Collaborative non-local means denoising of magnetic resonance images

Geng Chen, Pei Zhang, Yafeng Wu, Dinggang Shen, Pew Thian Yap

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Noise artifacts in magnetic resonance (MR) images increase the complexity of image processing workflows and decrease the reliability of inferences drawn from the images. To reduce noise, the non-local means (NLM) filter has been shown to yield state-of-the-art denoising performance. However, NLM relies heavily on the existence of recurring structural patterns and this condition might not always be satisfied especially within a single image, where complex patterns might not recur. In this paper, we propose to leverage common structures from multiple images to collaboratively denoise an image. The assumption is that, although the human brain is structurally complex, common structures can be found with greater probability from multiple scans than from a single scan. More specifically, to denoise an image, multiple images from different individuals are spatially aligned to the image and NLM-like block matching is performed on these aligned images with the image as the reference. Experiments on synthetic and real data indicate that the proposed approach - collaborative non-local means (CNLM) - outperforms the classic NLM and yields results with markedly improved structural details.

Original languageEnglish
Title of host publicationProceedings - International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages564-567
Number of pages4
Volume2015-July
ISBN (Print)9781479923748
DOIs
Publication statusPublished - 2015 Jul 21
Externally publishedYes
Event12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States
Duration: 2015 Apr 162015 Apr 19

Other

Other12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
CountryUnited States
CityBrooklyn
Period15/4/1615/4/19

Fingerprint

Magnetic resonance
Noise
Brain
Image processing
Magnetic Resonance Spectroscopy
Workflow
Artifacts
Experiments

Keywords

  • edge-preserving denoising
  • MRI denoising
  • non-local means filter
  • patch-based approach

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Chen, G., Zhang, P., Wu, Y., Shen, D., & Yap, P. T. (2015). Collaborative non-local means denoising of magnetic resonance images. In Proceedings - International Symposium on Biomedical Imaging (Vol. 2015-July, pp. 564-567). [7163936] IEEE Computer Society. https://doi.org/10.1109/ISBI.2015.7163936

Collaborative non-local means denoising of magnetic resonance images. / Chen, Geng; Zhang, Pei; Wu, Yafeng; Shen, Dinggang; Yap, Pew Thian.

Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. p. 564-567 7163936.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, G, Zhang, P, Wu, Y, Shen, D & Yap, PT 2015, Collaborative non-local means denoising of magnetic resonance images. in Proceedings - International Symposium on Biomedical Imaging. vol. 2015-July, 7163936, IEEE Computer Society, pp. 564-567, 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, Brooklyn, United States, 15/4/16. https://doi.org/10.1109/ISBI.2015.7163936
Chen G, Zhang P, Wu Y, Shen D, Yap PT. Collaborative non-local means denoising of magnetic resonance images. In Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July. IEEE Computer Society. 2015. p. 564-567. 7163936 https://doi.org/10.1109/ISBI.2015.7163936
Chen, Geng ; Zhang, Pei ; Wu, Yafeng ; Shen, Dinggang ; Yap, Pew Thian. / Collaborative non-local means denoising of magnetic resonance images. Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. pp. 564-567
@inproceedings{f4b117477752418f8db17dc2c48ff169,
title = "Collaborative non-local means denoising of magnetic resonance images",
abstract = "Noise artifacts in magnetic resonance (MR) images increase the complexity of image processing workflows and decrease the reliability of inferences drawn from the images. To reduce noise, the non-local means (NLM) filter has been shown to yield state-of-the-art denoising performance. However, NLM relies heavily on the existence of recurring structural patterns and this condition might not always be satisfied especially within a single image, where complex patterns might not recur. In this paper, we propose to leverage common structures from multiple images to collaboratively denoise an image. The assumption is that, although the human brain is structurally complex, common structures can be found with greater probability from multiple scans than from a single scan. More specifically, to denoise an image, multiple images from different individuals are spatially aligned to the image and NLM-like block matching is performed on these aligned images with the image as the reference. Experiments on synthetic and real data indicate that the proposed approach - collaborative non-local means (CNLM) - outperforms the classic NLM and yields results with markedly improved structural details.",
keywords = "edge-preserving denoising, MRI denoising, non-local means filter, patch-based approach",
author = "Geng Chen and Pei Zhang and Yafeng Wu and Dinggang Shen and Yap, {Pew Thian}",
year = "2015",
month = "7",
day = "21",
doi = "10.1109/ISBI.2015.7163936",
language = "English",
isbn = "9781479923748",
volume = "2015-July",
pages = "564--567",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Collaborative non-local means denoising of magnetic resonance images

AU - Chen, Geng

AU - Zhang, Pei

AU - Wu, Yafeng

AU - Shen, Dinggang

AU - Yap, Pew Thian

PY - 2015/7/21

Y1 - 2015/7/21

N2 - Noise artifacts in magnetic resonance (MR) images increase the complexity of image processing workflows and decrease the reliability of inferences drawn from the images. To reduce noise, the non-local means (NLM) filter has been shown to yield state-of-the-art denoising performance. However, NLM relies heavily on the existence of recurring structural patterns and this condition might not always be satisfied especially within a single image, where complex patterns might not recur. In this paper, we propose to leverage common structures from multiple images to collaboratively denoise an image. The assumption is that, although the human brain is structurally complex, common structures can be found with greater probability from multiple scans than from a single scan. More specifically, to denoise an image, multiple images from different individuals are spatially aligned to the image and NLM-like block matching is performed on these aligned images with the image as the reference. Experiments on synthetic and real data indicate that the proposed approach - collaborative non-local means (CNLM) - outperforms the classic NLM and yields results with markedly improved structural details.

AB - Noise artifacts in magnetic resonance (MR) images increase the complexity of image processing workflows and decrease the reliability of inferences drawn from the images. To reduce noise, the non-local means (NLM) filter has been shown to yield state-of-the-art denoising performance. However, NLM relies heavily on the existence of recurring structural patterns and this condition might not always be satisfied especially within a single image, where complex patterns might not recur. In this paper, we propose to leverage common structures from multiple images to collaboratively denoise an image. The assumption is that, although the human brain is structurally complex, common structures can be found with greater probability from multiple scans than from a single scan. More specifically, to denoise an image, multiple images from different individuals are spatially aligned to the image and NLM-like block matching is performed on these aligned images with the image as the reference. Experiments on synthetic and real data indicate that the proposed approach - collaborative non-local means (CNLM) - outperforms the classic NLM and yields results with markedly improved structural details.

KW - edge-preserving denoising

KW - MRI denoising

KW - non-local means filter

KW - patch-based approach

UR - http://www.scopus.com/inward/record.url?scp=84944318547&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944318547&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2015.7163936

DO - 10.1109/ISBI.2015.7163936

M3 - Conference contribution

AN - SCOPUS:84944318547

SN - 9781479923748

VL - 2015-July

SP - 564

EP - 567

BT - Proceedings - International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -