Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images

U. Raghavendra, Anjan Gudigar, M. Maithri, Arkadiusz Gertych, Kristen M. Meiburger, Chai Hong Yeong, Chakri Madla, Pailin Kongmebhol, Filippo Molinari, Kwan Hoong Ng, U. Rajendra Acharya

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Ultrasound imaging is one of the most common visualizing tools used by radiologists to identify the location of thyroid nodules. However, visual assessment of nodules is difficult and often affected by inter- and intra-observer variabilities. Thus, a computer-aided diagnosis (CAD) system can be helpful to cross-verify the severity of nodules. This paper proposes a new CAD system to characterize thyroid nodules using optimized multi-level elongated quinary patterns. In this study, higher order spectral (HOS) entropy features extracted from these patterns appropriately distinguished benign and malignant nodules under particle swarm optimization (PSO) and support vector machine (SVM) frameworks. Our CAD algorithm achieved a maximum accuracy of 97.71% and 97.01% in private and public datasets respectively. The evaluation of this CAD system on both private and public datasets confirmed its effectiveness as a secondary tool in assisting radiological findings.

Original languageEnglish
Pages (from-to)55-62
Number of pages8
JournalComputers in Biology and Medicine
Volume95
DOIs
Publication statusPublished - 01-04-2018

Fingerprint

Computer aided diagnosis
Thyroid Nodule
Ultrasonics
Observer Variation
Entropy
Particle swarm optimization (PSO)
Support vector machines
Ultrasonography
Imaging techniques
Datasets

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Health Informatics

Cite this

Raghavendra, U. ; Gudigar, Anjan ; Maithri, M. ; Gertych, Arkadiusz ; Meiburger, Kristen M. ; Yeong, Chai Hong ; Madla, Chakri ; Kongmebhol, Pailin ; Molinari, Filippo ; Ng, Kwan Hoong ; Acharya, U. Rajendra. / Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images. In: Computers in Biology and Medicine. 2018 ; Vol. 95. pp. 55-62.
@article{3b3116713c3c40f1a57887b706a1f732,
title = "Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images",
abstract = "Ultrasound imaging is one of the most common visualizing tools used by radiologists to identify the location of thyroid nodules. However, visual assessment of nodules is difficult and often affected by inter- and intra-observer variabilities. Thus, a computer-aided diagnosis (CAD) system can be helpful to cross-verify the severity of nodules. This paper proposes a new CAD system to characterize thyroid nodules using optimized multi-level elongated quinary patterns. In this study, higher order spectral (HOS) entropy features extracted from these patterns appropriately distinguished benign and malignant nodules under particle swarm optimization (PSO) and support vector machine (SVM) frameworks. Our CAD algorithm achieved a maximum accuracy of 97.71{\%} and 97.01{\%} in private and public datasets respectively. The evaluation of this CAD system on both private and public datasets confirmed its effectiveness as a secondary tool in assisting radiological findings.",
author = "U. Raghavendra and Anjan Gudigar and M. Maithri and Arkadiusz Gertych and Meiburger, {Kristen M.} and Yeong, {Chai Hong} and Chakri Madla and Pailin Kongmebhol and Filippo Molinari and Ng, {Kwan Hoong} and Acharya, {U. Rajendra}",
year = "2018",
month = "4",
day = "1",
doi = "10.1016/j.compbiomed.2018.02.002",
language = "English",
volume = "95",
pages = "55--62",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

Raghavendra, U, Gudigar, A, Maithri, M, Gertych, A, Meiburger, KM, Yeong, CH, Madla, C, Kongmebhol, P, Molinari, F, Ng, KH & Acharya, UR 2018, 'Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images', Computers in Biology and Medicine, vol. 95, pp. 55-62. https://doi.org/10.1016/j.compbiomed.2018.02.002

Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images. / Raghavendra, U.; Gudigar, Anjan; Maithri, M.; Gertych, Arkadiusz; Meiburger, Kristen M.; Yeong, Chai Hong; Madla, Chakri; Kongmebhol, Pailin; Molinari, Filippo; Ng, Kwan Hoong; Acharya, U. Rajendra.

In: Computers in Biology and Medicine, Vol. 95, 01.04.2018, p. 55-62.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images

AU - Raghavendra, U.

AU - Gudigar, Anjan

AU - Maithri, M.

AU - Gertych, Arkadiusz

AU - Meiburger, Kristen M.

AU - Yeong, Chai Hong

AU - Madla, Chakri

AU - Kongmebhol, Pailin

AU - Molinari, Filippo

AU - Ng, Kwan Hoong

AU - Acharya, U. Rajendra

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Ultrasound imaging is one of the most common visualizing tools used by radiologists to identify the location of thyroid nodules. However, visual assessment of nodules is difficult and often affected by inter- and intra-observer variabilities. Thus, a computer-aided diagnosis (CAD) system can be helpful to cross-verify the severity of nodules. This paper proposes a new CAD system to characterize thyroid nodules using optimized multi-level elongated quinary patterns. In this study, higher order spectral (HOS) entropy features extracted from these patterns appropriately distinguished benign and malignant nodules under particle swarm optimization (PSO) and support vector machine (SVM) frameworks. Our CAD algorithm achieved a maximum accuracy of 97.71% and 97.01% in private and public datasets respectively. The evaluation of this CAD system on both private and public datasets confirmed its effectiveness as a secondary tool in assisting radiological findings.

AB - Ultrasound imaging is one of the most common visualizing tools used by radiologists to identify the location of thyroid nodules. However, visual assessment of nodules is difficult and often affected by inter- and intra-observer variabilities. Thus, a computer-aided diagnosis (CAD) system can be helpful to cross-verify the severity of nodules. This paper proposes a new CAD system to characterize thyroid nodules using optimized multi-level elongated quinary patterns. In this study, higher order spectral (HOS) entropy features extracted from these patterns appropriately distinguished benign and malignant nodules under particle swarm optimization (PSO) and support vector machine (SVM) frameworks. Our CAD algorithm achieved a maximum accuracy of 97.71% and 97.01% in private and public datasets respectively. The evaluation of this CAD system on both private and public datasets confirmed its effectiveness as a secondary tool in assisting radiological findings.

UR - http://www.scopus.com/inward/record.url?scp=85042178227&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042178227&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2018.02.002

DO - 10.1016/j.compbiomed.2018.02.002

M3 - Article

AN - SCOPUS:85042178227

VL - 95

SP - 55

EP - 62

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -