BCC skin cancer diagnosis based on texture analysis techniques

Shao Hui Chuang; Xiaoyan Sun; Wen Yu Chang; Gwo Shing Chen; Adam Huang; Jiang Li; Frederic D. McKenzie

doi:10.1117/12.878124

BCC skin cancer diagnosis based on texture analysis techniques

Shao Hui Chuang, Xiaoyan Sun, Wen Yu Chang, Gwo Shing Chen, Adam Huang, Jiang Li, Frederic D. McKenzie

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

3 引文斯高帕斯（Scopus）

摘要

In this paper, we present a texture analysis based method for diagnosing the Basal Cell Carcinoma (BCC) skin cancer using optical images taken from the suspicious skin regions. We first extracted the Run Length Matrix and Haralick texture features from the images and used a feature selection algorithm to identify the most effective feature set for the diagnosis. We then utilized a Multi-Layer Perceptron (MLP) classifier to classify the images to BCC or normal cases. Experiments showed that detecting BCC cancer based on optical images is feasible. The best sensitivity and specificity we achieved on our data set were 94% and 95%, respectively.

原文	???core.languages.en_GB???
主出版物標題	Medical Imaging 2011
主出版物子標題	Computer-Aided Diagnosis
DOIs	https://doi.org/10.1117/12.878124
出版狀態	已出版 - 2011
事件	Medical Imaging 2011: Computer-Aided Diagnosis - Lake Buena Vista, FL, United States 持續時間: 15 2月 2011 → 17 2月 2011

出版系列

名字	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
卷	7963
ISSN（列印）	1605-7422

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	Medical Imaging 2011: Computer-Aided Diagnosis
國家/地區	United States
城市	Lake Buena Vista, FL
期間	15/02/11 → 17/02/11

UN SDG

此研究成果有助於以下永續發展目標

存取文件

10.1117/12.878124

引用此

@inproceedings{2eefd3a8a6a6464d8e790075c7de4f43,

title = "BCC skin cancer diagnosis based on texture analysis techniques",

abstract = "In this paper, we present a texture analysis based method for diagnosing the Basal Cell Carcinoma (BCC) skin cancer using optical images taken from the suspicious skin regions. We first extracted the Run Length Matrix and Haralick texture features from the images and used a feature selection algorithm to identify the most effective feature set for the diagnosis. We then utilized a Multi-Layer Perceptron (MLP) classifier to classify the images to BCC or normal cases. Experiments showed that detecting BCC cancer based on optical images is feasible. The best sensitivity and specificity we achieved on our data set were 94% and 95%, respectively.",

keywords = "BCC Skin Cancer, Gray Level Co-occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLCM), Texture Analysis",

author = "Chuang, {Shao Hui} and Xiaoyan Sun and Chang, {Wen Yu} and Chen, {Gwo Shing} and Adam Huang and Jiang Li and McKenzie, {Frederic D.}",

year = "2011",

doi = "10.1117/12.878124",

language = "???core.languages.en_GB???",

isbn = "9780819485052",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

booktitle = "Medical Imaging 2011",

note = "Medical Imaging 2011: Computer-Aided Diagnosis ; Conference date: 15-02-2011 Through 17-02-2011",

}

Chuang, SH, Sun, X, Chang, WY, Chen, GS, Huang, A, Li, J & McKenzie, FD 2011, BCC skin cancer diagnosis based on texture analysis techniques. 於 Medical Imaging 2011: Computer-Aided Diagnosis., 79633O, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, 卷 7963, Medical Imaging 2011: Computer-Aided Diagnosis, Lake Buena Vista, FL, United States, 15/02/11. https://doi.org/10.1117/12.878124

TY - GEN

T1 - BCC skin cancer diagnosis based on texture analysis techniques

AU - Chuang, Shao Hui

AU - Sun, Xiaoyan

AU - Chang, Wen Yu

AU - Chen, Gwo Shing

AU - Huang, Adam

AU - Li, Jiang

AU - McKenzie, Frederic D.

PY - 2011

Y1 - 2011

N2 - In this paper, we present a texture analysis based method for diagnosing the Basal Cell Carcinoma (BCC) skin cancer using optical images taken from the suspicious skin regions. We first extracted the Run Length Matrix and Haralick texture features from the images and used a feature selection algorithm to identify the most effective feature set for the diagnosis. We then utilized a Multi-Layer Perceptron (MLP) classifier to classify the images to BCC or normal cases. Experiments showed that detecting BCC cancer based on optical images is feasible. The best sensitivity and specificity we achieved on our data set were 94% and 95%, respectively.

AB - In this paper, we present a texture analysis based method for diagnosing the Basal Cell Carcinoma (BCC) skin cancer using optical images taken from the suspicious skin regions. We first extracted the Run Length Matrix and Haralick texture features from the images and used a feature selection algorithm to identify the most effective feature set for the diagnosis. We then utilized a Multi-Layer Perceptron (MLP) classifier to classify the images to BCC or normal cases. Experiments showed that detecting BCC cancer based on optical images is feasible. The best sensitivity and specificity we achieved on our data set were 94% and 95%, respectively.

KW - BCC Skin Cancer

KW - Gray Level Co-occurrence Matrix (GLCM)

KW - Gray Level Run Length Matrix (GLCM)

KW - Texture Analysis

UR - http://www.scopus.com/inward/record.url?scp=79955752683&partnerID=8YFLogxK

U2 - 10.1117/12.878124

DO - 10.1117/12.878124

M3 - 會議論文篇章

AN - SCOPUS:79955752683

SN - 9780819485052

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2011

T2 - Medical Imaging 2011: Computer-Aided Diagnosis

Y2 - 15 February 2011 through 17 February 2011

ER -

BCC skin cancer diagnosis based on texture analysis techniques

摘要

出版系列

???event.eventtypes.event.conference???

UN SDG

存取文件

指紋

引用此