Fetal magnetic resonance image denoising based on homogeneity testing and Non Local Means
(2016) 42nd Computing in Cardiology Conference, 2015 42. p.341-344- Abstract
A novel edge-preserving denoising method for MR images is proposed. Local statistical homogeneity testing is combined with the well-known for structure preserving properties, Non Local Means (NLM) denoising method. The detection of homogeneity reduces remarkably the computational effort required by NLM which is applied only to information-rich image areas. Preliminary qualitative results on fetal and cardiac MR images are shown. These initial results are positive proving the effective noise reduction with less computational load.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/a6430c87-cca7-4cb6-9848-faa4a814606e
- author
- Haris, K. LU ; Kantasis, G. ; Maglaveras, N. and Aletras, A. H. LU
- publishing date
- 2016-02-16
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Computing in Cardiology
- volume
- 42
- article number
- 7408656
- pages
- 4 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 42nd Computing in Cardiology Conference, 2015
- conference location
- Nice, France
- conference dates
- 2015-09-06 - 2015-09-09
- external identifiers
-
- scopus:84964077792
- ISBN
- 9781509006854
- DOI
- 10.1109/CIC.2015.7408656
- language
- English
- LU publication?
- no
- id
- a6430c87-cca7-4cb6-9848-faa4a814606e
- date added to LUP
- 2016-06-28 14:41:48
- date last changed
- 2022-01-30 04:47:57
@inproceedings{a6430c87-cca7-4cb6-9848-faa4a814606e, abstract = {{<p>A novel edge-preserving denoising method for MR images is proposed. Local statistical homogeneity testing is combined with the well-known for structure preserving properties, Non Local Means (NLM) denoising method. The detection of homogeneity reduces remarkably the computational effort required by NLM which is applied only to information-rich image areas. Preliminary qualitative results on fetal and cardiac MR images are shown. These initial results are positive proving the effective noise reduction with less computational load.</p>}}, author = {{Haris, K. and Kantasis, G. and Maglaveras, N. and Aletras, A. H.}}, booktitle = {{Computing in Cardiology}}, isbn = {{9781509006854}}, language = {{eng}}, month = {{02}}, pages = {{341--344}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Fetal magnetic resonance image denoising based on homogeneity testing and Non Local Means}}, url = {{http://dx.doi.org/10.1109/CIC.2015.7408656}}, doi = {{10.1109/CIC.2015.7408656}}, volume = {{42}}, year = {{2016}}, }