Classifying Benign and Malignant Tissues within the Prostate Peripheral Zone using Textons

Yambu Andrik Rampun; Ling Zheng; Paul Malcolm; Reyer Zwiggelaar

Classifying Benign and Malignant Tissues within the Prostate Peripheral Zone using Textons

Yambu Andrik Rampun, Ling Zheng, Paul Malcolm, Reyer Zwiggelaar

Adran Cyfrifiadureg

Norfolk and Norwich University Hospitals NHS Foundation Trust

Allbwn ymchwil: Cyfraniad at gynhadledd › Papur › adolygiad gan gymheiriaid

6 Wedi eu Llwytho i Lawr (Pure)

Crynodeb

In this paper, we present our preliminary results classifying benign and malignant tissues within the prostate peripheral zone using textons. For this purpose, patches are randomly extracted from malignant and benign regions and we perform k-means clustering to generate textons. All textons are combined to form the texton dictionary which was used to construct a texton map for every peripheral zone region in each training image. Based on the texton map, histogram models for each malignant and benign tissue are constructed which will be used to train our classifiers. We tested the proposed method on 418 T2-W MR images taken from 45 patients and evaluation results of Az = 87% ±7% show a comparable performance with the state-of-the-art in the literature.

Iaith wreiddiol	Saesneg
Tudalennau	138-143
Nifer y tudalennau	6
Statws	Cyhoeddwyd - 15 Gorff 2015
Digwyddiad	19th Conference on Medical Image Understanding and Analysis 2015 - Lincoln, Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon Hyd: 15 Gorff 2015 → 17 Gorff 2015

Cynhadledd

Cynhadledd	19th Conference on Medical Image Understanding and Analysis 2015
Teitl cryno	MIUA
Gwlad/Tiriogaeth	Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon
Dinas	Lincoln
Cyfnod	15 Gorff 2015 → 17 Gorff 2015

Mynediad at Ddogfen

PaperFersiwn derfynol wedi’i chyhoeddi, 613 KB

Cysylltiad parhaol

Dolen barhaus

Dyfynnu hyn

@conference{ad045b0a3a96420f9a7a39c209dd6690,

title = "Classifying Benign and Malignant Tissues within the Prostate Peripheral Zone using Textons",

abstract = "In this paper, we present our preliminary results classifying benign and malignant tissues within the prostate peripheral zone using textons. For this purpose, patches are randomly extracted from malignant and benign regions and we perform k-means clustering to generate textons. All textons are combined to form the texton dictionary which was used to construct a texton map for every peripheral zone region in each training image. Based on the texton map, histogram models for each malignant and benign tissue are constructed which will be used to train our classifiers. We tested the proposed method on 418 T2-W MR images taken from 45 patients and evaluation results of Az = 87\% ±7\% show a comparable performance with the state-of-the-art in the literature.",

author = "Rampun, \{Yambu Andrik\} and Ling Zheng and Paul Malcolm and Reyer Zwiggelaar",

year = "2015",

month = jul,

day = "15",

language = "English",

pages = "138--143",

note = "19th Conference on Medical Image Understanding and Analysis 2015, MIUA ; Conference date: 15-07-2015 Through 17-07-2015",

}

Classifying Benign and Malignant Tissues within the Prostate Peripheral Zone using Textons. / Rampun, Yambu Andrik; Zheng, Ling; Malcolm, Paul et al.
2015. 138-143 Papur a gyflwynwyd yn 19th Conference on Medical Image Understanding and Analysis 2015, Lincoln, Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon.

Allbwn ymchwil: Cyfraniad at gynhadledd › Papur › adolygiad gan gymheiriaid

TY - CONF

T1 - Classifying Benign and Malignant Tissues within the Prostate Peripheral Zone using Textons

AU - Rampun, Yambu Andrik

AU - Zheng, Ling

AU - Malcolm, Paul

AU - Zwiggelaar, Reyer

PY - 2015/7/15

Y1 - 2015/7/15

N2 - In this paper, we present our preliminary results classifying benign and malignant tissues within the prostate peripheral zone using textons. For this purpose, patches are randomly extracted from malignant and benign regions and we perform k-means clustering to generate textons. All textons are combined to form the texton dictionary which was used to construct a texton map for every peripheral zone region in each training image. Based on the texton map, histogram models for each malignant and benign tissue are constructed which will be used to train our classifiers. We tested the proposed method on 418 T2-W MR images taken from 45 patients and evaluation results of Az = 87% ±7% show a comparable performance with the state-of-the-art in the literature.

AB - In this paper, we present our preliminary results classifying benign and malignant tissues within the prostate peripheral zone using textons. For this purpose, patches are randomly extracted from malignant and benign regions and we perform k-means clustering to generate textons. All textons are combined to form the texton dictionary which was used to construct a texton map for every peripheral zone region in each training image. Based on the texton map, histogram models for each malignant and benign tissue are constructed which will be used to train our classifiers. We tested the proposed method on 418 T2-W MR images taken from 45 patients and evaluation results of Az = 87% ±7% show a comparable performance with the state-of-the-art in the literature.

M3 - Paper

SP - 138

EP - 143

T2 - 19th Conference on Medical Image Understanding and Analysis 2015

Y2 - 15 July 2015 through 17 July 2015

ER -

Classifying Benign and Malignant Tissues within the Prostate Peripheral Zone using Textons

Crynodeb

Cynhadledd

Mynediad at Ddogfen

Cysylltiad parhaol

Ôl bys

Dyfynnu hyn