Fetal magnetic resonance image denoising based on homogeneity testing and Non Local Means

K. Haris; G. Kantasis; N. Maglaveras; A. H. Aletras

doi:10.1109/CIC.2015.7408656

Fetal magnetic resonance image denoising based on homogeneity testing and Non Local Means

K. Haris, G. Kantasis, N. Maglaveras, A. H. Aletras

Aristotle University of Thessaloniki

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

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.

Original language	English
Title of host publication	Computing in Cardiology
Publisher	IEEE - Institute of Electrical and Electronics Engineers Inc.
Pages	341-344
Number of pages	4
Volume	42
ISBN (Print)	9781509006854
DOIs	https://doi.org/10.1109/CIC.2015.7408656
Publication status	Published - 2016 Feb 16
Externally published	Yes
Event	42nd Computing in Cardiology Conference, 2015 - Nice, France Duration: 2015 Sept 6 → 2015 Sept 9 Conference number: 42

Conference

Conference	42nd Computing in Cardiology Conference, 2015
Abbreviated title	CinC 2015
Country/Territory	France
City	Nice
Period	2015/09/06 → 2015/09/09

Subject classification (UKÄ)

Other Medical Biotechnology

Access to Document

10.1109/CIC.2015.7408656

Cite this

@inproceedings{a6430c87cca74cb69848faa4a814606e,

title = "Fetal magnetic resonance image denoising based on homogeneity testing and Non Local Means",

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.",

author = "K. Haris and G. Kantasis and N. Maglaveras and Aletras, {A. H.}",

year = "2016",

month = feb,

day = "16",

doi = "10.1109/CIC.2015.7408656",

language = "English",

isbn = "9781509006854",

volume = "42",

pages = "341--344",

booktitle = "Computing in Cardiology",

publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "42nd Computing in Cardiology Conference, 2015, CinC 2015 ; Conference date: 06-09-2015 Through 09-09-2015",

}

Haris, K, Kantasis, G, Maglaveras, N & Aletras, AH 2016, Fetal magnetic resonance image denoising based on homogeneity testing and Non Local Means. in Computing in Cardiology. vol. 42, 7408656, IEEE - Institute of Electrical and Electronics Engineers Inc., pp. 341-344, 42nd Computing in Cardiology Conference, 2015, Nice, France, 2015/09/06. https://doi.org/10.1109/CIC.2015.7408656

Fetal magnetic resonance image denoising based on homogeneity testing and Non Local Means. / Haris, K.; Kantasis, G.; Maglaveras, N. et al.
Computing in Cardiology. Vol. 42 IEEE - Institute of Electrical and Electronics Engineers Inc., 2016. p. 341-344 7408656.

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

TY - GEN

T1 - Fetal magnetic resonance image denoising based on homogeneity testing and Non Local Means

AU - Haris, K.

AU - Kantasis, G.

AU - Maglaveras, N.

AU - Aletras, A. H.

N1 - Conference code: 42

PY - 2016/2/16

Y1 - 2016/2/16

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84964077792&partnerID=8YFLogxK

U2 - 10.1109/CIC.2015.7408656

DO - 10.1109/CIC.2015.7408656

M3 - Paper in conference proceeding

AN - SCOPUS:84964077792

SN - 9781509006854

VL - 42

SP - 341

EP - 344

BT - Computing in Cardiology

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

T2 - 42nd Computing in Cardiology Conference, 2015

Y2 - 6 September 2015 through 9 September 2015

ER -

Fetal magnetic resonance image denoising based on homogeneity testing and Non Local Means

Abstract

Conference

Subject classification (UKÄ)

Access to Document

Other files and links

Fingerprint

Cite this