ShanghaiTech University Knowledge Management System
| Learn an Index Operator by CNN for Solving Diffusive Optical Tomography: A Deep Direct Sampling Method | |
| 2023-04-01 | |
| Source Publication | JOURNAL OF SCIENTIFIC COMPUTING
 |
| ISSN | 0885-7474 |
| EISSN | 1573-7691 |
| Volume | 95Issue:1 |
| Status | 已发表 |
| DOI | 10.1007/s10915-023-02115-7 |
| Abstract | In this work, we investigate the diffusive optical tomography (DOT) problem in the case that limited boundary measurements are available. Motivated by the direct sampling method (DSM) proposed in Chow et al. (SIAM J Sci Comput 37(4):A1658-A1684, 2015), we develop a deep direct sampling method (DDSM) to recover the inhomogeneous inclusions buried in a homogeneous background. In this method, we design a convolutional neural network to approximate the index functional that mimics the underling mathematical structure. The benefits of the proposed DDSM include fast and easy implementation, capability of incorporating multiple measurements to attain high-quality reconstruction, and advanced robustness against the noise. Numerical experiments show that the reconstruction accuracy is improved without degrading the efficiency, demonstrating its potential for solving the real-world DOT problems. |
| Keyword | Deep learning Inverse problems Direct sampling methods Diffusive optical tomography Reconstruction algorithm |
| URL | 查看原文 |
| Indexed By | SCI ; EI |
| Language | 英语 |
| Funding Project | ShanghaiTech University[2020F0203-000-16] ; Shanghai Science and Technology Innovation Program[21YF1429100] ; National Natural Science Foundation of China[12101406] ; NSF[DMS-2012465] |
| WOS Research Area | Mathematics |
| WOS Subject | Mathematics, Applied |
| WOS ID | WOS:000946265400006 |
| Publisher | SPRINGER/PLENUM PUBLISHERS |
| EI Accession Number | 20231213747425 |
| EI Keywords | Inverse problems |
| EI Classification Number | 461.4 Ergonomics and Human Factors Engineering ; 741.3 Optical Devices and Systems |
| Original Document Type | Journal article (JA) |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/287882 |
| Collection | 数学科学研究所 信息科学与技术学院 数学科学研究所_PI研究组(P)_姜嘉骅组 |
| Corresponding Author | Jiang, Jiahua |
| Affiliation | 1.Univ Calif Irvine, Dept Math, Irvine, CA USA 2.Univ Birmingham, Sch Math, Birmingham, England 3.ShanghaiTech Univ, Inst Math Sci, Pudong, Peoples R China 4.ShanghaiTech Univ, Sch Informat Sci & Technol, Pudong, Peoples R China |
| Corresponding Author Affilication | Institute of Mathematical Sciences |
| Recommended Citation GB/T 7714 | Guo, Ruchi,Jiang, Jiahua,Li, Yi. Learn an Index Operator by CNN for Solving Diffusive Optical Tomography: A Deep Direct Sampling Method[J]. JOURNAL OF SCIENTIFIC COMPUTING,2023,95(1). |
| APA | Guo, Ruchi,Jiang, Jiahua,&Li, Yi.(2023).Learn an Index Operator by CNN for Solving Diffusive Optical Tomography: A Deep Direct Sampling Method.JOURNAL OF SCIENTIFIC COMPUTING,95(1). |
| MLA | Guo, Ruchi,et al."Learn an Index Operator by CNN for Solving Diffusive Optical Tomography: A Deep Direct Sampling Method".JOURNAL OF SCIENTIFIC COMPUTING 95.1(2023). |
| Files in This Item: | Download All | |||||
| File Name/Size | DocType | Version | Access | License | ||
Edit Comment
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.