Classification of bladder cancer on radiotherapy planning CT images using textural features

Hanqing Liao; William H. Nailon; Duncan B. McLaren; Steve McLaughlin

Classification of bladder cancer on radiotherapy planning CT images using textural features

Hanqing Liao^*, William H. Nailon, Duncan B. McLaren, Steve McLaughlin

^*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

Highly reliable classification of anatomical regions is an important step in the delineation of the gross tumour volume (GTV) in computed tomography (CT) images during radiotherapy planning. In this study pixel-based statistics such as mean and variance were insufficient for classifying the bladder, rectum and a control region. Statistical texture analysis were used to extract features from gray-tone spatial dependence matrices (GTSDM). The features were de-correlated and reduced using principal component analysis (PCA), and the principal components (PC) were classified by a naive Bayes classifier (NBC). The results suggests that the three most significant PC of the 56 features from GTSDM with distances d = 1,2,3,4 give the highest average correct classification percentage.

Original language	English
Title of host publication	2010 18th European Signal Processing Conference
Publisher	IEEE
Pages	284-288
Number of pages	5
Publication status	Published - 2010
Event	18th European Signal Processing Conference 2010 - Aalborg, Denmark Duration: 23 Aug 2010 → 27 Aug 2010

Publication series

Name	European Signal Processing Conference
ISSN (Print)	2219-5491

Conference

Conference	18th European Signal Processing Conference 2010
Abbreviated title	EUSIPCO 2010
Country/Territory	Denmark
City	Aalborg
Period	23/08/10 → 27/08/10

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

@inproceedings{ad2eaf39af2f44b78809e5bd41fd8c1b,

title = "Classification of bladder cancer on radiotherapy planning CT images using textural features",

abstract = "Highly reliable classification of anatomical regions is an important step in the delineation of the gross tumour volume (GTV) in computed tomography (CT) images during radiotherapy planning. In this study pixel-based statistics such as mean and variance were insufficient for classifying the bladder, rectum and a control region. Statistical texture analysis were used to extract features from gray-tone spatial dependence matrices (GTSDM). The features were de-correlated and reduced using principal component analysis (PCA), and the principal components (PC) were classified by a naive Bayes classifier (NBC). The results suggests that the three most significant PC of the 56 features from GTSDM with distances d = 1,2,3,4 give the highest average correct classification percentage.",

author = "Hanqing Liao and Nailon, {William H.} and McLaren, {Duncan B.} and Steve McLaughlin",

year = "2010",

language = "English",

series = "European Signal Processing Conference",

publisher = "IEEE",

pages = "284--288",

booktitle = "2010 18th European Signal Processing Conference",

address = "United States",

}

TY - GEN

T1 - Classification of bladder cancer on radiotherapy planning CT images using textural features

AU - Liao, Hanqing

AU - Nailon, William H.

AU - McLaren, Duncan B.

AU - McLaughlin, Steve

PY - 2010

Y1 - 2010

N2 - Highly reliable classification of anatomical regions is an important step in the delineation of the gross tumour volume (GTV) in computed tomography (CT) images during radiotherapy planning. In this study pixel-based statistics such as mean and variance were insufficient for classifying the bladder, rectum and a control region. Statistical texture analysis were used to extract features from gray-tone spatial dependence matrices (GTSDM). The features were de-correlated and reduced using principal component analysis (PCA), and the principal components (PC) were classified by a naive Bayes classifier (NBC). The results suggests that the three most significant PC of the 56 features from GTSDM with distances d = 1,2,3,4 give the highest average correct classification percentage.

AB - Highly reliable classification of anatomical regions is an important step in the delineation of the gross tumour volume (GTV) in computed tomography (CT) images during radiotherapy planning. In this study pixel-based statistics such as mean and variance were insufficient for classifying the bladder, rectum and a control region. Statistical texture analysis were used to extract features from gray-tone spatial dependence matrices (GTSDM). The features were de-correlated and reduced using principal component analysis (PCA), and the principal components (PC) were classified by a naive Bayes classifier (NBC). The results suggests that the three most significant PC of the 56 features from GTSDM with distances d = 1,2,3,4 give the highest average correct classification percentage.

UR - http://www.scopus.com/inward/record.url?scp=84863787198&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84863787198

T3 - European Signal Processing Conference

SP - 284

EP - 288

BT - 2010 18th European Signal Processing Conference

PB - IEEE

T2 - 18th European Signal Processing Conference 2010

Y2 - 23 August 2010 through 27 August 2010

ER -

Classification of bladder cancer on radiotherapy planning CT images using textural features

Abstract

Publication series

Conference

ASJC Scopus subject areas

UN SDGs

Other files and links

Fingerprint

Cite this