Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework

Ovarian cancer is one of the prime causes of mortality in women. Diagnosis of ovarian cancer using ultrasonography is tedious as ovarian tumors exhibit minute clinical and structural differences between the suspicious and non-suspicious classes. Early prediction of ovarian cancer will reduce its gro...

Full description

Saved in:
Bibliographic Details
Main Authors: Acharya, U. Rajendra, Akter, Ayesha, Chowriappa, Pradeep, Dua, Sumeet, Raghavendra, U., Koh, Joel E. W., Tan, Jen Hong, Leong, Sook Sam, Vijayananthan, Anushya, Hagiwara, Yuki, Ramli, Marlina Tanty, Ng, Kwan Hoong
Format: Article
Published: Springer Berlin Heidelberg 2018
Subjects:
Online Access:http://eprints.um.edu.my/22709/
https://doi.org/10.1007/s40815-018-0456-9
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Malaya
id my.um.eprints.22709
record_format eprints
spelling my.um.eprints.227092019-10-08T06:54:18Z http://eprints.um.edu.my/22709/ Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework Acharya, U. Rajendra Akter, Ayesha Chowriappa, Pradeep Dua, Sumeet Raghavendra, U. Koh, Joel E. W. Tan, Jen Hong Leong, Sook Sam Vijayananthan, Anushya Hagiwara, Yuki Ramli, Marlina Tanty Ng, Kwan Hoong R Medicine Ovarian cancer is one of the prime causes of mortality in women. Diagnosis of ovarian cancer using ultrasonography is tedious as ovarian tumors exhibit minute clinical and structural differences between the suspicious and non-suspicious classes. Early prediction of ovarian cancer will reduce its growth rate and may save many lives. Computer-aided diagnosis (CAD) is a noninvasive method for finding ovarian cancer in its early stage which can avoid patient anxiety and unnecessary biopsy. This study investigates the efficacy of a novel CAD tool to characterize suspicious ovarian cancer using Radon-transformed nonlinear features. The obtained dimension of the extracted features is reduced using Relief-F feature selection method. In this study, we have employed the fuzzy forest-based ensemble classifier in contrast to the known crisp rule-based classifiers. The proposed method is evaluated using 469 (non-suspicious: 238, suspicious: 231) subjects and achieved a maximum 80.60 ± 0.5% accuracy, 81.40% sensitivity, 76.30% specificity with fuzzy forest, an ensemble fuzzy classifier using thirty-nine features. The proposed method is robust and reproducible as it uses maximum number subjects (469) as compared to state-of-the-art techniques. Hence, it can be used as an assisting tool by gynecologists during their routine screening. Springer Berlin Heidelberg 2018 Article PeerReviewed Acharya, U. Rajendra and Akter, Ayesha and Chowriappa, Pradeep and Dua, Sumeet and Raghavendra, U. and Koh, Joel E. W. and Tan, Jen Hong and Leong, Sook Sam and Vijayananthan, Anushya and Hagiwara, Yuki and Ramli, Marlina Tanty and Ng, Kwan Hoong (2018) Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework. International Journal of Fuzzy Systems, 20 (4). pp. 1385-1402. ISSN 1562-2479 https://doi.org/10.1007/s40815-018-0456-9 doi:10.1007/s40815-018-0456-9
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic R Medicine
spellingShingle R Medicine
Acharya, U. Rajendra
Akter, Ayesha
Chowriappa, Pradeep
Dua, Sumeet
Raghavendra, U.
Koh, Joel E. W.
Tan, Jen Hong
Leong, Sook Sam
Vijayananthan, Anushya
Hagiwara, Yuki
Ramli, Marlina Tanty
Ng, Kwan Hoong
Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework
description Ovarian cancer is one of the prime causes of mortality in women. Diagnosis of ovarian cancer using ultrasonography is tedious as ovarian tumors exhibit minute clinical and structural differences between the suspicious and non-suspicious classes. Early prediction of ovarian cancer will reduce its growth rate and may save many lives. Computer-aided diagnosis (CAD) is a noninvasive method for finding ovarian cancer in its early stage which can avoid patient anxiety and unnecessary biopsy. This study investigates the efficacy of a novel CAD tool to characterize suspicious ovarian cancer using Radon-transformed nonlinear features. The obtained dimension of the extracted features is reduced using Relief-F feature selection method. In this study, we have employed the fuzzy forest-based ensemble classifier in contrast to the known crisp rule-based classifiers. The proposed method is evaluated using 469 (non-suspicious: 238, suspicious: 231) subjects and achieved a maximum 80.60 ± 0.5% accuracy, 81.40% sensitivity, 76.30% specificity with fuzzy forest, an ensemble fuzzy classifier using thirty-nine features. The proposed method is robust and reproducible as it uses maximum number subjects (469) as compared to state-of-the-art techniques. Hence, it can be used as an assisting tool by gynecologists during their routine screening.
format Article
author Acharya, U. Rajendra
Akter, Ayesha
Chowriappa, Pradeep
Dua, Sumeet
Raghavendra, U.
Koh, Joel E. W.
Tan, Jen Hong
Leong, Sook Sam
Vijayananthan, Anushya
Hagiwara, Yuki
Ramli, Marlina Tanty
Ng, Kwan Hoong
author_facet Acharya, U. Rajendra
Akter, Ayesha
Chowriappa, Pradeep
Dua, Sumeet
Raghavendra, U.
Koh, Joel E. W.
Tan, Jen Hong
Leong, Sook Sam
Vijayananthan, Anushya
Hagiwara, Yuki
Ramli, Marlina Tanty
Ng, Kwan Hoong
author_sort Acharya, U. Rajendra
title Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework
title_short Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework
title_full Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework
title_fullStr Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework
title_full_unstemmed Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework
title_sort use of nonlinear features for automated characterization of suspicious ovarian tumors using ultrasound images in fuzzy forest framework
publisher Springer Berlin Heidelberg
publishDate 2018
url http://eprints.um.edu.my/22709/
https://doi.org/10.1007/s40815-018-0456-9
_version_ 1648736188069052416