MR image resolution enhancement using a multi-layer neural network

H. Yan; J. Mao; B. Chen

doi:10.1109/CBMS.1992.245027

MR image resolution enhancement using a multi-layer neural network

H. Yan
, J. Mao
, B. Chen

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

A magnetic resonance image may contain truncation artifacts if there are not enough high-frequency data when the conventional Fourier transform method is used for reconstruction. The authors propose a method for reducing the artifacts using a multilayer neural network. The network consists of one linear output layer and at least one nonlinear hidden layer. In this method the missing high-frequency components are predicted based on known low-frequency components and are used to improve the resolution of the image. The method is tested with simulated data with good results.

Original language	English
Title of host publication	Computer-Based Medical Systems - Proceedings of the 5th Annual IEEE Symposium, CBMS 1992
Publisher	IEEE
Pages	624-632
Volume	1992-June
ISBN (Print)	0818627425
DOIs	https://doi.org/10.1109/CBMS.1992.245027
Publication status	Published - 1992
Externally published	Yes
Event	5th Annual IEEE Symposium on Computer-Based Medical Systems, CBMS 1992 - Durham, United States Duration: 14 Jun 1992 → 17 Jun 1992

Publication series

Name	Proceedings - IEEE Symposium on Computer-Based Medical Systems
Volume	1992-June
ISSN (Print)	1063-7125

Conference

Conference	5th Annual IEEE Symposium on Computer-Based Medical Systems, CBMS 1992
Place	United States
City	Durham
Period	14/06/92 → 17/06/92

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Access Output

10.1109/CBMS.1992.245027

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Yan, H., Mao, J., & Chen, B. (1992). MR image resolution enhancement using a multi-layer neural network. In Computer-Based Medical Systems - Proceedings of the 5th Annual IEEE Symposium, CBMS 1992 (Vol. 1992-June, pp. 624-632). Article 245027 (Proceedings - IEEE Symposium on Computer-Based Medical Systems; Vol. 1992-June). IEEE. https://doi.org/10.1109/CBMS.1992.245027

@inproceedings{35679751312a463bbaa069f751fa79e5,

title = "MR image resolution enhancement using a multi-layer neural network",

abstract = "A magnetic resonance image may contain truncation artifacts if there are not enough high-frequency data when the conventional Fourier transform method is used for reconstruction. The authors propose a method for reducing the artifacts using a multilayer neural network. The network consists of one linear output layer and at least one nonlinear hidden layer. In this method the missing high-frequency components are predicted based on known low-frequency components and are used to improve the resolution of the image. The method is tested with simulated data with good results.",

author = "H. Yan and J. Mao and B. Chen",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].; 5th Annual IEEE Symposium on Computer-Based Medical Systems, CBMS 1992 ; Conference date: 14-06-1992 Through 17-06-1992",

year = "1992",

doi = "10.1109/CBMS.1992.245027",

language = "English",

isbn = "0818627425",

volume = "1992-June",

series = "Proceedings - IEEE Symposium on Computer-Based Medical Systems",

publisher = "IEEE",

pages = "624--632",

booktitle = "Computer-Based Medical Systems - Proceedings of the 5th Annual IEEE Symposium, CBMS 1992",

address = "United States",

}

Yan, H, Mao, J & Chen, B 1992, MR image resolution enhancement using a multi-layer neural network. in Computer-Based Medical Systems - Proceedings of the 5th Annual IEEE Symposium, CBMS 1992. vol. 1992-June, 245027, Proceedings - IEEE Symposium on Computer-Based Medical Systems, vol. 1992-June, IEEE, pp. 624-632, 5th Annual IEEE Symposium on Computer-Based Medical Systems, CBMS 1992, Durham, North Carolina, United States, 14/06/92. https://doi.org/10.1109/CBMS.1992.245027

MR image resolution enhancement using a multi-layer neural network. / Yan, H.; Mao, J.; Chen, B.
Computer-Based Medical Systems - Proceedings of the 5th Annual IEEE Symposium, CBMS 1992. Vol. 1992-June IEEE, 1992. p. 624-632 245027 (Proceedings - IEEE Symposium on Computer-Based Medical Systems; Vol. 1992-June).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - MR image resolution enhancement using a multi-layer neural network

AU - Yan, H.

AU - Mao, J.

AU - Chen, B.

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 1992

Y1 - 1992

N2 - A magnetic resonance image may contain truncation artifacts if there are not enough high-frequency data when the conventional Fourier transform method is used for reconstruction. The authors propose a method for reducing the artifacts using a multilayer neural network. The network consists of one linear output layer and at least one nonlinear hidden layer. In this method the missing high-frequency components are predicted based on known low-frequency components and are used to improve the resolution of the image. The method is tested with simulated data with good results.

AB - A magnetic resonance image may contain truncation artifacts if there are not enough high-frequency data when the conventional Fourier transform method is used for reconstruction. The authors propose a method for reducing the artifacts using a multilayer neural network. The network consists of one linear output layer and at least one nonlinear hidden layer. In this method the missing high-frequency components are predicted based on known low-frequency components and are used to improve the resolution of the image. The method is tested with simulated data with good results.

UR - https://www.scopus.com/pages/publications/84955046492

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84955046492&origin=recordpage

U2 - 10.1109/CBMS.1992.245027

DO - 10.1109/CBMS.1992.245027

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0818627425

VL - 1992-June

T3 - Proceedings - IEEE Symposium on Computer-Based Medical Systems

SP - 624

EP - 632

BT - Computer-Based Medical Systems - Proceedings of the 5th Annual IEEE Symposium, CBMS 1992

PB - IEEE

T2 - 5th Annual IEEE Symposium on Computer-Based Medical Systems, CBMS 1992

Y2 - 14 June 1992 through 17 June 1992

ER -

MR image resolution enhancement using a multi-layer neural network

Abstract

Publication series

Conference

Bibliographical note

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this