A review of machine learning applications for the proton MR spectroscopy workflow

Author:

van de Sande Dennis M. J.1ORCID,Merkofer Julian P.2ORCID,Amirrajab Sina1ORCID,Veta Mitko1ORCID,van Sloun Ruud J. G.23ORCID,Versluis Maarten J.4ORCID,Jansen Jacobus F. A.256ORCID,van den Brink Johan S.4ORCID,Breeuwer Marcel124ORCID

Affiliation:

1. Department of Biomedical Engineering Eindhoven University of Technology Eindhoven The Netherlands

2. Department of Electrical Engineering Eindhoven University of Technology Eindhoven The Netherlands

3. Philips Research Philips Research Eindhoven The Netherlands

4. MR R&D ‐ Clinical Science Philips Healthcare Best The Netherlands

5. Department of Radiology and Nuclear Medicine Maastricht University Medical Center Maastricht The Netherlands

6. School for Mental Health and Neuroscience Maastricht University Maastricht The Netherlands

Abstract

AbstractThis literature review presents a comprehensive overview of machine learning (ML) applications in proton MR spectroscopy (MRS). As the use of ML techniques in MRS continues to grow, this review aims to provide the MRS community with a structured overview of the state‐of‐the‐art methods. Specifically, we examine and summarize studies published between 2017 and 2023 from major journals in the MR field. We categorize these studies based on a typical MRS workflow, including data acquisition, processing, analysis, and artificial data generation. Our review reveals that ML in MRS is still in its early stages, with a primary focus on processing and analysis techniques, and less attention given to data acquisition. We also found that many studies use similar model architectures, with little comparison to alternative architectures. Additionally, the generation of artificial data is a crucial topic, with no consistent method for its generation. Furthermore, many studies demonstrate that artificial data suffers from generalization issues when tested on in vivo data. We also conclude that risks related to ML models should be addressed, particularly for clinical applications. Therefore, output uncertainty measures and model biases are critical to investigate. Nonetheless, the rapid development of ML in MRS and the promising results from the reviewed studies justify further research in this field.

Publisher

Wiley

Subject

Radiology, Nuclear Medicine and imaging

Cited by 8 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

1. Simultaneous multi‐transient linear‐combination modeling of MRS data improves uncertainty estimation;Magnetic Resonance in Medicine;2024-04-22

2. Results of the 2023 ISBI challenge to reduce GABA-edited MRS acquisition time;Magnetic Resonance Materials in Physics, Biology and Medicine;2024-04-13

3. Materials science in the era of large language models: a perspective;Digital Discovery;2024

4. Quo Vadis Hyperpolarized 13C MRI?;Zeitschrift für Medizinische Physik;2023-12

5. Magnetic Resonance Spectroscopy Fitting through Spectrogram and Vision Transformers;2023 19th International Symposium on Medical Information Processing and Analysis (SIPAIM);2023-11-15

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