Magnetic resonance-driven deep learning of electromagnetic metamaterials

Qun Ren; Yongjing Dang; Zhaoyang Zhang; Ruiqi Jin; Xiaohan Liu; Yanwei Pang

doi:10.1117/12.3037588

20 November 2024 Magnetic resonance-driven deep learning of electromagnetic metamaterials

Qun Ren, Yongjing Dang, Zhaoyang Zhang, Ruiqi Jin, Xiaohan Liu, Yanwei Pang

Proceedings Volume 13242, Optics in Health Care and Biomedical Optics XIV; 1324216 (2024) https://doi.org/10.1117/12.3037588
Event: SPIE/COS Photonics Asia, 2024, Nantong, Jiangsu, China

Abstract

Metamaterials, due to their extraordinary physical properties not found in natural materials, can control their electromagnetic properties by adjusting their geometry and structural parameters. Traditional MRl systems are often affected by magnetic field distortion and signal attenuation caused by metal structures. The introduction of metamaterials provides a new way to overcome these problems. However, designing metamaterials in the traditional way can present highly complex optimization challenges. In order to solve this problem, we introduce deep learning technology to study the relationship between the properties of metamaterials and the electromagnetic response under electromagnetic drive by training neural networks, and the experimental results show that compared with traditional hand-designed metamaterials. Metamaterials optimized by deep learning show superior performance in MRl systems. The combination of deep learning and electromagnetic metamaterial design opens up new directions for the development of MRI technology and has the potential to advance the entire field of healthcare.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Qun Ren, Yongjing Dang, Zhaoyang Zhang, Ruiqi Jin, Xiaohan Liu, and Yanwei Pang "Magnetic resonance-driven deep learning of electromagnetic metamaterials", Proc. SPIE 13242, Optics in Health Care and Biomedical Optics XIV, 1324216 (20 November 2024); https://doi.org/10.1117/12.3037588

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available