Adaptive Wiener filter based on Gaussian mixture model for denoising chest X-ray CT image

Motohiro Tabuchi; Nobumoto Yamane; Yoshitaka Morikawa

doi:10.1109/SICE.2007.4421069

Adaptive Wiener filter based on Gaussian mixture model for denoising chest X-ray CT image

Motohiro Tabuchi, Nobumoto Yamane, Yoshitaka Morikawa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

Because the X-ray CT imaging has high spatial resolution, it becomes more important in diagnostic imaging. However the techniques of low dose imaging at X-ray mass examination or thin slice imaging provide degraded CT images by noise. The CT images have specific noise, called streak artifact. In this paper, we apply an adaptive Wiener filter (AWF) based on the Gaussian mixture distribution model (GMM), proposed previously to reduce Gaussian white noise. Simulation results show that a new AWF-GMM designed using high dose (original) CT image and low dose (observed) CT image pairs of chest phantom for training image set provides high restoration ability.

Original language	English
Title of host publication	SICE Annual Conference, SICE 2007
Pages	682-689
Number of pages	8
DOIs	https://doi.org/10.1109/SICE.2007.4421069
Publication status	Published - 2007
Event	SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007 - Takamatsu, Japan Duration: Sep 17 2007 → Sep 20 2007

Publication series

Name	Proceedings of the SICE Annual Conference

Other

Other	SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007
Country	Japan
City	Takamatsu
Period	9/17/07 → 9/20/07

Keywords

Adaptive wiener filter
Expectation-maximization algorithm
Gaussian mixture distribution model
Maximum a posteriori probability
Phantom

ASJC Scopus subject areas

Control and Systems Engineering
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/SICE.2007.4421069

Fingerprint Dive into the research topics of 'Adaptive Wiener filter based on Gaussian mixture model for denoising chest X-ray CT image'. Together they form a unique fingerprint.

Cite this

Tabuchi, M, Yamane, N & Morikawa, Y 2007, Adaptive Wiener filter based on Gaussian mixture model for denoising chest X-ray CT image. in SICE Annual Conference, SICE 2007., 4421069, Proceedings of the SICE Annual Conference, pp. 682-689, SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007, Takamatsu, Japan, 9/17/07. https://doi.org/10.1109/SICE.2007.4421069

@inproceedings{0df9a057c3114674885e96e95432a520,

title = "Adaptive Wiener filter based on Gaussian mixture model for denoising chest X-ray CT image",

abstract = "Because the X-ray CT imaging has high spatial resolution, it becomes more important in diagnostic imaging. However the techniques of low dose imaging at X-ray mass examination or thin slice imaging provide degraded CT images by noise. The CT images have specific noise, called streak artifact. In this paper, we apply an adaptive Wiener filter (AWF) based on the Gaussian mixture distribution model (GMM), proposed previously to reduce Gaussian white noise. Simulation results show that a new AWF-GMM designed using high dose (original) CT image and low dose (observed) CT image pairs of chest phantom for training image set provides high restoration ability.",

keywords = "Adaptive wiener filter, Expectation-maximization algorithm, Gaussian mixture distribution model, Maximum a posteriori probability, Phantom",

author = "Motohiro Tabuchi and Nobumoto Yamane and Yoshitaka Morikawa",

year = "2007",

doi = "10.1109/SICE.2007.4421069",

language = "English",

isbn = "4907764286",

series = "Proceedings of the SICE Annual Conference",

pages = "682--689",

booktitle = "SICE Annual Conference, SICE 2007",

note = "SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007 ; Conference date: 17-09-2007 Through 20-09-2007",

}

TY - GEN

T1 - Adaptive Wiener filter based on Gaussian mixture model for denoising chest X-ray CT image

AU - Tabuchi, Motohiro

AU - Yamane, Nobumoto

AU - Morikawa, Yoshitaka

PY - 2007

Y1 - 2007

N2 - Because the X-ray CT imaging has high spatial resolution, it becomes more important in diagnostic imaging. However the techniques of low dose imaging at X-ray mass examination or thin slice imaging provide degraded CT images by noise. The CT images have specific noise, called streak artifact. In this paper, we apply an adaptive Wiener filter (AWF) based on the Gaussian mixture distribution model (GMM), proposed previously to reduce Gaussian white noise. Simulation results show that a new AWF-GMM designed using high dose (original) CT image and low dose (observed) CT image pairs of chest phantom for training image set provides high restoration ability.

AB - Because the X-ray CT imaging has high spatial resolution, it becomes more important in diagnostic imaging. However the techniques of low dose imaging at X-ray mass examination or thin slice imaging provide degraded CT images by noise. The CT images have specific noise, called streak artifact. In this paper, we apply an adaptive Wiener filter (AWF) based on the Gaussian mixture distribution model (GMM), proposed previously to reduce Gaussian white noise. Simulation results show that a new AWF-GMM designed using high dose (original) CT image and low dose (observed) CT image pairs of chest phantom for training image set provides high restoration ability.

KW - Adaptive wiener filter

KW - Expectation-maximization algorithm

KW - Gaussian mixture distribution model

KW - Maximum a posteriori probability

KW - Phantom

UR - http://www.scopus.com/inward/record.url?scp=50249153697&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249153697&partnerID=8YFLogxK

U2 - 10.1109/SICE.2007.4421069

DO - 10.1109/SICE.2007.4421069

M3 - Conference contribution

AN - SCOPUS:50249153697

SN - 4907764286

SN - 9784907764289

T3 - Proceedings of the SICE Annual Conference

SP - 682

EP - 689

BT - SICE Annual Conference, SICE 2007

T2 - SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007

Y2 - 17 September 2007 through 20 September 2007

ER -