Global weighted LBP based entropy features for the assessment of pulmonary hypertension

Anjan Gudigar, U. Raghavendra, Tom Devasia, Krishnananda Nayak, Sheik Mohammed Danish, Gautam Kamath, Jyothi Samanth, Umesh M. Pai, Vidya Nayak, Ru San Tan, Edward J. Ciaccio, U. Rajendra Acharya

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Pulmonary hypertension (PH) is characterized by elevated pulmonary arterial pressure. Echocardiography, or cardiac ultrasound, is a helpful imaging tool to screen for PH. However, expert interpretation is required for successful screening. Development of a more automated method for diagnosis of PH would be useful to minimize error, thereby improving patient health. This task is challenging and the literature pertaining to the problem is still nascent. In this paper, we propose a computer aided diagnosis (CAD) tool, using ultrasound images, to expedite the screening of PH. Textural components play a significant role in ultrasound imaging for the efficient identification of PH. The extraction of such features is accomplished by computing several entropy measurements over a globally weighted local binary pattern (LBP). Thereafter, the blend of ranked maximum and fuzzy entropy features are input to a support vector machine, resulting in a maximum accuracy of approximately 92%. A comparison with variants indicates improved performance of the proposed globally weighted LBP.

Original languageEnglish
Pages (from-to)35-41
Number of pages7
JournalPattern Recognition Letters
Volume125
DOIs
Publication statusPublished - 01-07-2019

Fingerprint

Entropy
Ultrasonics
Screening
Imaging techniques
Echocardiography
Computer aided diagnosis
Support vector machines
Health

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Gudigar, Anjan ; Raghavendra, U. ; Devasia, Tom ; Nayak, Krishnananda ; Danish, Sheik Mohammed ; Kamath, Gautam ; Samanth, Jyothi ; Pai, Umesh M. ; Nayak, Vidya ; Tan, Ru San ; Ciaccio, Edward J. ; Acharya, U. Rajendra. / Global weighted LBP based entropy features for the assessment of pulmonary hypertension. In: Pattern Recognition Letters. 2019 ; Vol. 125. pp. 35-41.
@article{8d3988b141944a2aa9f92b9a6745804f,
title = "Global weighted LBP based entropy features for the assessment of pulmonary hypertension",
abstract = "Pulmonary hypertension (PH) is characterized by elevated pulmonary arterial pressure. Echocardiography, or cardiac ultrasound, is a helpful imaging tool to screen for PH. However, expert interpretation is required for successful screening. Development of a more automated method for diagnosis of PH would be useful to minimize error, thereby improving patient health. This task is challenging and the literature pertaining to the problem is still nascent. In this paper, we propose a computer aided diagnosis (CAD) tool, using ultrasound images, to expedite the screening of PH. Textural components play a significant role in ultrasound imaging for the efficient identification of PH. The extraction of such features is accomplished by computing several entropy measurements over a globally weighted local binary pattern (LBP). Thereafter, the blend of ranked maximum and fuzzy entropy features are input to a support vector machine, resulting in a maximum accuracy of approximately 92{\%}. A comparison with variants indicates improved performance of the proposed globally weighted LBP.",
author = "Anjan Gudigar and U. Raghavendra and Tom Devasia and Krishnananda Nayak and Danish, {Sheik Mohammed} and Gautam Kamath and Jyothi Samanth and Pai, {Umesh M.} and Vidya Nayak and Tan, {Ru San} and Ciaccio, {Edward J.} and Acharya, {U. Rajendra}",
year = "2019",
month = "7",
day = "1",
doi = "10.1016/j.patrec.2019.03.027",
language = "English",
volume = "125",
pages = "35--41",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",

}

Global weighted LBP based entropy features for the assessment of pulmonary hypertension. / Gudigar, Anjan; Raghavendra, U.; Devasia, Tom; Nayak, Krishnananda; Danish, Sheik Mohammed; Kamath, Gautam; Samanth, Jyothi; Pai, Umesh M.; Nayak, Vidya; Tan, Ru San; Ciaccio, Edward J.; Acharya, U. Rajendra.

In: Pattern Recognition Letters, Vol. 125, 01.07.2019, p. 35-41.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Global weighted LBP based entropy features for the assessment of pulmonary hypertension

AU - Gudigar, Anjan

AU - Raghavendra, U.

AU - Devasia, Tom

AU - Nayak, Krishnananda

AU - Danish, Sheik Mohammed

AU - Kamath, Gautam

AU - Samanth, Jyothi

AU - Pai, Umesh M.

AU - Nayak, Vidya

AU - Tan, Ru San

AU - Ciaccio, Edward J.

AU - Acharya, U. Rajendra

PY - 2019/7/1

Y1 - 2019/7/1

N2 - Pulmonary hypertension (PH) is characterized by elevated pulmonary arterial pressure. Echocardiography, or cardiac ultrasound, is a helpful imaging tool to screen for PH. However, expert interpretation is required for successful screening. Development of a more automated method for diagnosis of PH would be useful to minimize error, thereby improving patient health. This task is challenging and the literature pertaining to the problem is still nascent. In this paper, we propose a computer aided diagnosis (CAD) tool, using ultrasound images, to expedite the screening of PH. Textural components play a significant role in ultrasound imaging for the efficient identification of PH. The extraction of such features is accomplished by computing several entropy measurements over a globally weighted local binary pattern (LBP). Thereafter, the blend of ranked maximum and fuzzy entropy features are input to a support vector machine, resulting in a maximum accuracy of approximately 92%. A comparison with variants indicates improved performance of the proposed globally weighted LBP.

AB - Pulmonary hypertension (PH) is characterized by elevated pulmonary arterial pressure. Echocardiography, or cardiac ultrasound, is a helpful imaging tool to screen for PH. However, expert interpretation is required for successful screening. Development of a more automated method for diagnosis of PH would be useful to minimize error, thereby improving patient health. This task is challenging and the literature pertaining to the problem is still nascent. In this paper, we propose a computer aided diagnosis (CAD) tool, using ultrasound images, to expedite the screening of PH. Textural components play a significant role in ultrasound imaging for the efficient identification of PH. The extraction of such features is accomplished by computing several entropy measurements over a globally weighted local binary pattern (LBP). Thereafter, the blend of ranked maximum and fuzzy entropy features are input to a support vector machine, resulting in a maximum accuracy of approximately 92%. A comparison with variants indicates improved performance of the proposed globally weighted LBP.

UR - http://www.scopus.com/inward/record.url?scp=85063863166&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063863166&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2019.03.027

DO - 10.1016/j.patrec.2019.03.027

M3 - Article

VL - 125

SP - 35

EP - 41

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -