Generalizable synthetic MRI with physics‐informed convolutional networks

Author:

Jacobs Luuk12,Mandija Stefano12,Liu Hongyan12,van den Berg Cornelis A. T.12,Sbrizzi Alessandro12,Maspero Matteo12

Affiliation:

1. Department of Radiotherapy UMC Utrecht Utrecht The Netherlands

2. Computational Imaging Group for MR Diagnostics and Therapy UMC Utrecht Utrecht The Netherlands

Abstract

AbstractBackgroundMagnetic resonance imaging (MRI) provides state‐of‐the‐art image quality for neuroimaging, consisting of multiple separately acquired contrasts. Synthetic MRI aims to accelerate examinations by synthesizing any desirable contrast from a single acquisition.PurposeWe developed a physics‐informed deep learning‐based method to synthesize multiple brain MRI contrasts from a single 5‐min acquisition and investigate its ability to generalize to arbitrary contrasts.MethodsA dataset of 55 subjects acquired with a clinical MRI protocol and a 5‐min transient‐state sequence was used. The model, based on a generative adversarial network, maps data acquired from the five‐minute scan to “effective” quantitative parameter maps (q*‐maps), feeding the generated PD, T1, and T2 maps into a signal model to synthesize four clinical contrasts (proton density‐weighted, T1‐weighted, T2‐weighted, and T2‐weighted fluid‐attenuated inversion recovery), from which losses are computed. The synthetic contrasts are compared to an end‐to‐end deep learning‐based method proposed by literature. The generalizability of the proposed method is investigated for five volunteers by synthesizing three contrasts unseen during training and comparing these to ground truth acquisitions via qualitative assessment and contrast‐to‐noise ratio (CNR) assessment.ResultsThe physics‐informed method matched the quality of the end‐to‐end method for the four standard contrasts, with structural similarity metrics above 0.75 ± 0.08 (±std), peak signal‐to‐noise ratios above 22.4 ± 1.9, representing a portion of compact lesions comparable to standard MRI. Additionally, the physics‐informed method enabled contrast adjustment, and similar signal contrast and comparable CNRs to the ground truth acquisitions for three sequences unseen during model training.ConclusionsThe study demonstrated the feasibility of physics‐informed, deep learning‐based synthetic MRI to generate high‐quality contrasts and generalize to contrasts beyond the training data. This technology has the potential to accelerate neuroimaging protocols.

Publisher

Wiley

Subject

General Medicine

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3