File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1038/s41467-023-38021-7
- Scopus: eid_2-s2.0-85153424860
- PMID: 37081008
- WOS: WOS:001025247300001
Supplementary
- Citations:
- Appears in Collections:
Article: Energy-efficient high-fidelity image reconstruction with memristor arrays for medical diagnosis
Title | Energy-efficient high-fidelity image reconstruction with memristor arrays for medical diagnosis |
---|---|
Authors | |
Issue Date | 2023 |
Citation | Nature Communications, 2023, v. 14, n. 1, article no. 2276 How to Cite? |
Abstract | Medical imaging is an important tool for accurate medical diagnosis, while state-of-the-art image reconstruction algorithms raise critical challenges in massive data processing for high-speed and high-quality imaging. Here, we present a memristive image reconstructor (MIR) to greatly accelerate image reconstruction with discrete Fourier transformation (DFT) by computing-in-memory (CIM) with memristor arrays. A high-accuracy quasi-analogue mapping (QAM) method and generic complex matrix transfer (CMT) scheme was proposed to improve the mapping precision and transfer efficiency, respectively. High-fidelity magnetic resonance imaging (MRI) and computed tomography (CT) image reconstructions were demonstrated, achieving software-equivalent qualities and DICE scores after segmentation with nnU-Net algorithm. Remarkably, our MIR exhibited 153× and 79× improvements in energy efficiency and normalized image reconstruction speed, respectively, compared to graphics processing unit (GPU). This work demonstrates MIR as a promising high-fidelity image reconstruction platform for future medical diagnosis, and also largely extends the application of memristor-based CIM beyond artificial neural networks. |
Persistent Identifier | http://hdl.handle.net/10722/334920 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhao, Han | - |
dc.contributor.author | Liu, Zhengwu | - |
dc.contributor.author | Tang, Jianshi | - |
dc.contributor.author | Gao, Bin | - |
dc.contributor.author | Qin, Qi | - |
dc.contributor.author | Li, Jiaming | - |
dc.contributor.author | Zhou, Ying | - |
dc.contributor.author | Yao, Peng | - |
dc.contributor.author | Xi, Yue | - |
dc.contributor.author | Lin, Yudeng | - |
dc.contributor.author | Qian, He | - |
dc.contributor.author | Wu, Huaqiang | - |
dc.date.accessioned | 2023-10-20T06:51:44Z | - |
dc.date.available | 2023-10-20T06:51:44Z | - |
dc.date.issued | 2023 | - |
dc.identifier.citation | Nature Communications, 2023, v. 14, n. 1, article no. 2276 | - |
dc.identifier.uri | http://hdl.handle.net/10722/334920 | - |
dc.description.abstract | Medical imaging is an important tool for accurate medical diagnosis, while state-of-the-art image reconstruction algorithms raise critical challenges in massive data processing for high-speed and high-quality imaging. Here, we present a memristive image reconstructor (MIR) to greatly accelerate image reconstruction with discrete Fourier transformation (DFT) by computing-in-memory (CIM) with memristor arrays. A high-accuracy quasi-analogue mapping (QAM) method and generic complex matrix transfer (CMT) scheme was proposed to improve the mapping precision and transfer efficiency, respectively. High-fidelity magnetic resonance imaging (MRI) and computed tomography (CT) image reconstructions were demonstrated, achieving software-equivalent qualities and DICE scores after segmentation with nnU-Net algorithm. Remarkably, our MIR exhibited 153× and 79× improvements in energy efficiency and normalized image reconstruction speed, respectively, compared to graphics processing unit (GPU). This work demonstrates MIR as a promising high-fidelity image reconstruction platform for future medical diagnosis, and also largely extends the application of memristor-based CIM beyond artificial neural networks. | - |
dc.language | eng | - |
dc.relation.ispartof | Nature Communications | - |
dc.title | Energy-efficient high-fidelity image reconstruction with memristor arrays for medical diagnosis | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1038/s41467-023-38021-7 | - |
dc.identifier.pmid | 37081008 | - |
dc.identifier.scopus | eid_2-s2.0-85153424860 | - |
dc.identifier.volume | 14 | - |
dc.identifier.issue | 1 | - |
dc.identifier.spage | article no. 2276 | - |
dc.identifier.epage | article no. 2276 | - |
dc.identifier.eissn | 2041-1723 | - |
dc.identifier.isi | WOS:001025247300001 | - |