Impact of deep learning reconstruction on intracranial 1.5 T magnetic resonance angiography

Koichiro Yasaka,Hiroyuki Akai,Naoki Yoshioka,Hiroyuki Kabasawa,Haruto Sugawara,Shigeru Kiryu,Masaaki Akahane,Taku Tajima,Osamu Abe,Rintaro Miyo,Kuni Ohtomo

doi:10.1007/s11604-021-01225-2

Abstract

PurposeThe 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 methodsIn 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.ResultsThe 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.ConclusionDLR enables the production of higher quality 1.5 T intracranial MRA images with improved visualization of arteries.

Highlights

Defects in intracranial vessels cause several neurological diseases
This technique successfully reduced image noise and provided clearer depictions of large and small intracranial arteries in Magnetic resonance angiography (MRA) images obtained with a 1.5 T magnetic resonance imaging (MRI) unit
MRA images obtained with 1.5 T units are associated with lower signal-to-noise ratio (SNR)

Summary

Introduction

Defects in intracranial vessels cause several neurological diseases. Strokes are common and affect one in four people [1, 2]. They are the second-leading cause of death and the third-leading cause of disability in adults worldwide [1]. According to the Stop Stroke Study-Trial of ORG 10,172 in Acute Stroke Treatment (SSS-TOAST), cases of acute ischemic stroke can be classified into the following predetermined etiologic categories: large artery atherosclerosis, small-artery occlusion, cardioaortic embolism, undetermined causes and other causes. Subarachnoid hemorrhage accounts for 5–10% of all strokes in the United States [4]. Many subarachnoid hemorrhages without any preceding trauma are caused by the rupture of an intracranial aneurysm [5].

Objectives

Methods

Results

Conclusion