An approach towards automatic detection of toxoplasmosis using fundus images

Adithi Deborah Chakravarthy; Dilanga Abeyrathna; Mahadevan Subramaniam; Parvathi Chundi; Muhammad Sohail Halim; Murat Hasanreisoglu; Yasir J. Sepah; Quan Dong Nguyen

doi:10.1109/BIBE.2019.00134

An approach towards automatic detection of toxoplasmosis using fundus images

Adithi Deborah Chakravarthy, Dilanga Abeyrathna, Mahadevan Subramaniam, Parvathi Chundi, Muhammad Sohail Halim, Murat Hasanreisoglu, Yasir J. Sepah, Quan Dong Nguyen

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Scopus citations

Abstract

Ocular Toxoplasmosis (OT) is a widespread infectious chorioretinal disease whose timely diagnosis and treatment are crucial to prevent potential vision loss. Diagnosing OT is a challenging task ranging from tedious analyses of fundus images of the eye to serological clinical tests. An automated approach using convolutional neural networks (CNNs) towards diagnosing OT by analyzing fundus images is described. Fundus images are segmented to patches using a sliding window and are classified into healthy and unhealthy fundus image patches using a CNN model. An OT lesion heat map of a fundus image is generated from these patches. The heat map and patch features are then combined to develop a dual input hybrid CNN model detecting OT fundus images with high accuracy. The approach was applied to a dataset of fundus images involving OT and normal subjects and was highly effective in identifying fundus images having OT lesions.

Original language	English (US)
Title of host publication	Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	710-717
Number of pages	8
ISBN (Electronic)	9781728146171
DOIs	https://doi.org/10.1109/BIBE.2019.00134
State	Published - Oct 2019
Event	19th International Conference on Bioinformatics and Bioengineering, BIBE 2019 - Athens, Greece Duration: Oct 28 2019 → Oct 30 2019

Publication series

Name	Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019

Conference

Conference	19th International Conference on Bioinformatics and Bioengineering, BIBE 2019
Country/Territory	Greece
City	Athens
Period	10/28/19 → 10/30/19

Keywords

Deep Learning
Medical Imaging
Neural Networks
Ocular Toxoplasmosis

ASJC Scopus subject areas

Information Systems
Biomedical Engineering
Health Informatics

Access to Document

10.1109/BIBE.2019.00134

Cite this

Chakravarthy, A. D., Abeyrathna, D., Subramaniam, M., Chundi, P., Halim, M. S., Hasanreisoglu, M., Sepah, Y. J., & Nguyen, Q. D. (2019). An approach towards automatic detection of toxoplasmosis using fundus images. In Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019 (pp. 710-717). Article 8941984 (Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBE.2019.00134

An approach towards automatic detection of toxoplasmosis using fundus images. / Chakravarthy, Adithi Deborah; Abeyrathna, Dilanga; Subramaniam, Mahadevan et al.
Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 710-717 8941984 (Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chakravarthy, AD, Abeyrathna, D, Subramaniam, M, Chundi, P, Halim, MS, Hasanreisoglu, M, Sepah, YJ & Nguyen, QD 2019, An approach towards automatic detection of toxoplasmosis using fundus images. in Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019., 8941984, Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019, Institute of Electrical and Electronics Engineers Inc., pp. 710-717, 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019, Athens, Greece, 10/28/19. https://doi.org/10.1109/BIBE.2019.00134

Chakravarthy AD, Abeyrathna D, Subramaniam M, Chundi P, Halim MS, Hasanreisoglu M et al. An approach towards automatic detection of toxoplasmosis using fundus images. In Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 710-717. 8941984. (Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019). doi: 10.1109/BIBE.2019.00134

Chakravarthy, Adithi Deborah ; Abeyrathna, Dilanga ; Subramaniam, Mahadevan et al. / An approach towards automatic detection of toxoplasmosis using fundus images. Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 710-717 (Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019).

@inproceedings{d92b993e2302445b88ed2cbc6d04e26e,

title = "An approach towards automatic detection of toxoplasmosis using fundus images",

abstract = "Ocular Toxoplasmosis (OT) is a widespread infectious chorioretinal disease whose timely diagnosis and treatment are crucial to prevent potential vision loss. Diagnosing OT is a challenging task ranging from tedious analyses of fundus images of the eye to serological clinical tests. An automated approach using convolutional neural networks (CNNs) towards diagnosing OT by analyzing fundus images is described. Fundus images are segmented to patches using a sliding window and are classified into healthy and unhealthy fundus image patches using a CNN model. An OT lesion heat map of a fundus image is generated from these patches. The heat map and patch features are then combined to develop a dual input hybrid CNN model detecting OT fundus images with high accuracy. The approach was applied to a dataset of fundus images involving OT and normal subjects and was highly effective in identifying fundus images having OT lesions.",

keywords = "Deep Learning, Medical Imaging, Neural Networks, Ocular Toxoplasmosis",

author = "Chakravarthy, {Adithi Deborah} and Dilanga Abeyrathna and Mahadevan Subramaniam and Parvathi Chundi and Halim, {Muhammad Sohail} and Murat Hasanreisoglu and Sepah, {Yasir J.} and Nguyen, {Quan Dong}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019 ; Conference date: 28-10-2019 Through 30-10-2019",

year = "2019",

month = oct,

doi = "10.1109/BIBE.2019.00134",

language = "English (US)",

series = "Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "710--717",

booktitle = "Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019",

}

TY - GEN

T1 - An approach towards automatic detection of toxoplasmosis using fundus images

AU - Chakravarthy, Adithi Deborah

AU - Abeyrathna, Dilanga

AU - Subramaniam, Mahadevan

AU - Chundi, Parvathi

AU - Halim, Muhammad Sohail

AU - Hasanreisoglu, Murat

AU - Sepah, Yasir J.

AU - Nguyen, Quan Dong

PY - 2019/10

Y1 - 2019/10

N2 - Ocular Toxoplasmosis (OT) is a widespread infectious chorioretinal disease whose timely diagnosis and treatment are crucial to prevent potential vision loss. Diagnosing OT is a challenging task ranging from tedious analyses of fundus images of the eye to serological clinical tests. An automated approach using convolutional neural networks (CNNs) towards diagnosing OT by analyzing fundus images is described. Fundus images are segmented to patches using a sliding window and are classified into healthy and unhealthy fundus image patches using a CNN model. An OT lesion heat map of a fundus image is generated from these patches. The heat map and patch features are then combined to develop a dual input hybrid CNN model detecting OT fundus images with high accuracy. The approach was applied to a dataset of fundus images involving OT and normal subjects and was highly effective in identifying fundus images having OT lesions.

AB - Ocular Toxoplasmosis (OT) is a widespread infectious chorioretinal disease whose timely diagnosis and treatment are crucial to prevent potential vision loss. Diagnosing OT is a challenging task ranging from tedious analyses of fundus images of the eye to serological clinical tests. An automated approach using convolutional neural networks (CNNs) towards diagnosing OT by analyzing fundus images is described. Fundus images are segmented to patches using a sliding window and are classified into healthy and unhealthy fundus image patches using a CNN model. An OT lesion heat map of a fundus image is generated from these patches. The heat map and patch features are then combined to develop a dual input hybrid CNN model detecting OT fundus images with high accuracy. The approach was applied to a dataset of fundus images involving OT and normal subjects and was highly effective in identifying fundus images having OT lesions.

KW - Deep Learning

KW - Medical Imaging

KW - Neural Networks

KW - Ocular Toxoplasmosis

UR - http://www.scopus.com/inward/record.url?scp=85078030948&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85078030948&partnerID=8YFLogxK

U2 - 10.1109/BIBE.2019.00134

DO - 10.1109/BIBE.2019.00134

M3 - Conference contribution

AN - SCOPUS:85078030948

T3 - Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019

SP - 710

EP - 717

BT - Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019

Y2 - 28 October 2019 through 30 October 2019

ER -

An approach towards automatic detection of toxoplasmosis using fundus images

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this