Impact of Deep Learning Reconstruction on Intracranial 1.5 T Magnetic Resonance Angiography

Overview

Journal Jpn J Radiol

Publisher Springer

Specialty Radiology

Date 2021 Dec 1

PMID 34851499

Citations 17

Authors

Koichiro Yasaka

Hiroyuki Akai

Haruto Sugawara

Taku Tajima

Masaaki Akahane

Naoki Yoshioka

Hiroyuki Kabasawa

Rintaro Miyo

Kuni Ohtomo

Osamu Abe

Shigeru Kiryu

Affiliations

Soon will be listed here.

Abstract

Purpose: The purpose of this study was to evaluate whether deep learning reconstruction (DLR) improves the image quality of intracranial magnetic resonance angiography (MRA) at 1.5 T.

Materials And Methods: In this retrospective study, MRA images of 40 patients (21 males and 19 females; mean age, 65.8 ± 13.2 years) were reconstructed with and without the DLR technique (DLR image and non-DLR image, respectively). Quantitative image analysis was performed by placing regions of interest on the basilar artery and cerebrospinal fluid in the prepontine cistern. We calculated the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) for analyses of the basilar artery. Two experienced radiologists evaluated the depiction of structures (the right internal carotid artery, right ophthalmic artery, basilar artery, and right superior cerebellar artery), artifacts, subjective noise and overall image quality in a qualitative image analysis. Scores were compared in the quantitative and qualitative image analyses between the DLR and non-DLR images using Wilcoxon signed-rank tests.

Results: The SNR and CNR for the basilar artery were significantly higher for the DLR images than for the non-DLR images (p < 0.001). Qualitative image analysis scores (p < 0.003 and p < 0.005 for readers 1 and 2, respectively), excluding those for artifacts (p = 0.072-0.565), were also significantly higher for the DLR images than for the non-DLR images.

Conclusion: DLR enables the production of higher quality 1.5 T intracranial MRA images with improved visualization of arteries.

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.

Applications of artificial intelligence in interventional oncology: An up-to-date review of the literature.

Matsui Y, Ueda D, Fujita S, Fushimi Y, Tsuboyama T, Kamagata K Jpn J Radiol. 2024; 43(2):164-176.

PMID: 39356439 PMC: 11790735. DOI: 10.1007/s11604-024-01668-3.

Recent trends in AI applications for pelvic MRI: a comprehensive review.

Tsuboyama T, Yanagawa M, Fujioka T, Fujita S, Ueda D, Ito R Radiol Med. 2024; 129(9):1275-1287.

PMID: 39096356 DOI: 10.1007/s11547-024-01861-4.

Iterative Motion Correction Technique with Deep Learning Reconstruction for Brain MRI: A Volunteer and Patient Study.

Yasaka K, Akai H, Kato S, Tajima T, Yoshioka N, Furuta T J Imaging Inform Med. 2024; 37(6):3070-3076.

PMID: 38942939 PMC: 11612051. DOI: 10.1007/s10278-024-01184-w.

Deep Learning-Based High-Resolution Magnetic Resonance Angiography (MRA) Generation Model for 4D Time-Resolved Angiography with Interleaved Stochastic Trajectories (TWIST) MRA in Fast Stroke Imaging.

Kim B, You S, Kim B, Shin J Diagnostics (Basel). 2024; 14(11).

PMID: 38893725 PMC: 11171826. DOI: 10.3390/diagnostics14111199.

References

Wardlaw J, Brindle W, Casado A, Shuler K, Henderson M, Thomas B . A systematic review of the utility of 1.5 versus 3 Tesla magnetic resonance brain imaging in clinical practice and research. Eur Radiol. 2012; 22(11):2295-303. DOI: 10.1007/s00330-012-2500-8. 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

Heidenreich J, Schilling A, Unterharnscheidt F, Stendel R, Hartlieb S, Wacker F . Assessment of 3D-TOF-MRA at 3.0 Tesla in the characterization of the angioarchitecture of cerebral arteriovenous malformations: a preliminary study. Acta Radiol. 2007; 48(6):678-86. DOI: 10.1080/02841850701326958. View

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

Uetani H, Nakaura T, Kitajima M, Yamashita Y, Hamasaki T, Tateishi M . A preliminary study of deep learning-based reconstruction specialized for denoising in high-frequency domain: usefulness in high-resolution three-dimensional magnetic resonance cisternography of the cerebellopontine angle. Neuroradiology. 2020; 63(1):63-71. DOI: 10.1007/s00234-020-02513-w. View

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

Kashiwagi N, Tanaka H, Yamashita Y, Takahashi H, Kassai Y, Fujiwara M . Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI. Acta Radiol Open. 2021; 10(6):20584601211023939. PMC: 8216362. DOI: 10.1177/20584601211023939. View

Fushimi Y, Miki Y, Kikuta K, Okada T, Kanagaki M, Yamamoto A . Comparison of 3.0- and 1.5-T three-dimensional time-of-flight MR angiography in moyamoya disease: preliminary experience. Radiology. 2006; 239(1):232-7. DOI: 10.1148/radiol.2383042020. View

Yasaka K, Abe O . Deep learning and artificial intelligence in radiology: Current applications and future directions. PLoS Med. 2018; 15(11):e1002707. PMC: 6267951. DOI: 10.1371/journal.pmed.1002707. View

10.

Higaki T, Nakamura Y, Tatsugami F, Nakaura T, Awai K . Improvement of image quality at CT and MRI using deep learning. Jpn J Radiol. 2018; 37(1):73-80. DOI: 10.1007/s11604-018-0796-2. View

11.

Rincon F, Rossenwasser R, Dumont A . The epidemiology of admissions of nontraumatic subarachnoid hemorrhage in the United States. Neurosurgery. 2013; 73(2):217-22. DOI: 10.1227/01.neu.0000430290.93304.33. View

12.

Lawton M, Vates G . Subarachnoid Hemorrhage. N Engl J Med. 2017; 377(3):257-266. DOI: 10.1056/NEJMcp1605827. View

13.

Ueda D, Yamamoto A, Nishimori M, Shimono T, Doishita S, Shimazaki A . Deep Learning for MR Angiography: Automated Detection of Cerebral Aneurysms. Radiology. 2018; 290(1):187-194. DOI: 10.1148/radiol.2018180901. View

14.

Yasaka K, Akai H, Abe O, Kiryu S . Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study. Radiology. 2017; 286(3):887-896. DOI: 10.1148/radiol.2017170706. View

15.

Campbell B, Khatri P . Stroke. Lancet. 2020; 396(10244):129-142. DOI: 10.1016/S0140-6736(20)31179-X. View

16.

Willinek W, Born M, Simon B, Tschampa H, Krautmacher C, Gieseke J . Time-of-flight MR angiography: comparison of 3.0-T imaging and 1.5-T imaging--initial experience. Radiology. 2003; 229(3):913-20. DOI: 10.1148/radiol.2293020782. View

17.

Anzalone N, Scomazzoni F, Cirillo M, Cadioli M, Iadanza A, Kirchin M . Follow-up of coiled cerebral aneurysms: comparison of three-dimensional time-of-flight magnetic resonance angiography at 3 tesla with three-dimensional time-of-flight magnetic resonance angiography and contrast-enhanced magnetic resonance.... Invest Radiol. 2008; 43(8):559-67. DOI: 10.1097/RLI.0b013e31817e9b0b. View

18.

Kanda Y . Investigation of the freely available easy-to-use software 'EZR' for medical statistics. Bone Marrow Transplant. 2012; 48(3):452-8. PMC: 3590441. DOI: 10.1038/bmt.2012.244. View

19.

Yasaka K, Akai H, Kunimatsu A, Abe O, Kiryu S . Liver Fibrosis: Deep Convolutional Neural Network for Staging by Using Gadoxetic Acid-enhanced Hepatobiliary Phase MR Images. Radiology. 2017; 287(1):146-155. DOI: 10.1148/radiol.2017171928. View

20.

HaiFeng L, Yongsheng X, YangQin X, Yu D, ShuaiWen W, XingRu L . Diagnostic value of 3D time-of-flight magnetic resonance angiography for detecting intracranial aneurysm: a meta-analysis. Neuroradiology. 2017; 59(11):1083-1092. DOI: 10.1007/s00234-017-1905-0. View