A Quantatiitive Study of Texture Features across Different Window Sizes in Prostate T2-weighted MRI

Andrik Rampun; Liping Wang; Paul Malcolm; Reyer Zwiggelaar

doi:10.1016/j.procs.2016.07.026

A Quantatiitive Study of Texture Features across Different Window Sizes in Prostate T2-weighted MRI

Andrik Rampun, Liping Wang, Paul Malcolm, Reyer Zwiggelaar

Department of Computer Science

Norfolk & Norwich University Hospital

Research output: Contribution to journal › Article › peer-review

152 Downloads (Pure)

Abstract

This study aims to investigate the effects of window size on the performance of prostate cancer CAD and to identify discriminant texture descriptors in prostate T2-W MRI. For this purpose we extracted 215 texture features from 418 T2-W MRI images and extracted them using 9 different window sizes (3 × 3 to 19 × 19). The Bayesian Network and Random Forest classifiers were employed to perform the classification. Experimental results suggest that using window size of 9 × 9 and 11 × 11 produced Az > 89%. Also, this study suggests a set of best texture features based on our experimental results.

Original language	English
Pages (from-to)	74-79
Number of pages	6
Journal	Procedia Computer Science
Volume	90
DOIs	https://doi.org/10.1016/j.procs.2016.07.026
Publication status	Published - 06 Jul 2016
Event	Medical Imaging Understanding and Analysis - Loughborough University, Loughborough, United Kingdom of Great Britain and Northern Ireland Duration: 06 Jul 2016 → 08 Jul 2016 Conference number: 20

Keywords

texture descriptors
window size
computer aided diagnosis
T2-" MRI
prostate cancer

UN SDGs

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

Access to Document

10.1016/j.procs.2016.07.026

A Quantatiitive Study of Texture Features Across Different Window Sizes in Prostate T2-Weighted MRIFinal published version, 180 KBLicence: CC BY-NC-ND
A Quantitative Study of Texture Features Across Different Window Sizes in Prostate T2-Weighted MRIFinal published version, 180 KBLicence: CC BY-NC-ND

Permanent link

Persistent link

Cite this

@article{55408116867e4bd1beb044c2d3d9084a,

title = "A Quantatiitive Study of Texture Features across Different Window Sizes in Prostate T2-weighted MRI",

abstract = "This study aims to investigate the effects of window size on the performance of prostate cancer CAD and to identify discriminant texture descriptors in prostate T2-W MRI. For this purpose we extracted 215 texture features from 418 T2-W MRI images and extracted them using 9 different window sizes (3 × 3 to 19 × 19). The Bayesian Network and Random Forest classifiers were employed to perform the classification. Experimental results suggest that using window size of 9 × 9 and 11 × 11 produced Az > 89%. Also, this study suggests a set of best texture features based on our experimental results.",

keywords = "texture descriptors, window size, computer aided diagnosis, T2-{"} MRI, prostate cancer",

author = "Andrik Rampun and Liping Wang and Paul Malcolm and Reyer Zwiggelaar",

year = "2016",

month = jul,

day = "6",

doi = "10.1016/j.procs.2016.07.026",

language = "English",

volume = "90",

pages = "74--79",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier",

note = "Medical Imaging Understanding and Analysis, MIUA 2016 ; Conference date: 06-07-2016 Through 08-07-2016",

}

TY - JOUR

T1 - A Quantatiitive Study of Texture Features across Different Window Sizes in Prostate T2-weighted MRI

AU - Rampun, Andrik

AU - Wang, Liping

AU - Malcolm, Paul

AU - Zwiggelaar, Reyer

N1 - Conference code: 20

PY - 2016/7/6

Y1 - 2016/7/6

N2 - This study aims to investigate the effects of window size on the performance of prostate cancer CAD and to identify discriminant texture descriptors in prostate T2-W MRI. For this purpose we extracted 215 texture features from 418 T2-W MRI images and extracted them using 9 different window sizes (3 × 3 to 19 × 19). The Bayesian Network and Random Forest classifiers were employed to perform the classification. Experimental results suggest that using window size of 9 × 9 and 11 × 11 produced Az > 89%. Also, this study suggests a set of best texture features based on our experimental results.

AB - This study aims to investigate the effects of window size on the performance of prostate cancer CAD and to identify discriminant texture descriptors in prostate T2-W MRI. For this purpose we extracted 215 texture features from 418 T2-W MRI images and extracted them using 9 different window sizes (3 × 3 to 19 × 19). The Bayesian Network and Random Forest classifiers were employed to perform the classification. Experimental results suggest that using window size of 9 × 9 and 11 × 11 produced Az > 89%. Also, this study suggests a set of best texture features based on our experimental results.

KW - texture descriptors

KW - window size

KW - computer aided diagnosis

KW - T2-" MRI

KW - prostate cancer

UR - http://hdl.handle.net/2160/43497

U2 - 10.1016/j.procs.2016.07.026

DO - 10.1016/j.procs.2016.07.026

M3 - Article

SN - 1877-0509

VL - 90

SP - 74

EP - 79

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - Medical Imaging Understanding and Analysis

Y2 - 6 July 2016 through 8 July 2016

ER -

A Quantatiitive Study of Texture Features across Different Window Sizes in Prostate T2-weighted MRI

Abstract

Keywords

UN SDGs

Access to Document

Permanent link

Other files and links

Fingerprint

Cite this