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

U. Rajendra Acharya, Ayesha Akter, Pradeep Chowriappa, Sumeet Dua, U. Raghavendra, Joel E.W. Koh, Jen Hong Tan, Sook Sam Leong, Anushya Vijayananthan, Yuki Hagiwara, Marlina Tanty Ramli, Kwan Hoong Ng

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)1385-1402
Number of pages18
JournalInternational Journal of Fuzzy Systems
Volume20
Issue number4
DOIs
Publication statusPublished - 01-04-2018

Fingerprint

Ovarian Cancer
Ultrasound Image
Computer aided diagnosis
Tumors
Tumor
Classifiers
Ultrasonics
Ensemble Classifier
Computer-aided Diagnosis
Ultrasonography
Biopsy
Radon
Feature extraction
Screening
Fuzzy Classifier
Anxiety
Mortality
Feature Selection
Specificity
Efficacy

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Artificial Intelligence

Cite this

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. In: International Journal of Fuzzy Systems. 2018 ; Vol. 20, No. 4. pp. 1385-1402.
@article{11b347dfbb2c4ce5aa4a55db93654113,
title = "Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework",
abstract = "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.",
author = "Acharya, {U. Rajendra} and Ayesha Akter and Pradeep Chowriappa and Sumeet Dua and U. Raghavendra and Koh, {Joel E.W.} and Tan, {Jen Hong} and Leong, {Sook Sam} and Anushya Vijayananthan and Yuki Hagiwara and Ramli, {Marlina Tanty} and Ng, {Kwan Hoong}",
year = "2018",
month = "4",
day = "1",
doi = "10.1007/s40815-018-0456-9",
language = "English",
volume = "20",
pages = "1385--1402",
journal = "International Journal of Fuzzy Systems",
issn = "1562-2479",
publisher = "Chinese Fuzzy Systems Association",
number = "4",

}

Acharya, UR, Akter, A, Chowriappa, P, Dua, S, Raghavendra, U, Koh, JEW, Tan, JH, Leong, SS, Vijayananthan, A, Hagiwara, Y, Ramli, MT & Ng, KH 2018, 'Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework', International Journal of Fuzzy Systems, vol. 20, no. 4, pp. 1385-1402. https://doi.org/10.1007/s40815-018-0456-9

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.

In: International Journal of Fuzzy Systems, Vol. 20, No. 4, 01.04.2018, p. 1385-1402.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Use of Nonlinear Features for Automated Characterization of Suspicious Ovarian Tumors Using Ultrasound Images in Fuzzy Forest Framework

AU - Acharya, U. Rajendra

AU - Akter, Ayesha

AU - Chowriappa, Pradeep

AU - Dua, Sumeet

AU - Raghavendra, U.

AU - Koh, Joel E.W.

AU - Tan, Jen Hong

AU - Leong, Sook Sam

AU - Vijayananthan, Anushya

AU - Hagiwara, Yuki

AU - Ramli, Marlina Tanty

AU - Ng, Kwan Hoong

PY - 2018/4/1

Y1 - 2018/4/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85044289115&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044289115&partnerID=8YFLogxK

U2 - 10.1007/s40815-018-0456-9

DO - 10.1007/s40815-018-0456-9

M3 - Article

AN - SCOPUS:85044289115

VL - 20

SP - 1385

EP - 1402

JO - International Journal of Fuzzy Systems

JF - International Journal of Fuzzy Systems

SN - 1562-2479

IS - 4

ER -