systematic review and meta-analysis (PRISMA-compliant article). Medicine (Baltimore). 2018; 97(38):e12401. PMC: 6160024. DOI: 10.1097/MD.0000000000012401. View

Minh Quan T, Nguyen-Duc T, Jeong W . Compressed Sensing MRI Reconstruction Using a Generative Adversarial Network With a Cyclic Loss. IEEE Trans Med Imaging. 2018; 37(6):1488-1497. DOI: 10.1109/TMI.2018.2820120. View

Yokota Y, Takeda C, Kidoh M, Oda S, Aoki R, Ito K . Effects of Deep Learning Reconstruction Technique in High-Resolution Non-contrast Magnetic Resonance Coronary Angiography at a 3-Tesla Machine. Can Assoc Radiol J. 2020; 72(1):120-127. DOI: 10.1177/0846537119900469. View

Hammernik K, Klatzer T, Kobler E, Recht M, Sodickson D, Pock T . Learning a variational network for reconstruction of accelerated MRI data. Magn Reson Med. 2017; 79(6):3055-3071. PMC: 5902683. DOI: 10.1002/mrm.26977. View

Feinstein A, Cicchetti D . High agreement but low kappa: I. The problems of two paradoxes. J Clin Epidemiol. 1990; 43(6):543-9. DOI: 10.1016/0895-4356(90)90158-l. View

Kidoh M, Shinoda K, Kitajima M, Isogawa K, Nambu M, Uetani H . Deep Learning Based Noise Reduction for Brain MR Imaging: Tests on Phantoms and Healthy Volunteers. Magn Reson Med Sci. 2019; 19(3):195-206. PMC: 7553817. DOI: 10.2463/mrms.mp.2019-0018. View

10.

Grossman J, De Smet A, Shinki K . Comparison of the accuracy rates of 3-T and 1.5-T MRI of the knee in the diagnosis of meniscal tear. AJR Am J Roentgenol. 2009; 193(2):509-14. DOI: 10.2214/AJR.08.2101. View

11.

Kiryu S, Yasaka K, Akai H, Nakata Y, Sugomori Y, Hara S . Deep learning to differentiate parkinsonian disorders separately using single midsagittal MR imaging: a proof of concept study. Eur Radiol. 2019; 29(12):6891-6899. DOI: 10.1007/s00330-019-06327-0. View

12.

Deshmane A, Gulani V, Griswold M, Seiberlich N . Parallel MR imaging. J Magn Reson Imaging. 2012; 36(1):55-72. PMC: 4459721. DOI: 10.1002/jmri.23639. View

13.

Chaudhari A, Fang Z, Kogan F, Wood J, Stevens K, Gibbons E . Super-resolution musculoskeletal MRI using deep learning. Magn Reson Med. 2018; 80(5):2139-2154. PMC: 6107420. DOI: 10.1002/mrm.27178. View

14.

Ueda T, Ohno Y, Yamamoto K, Iwase A, Fukuba T, Hanamatsu S . Compressed sensing and deep learning reconstruction for women's pelvic MRI denoising: Utility for improving image quality and examination time in routine clinical practice. Eur J Radiol. 2020; 134:109430. DOI: 10.1016/j.ejrad.2020.109430. View

15.

Van Dyck P, Kenis C, Vanhoenacker F, Lambrecht V, Wouters K, Gielen J . Comparison of 1.5- and 3-T MR imaging for evaluating the articular cartilage of the knee. Knee Surg Sports Traumatol Arthrosc. 2013; 22(6):1376-84. DOI: 10.1007/s00167-013-2704-8. View

16.

Yasaka K, Akai H, Kunimatsu A, Kiryu S, Abe O . Deep learning with convolutional neural network in radiology. Jpn J Radiol. 2018; 36(4):257-272. DOI: 10.1007/s11604-018-0726-3. View

17.

Nacey N, Geeslin M, Miller G, Pierce J . Magnetic resonance imaging of the knee: An overview and update of conventional and state of the art imaging. J Magn Reson Imaging. 2017; 45(5):1257-1275. DOI: 10.1002/jmri.25620. View

18.

Akkus Z, Galimzianova A, Hoogi A, Rubin D, Erickson B . Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions. J Digit Imaging. 2017; 30(4):449-459. PMC: 5537095. DOI: 10.1007/s10278-017-9983-4. View

19.

Yasaka K, Akai H, Kunimatsu A, Abe O, Kiryu S . Deep learning for staging liver fibrosis on CT: a pilot study. Eur Radiol. 2018; 28(11):4578-4585. DOI: 10.1007/s00330-018-5499-7. View

20.

Kwok W, Zhong J, You Z, Seo G, Totterman S . A four-element phased array coil for high resolution and parallel MR imaging of the knee. Magn Reson Imaging. 2003; 21(9):961-7. DOI: 10.1016/s0730-725x(03)00202-9. View