Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques

Japan Eye Genetics Consortium

Research output: Contribution to journalArticle

Abstract

Purpose. To illustrate a data-driven deep learning approach to predicting the gene responsible for the inherited retinal disorder (IRD) in macular dystrophy caused by ABCA4 and RP1L1 gene aberration in comparison with retinitis pigmentosa caused by EYS gene aberration and normal subjects. Methods. Seventy-five subjects with IRD or no ocular diseases have been ascertained from the database of Japan Eye Genetics Consortium; 10 ABCA4 retinopathy, 20 RP1L1 retinopathy, 28 EYS retinopathy, and 17 normal patients/subjects. Horizontal/vertical cross-sectional scans of optical coherence tomography (SD-OCT) at the central fovea were cropped/adjusted to a resolution of 400 pixels/inch with a size of 750 × 500 pix 2 for learning. Subjects were randomly split following a 3: 1 ratio into training and test sets. The commercially available learning tool, Medic mind was applied to this four-class classification program. The classification accuracy, sensitivity, and specificity were calculated during the learning process. This process was repeated four times with random assignment to training and test sets to control for selection bias. For each training/testing process, the classification accuracy was calculated per gene category. Results. A total of 178 images from 75 subjects were included in this study. The mean training accuracy was 98.5%, ranging from 90.6 to 100.0. The mean overall test accuracy was 90.9% (82.0-97.6). The mean test accuracy per gene category was 100% for ABCA4, 78.0% for RP1L1, 89.8% for EYS, and 93.4% for Normal. Test accuracy of RP1L1 and EYS was not high relative to the training accuracy which suggests overfitting. Conclusion. This study highlighted a novel application of deep neural networks in the prediction of the causative gene in IRD retinopathies from SD-OCT, with a high prediction accuracy. It is anticipated that deep neural networks will be integrated into general screening to support clinical/genetic diagnosis, as well as enrich the clinical education.

Original languageEnglish
Article number1691064
JournalJournal of Ophthalmology
Volume2019
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Optical Coherence Tomography
Learning
Genes
Retinitis Pigmentosa
Eye Diseases
Selection Bias
Macular Degeneration
Japan
Databases
Education
Sensitivity and Specificity

ASJC Scopus subject areas

  • Ophthalmology

Cite this

Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques. / Japan Eye Genetics Consortium.

In: Journal of Ophthalmology, Vol. 2019, 1691064, 01.01.2019.

Research output: Contribution to journalArticle

@article{e26e2956960845f8baaeff86ab71c7fa,
title = "Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques",
abstract = "Purpose. To illustrate a data-driven deep learning approach to predicting the gene responsible for the inherited retinal disorder (IRD) in macular dystrophy caused by ABCA4 and RP1L1 gene aberration in comparison with retinitis pigmentosa caused by EYS gene aberration and normal subjects. Methods. Seventy-five subjects with IRD or no ocular diseases have been ascertained from the database of Japan Eye Genetics Consortium; 10 ABCA4 retinopathy, 20 RP1L1 retinopathy, 28 EYS retinopathy, and 17 normal patients/subjects. Horizontal/vertical cross-sectional scans of optical coherence tomography (SD-OCT) at the central fovea were cropped/adjusted to a resolution of 400 pixels/inch with a size of 750 × 500 pix 2 for learning. Subjects were randomly split following a 3: 1 ratio into training and test sets. The commercially available learning tool, Medic mind was applied to this four-class classification program. The classification accuracy, sensitivity, and specificity were calculated during the learning process. This process was repeated four times with random assignment to training and test sets to control for selection bias. For each training/testing process, the classification accuracy was calculated per gene category. Results. A total of 178 images from 75 subjects were included in this study. The mean training accuracy was 98.5{\%}, ranging from 90.6 to 100.0. The mean overall test accuracy was 90.9{\%} (82.0-97.6). The mean test accuracy per gene category was 100{\%} for ABCA4, 78.0{\%} for RP1L1, 89.8{\%} for EYS, and 93.4{\%} for Normal. Test accuracy of RP1L1 and EYS was not high relative to the training accuracy which suggests overfitting. Conclusion. This study highlighted a novel application of deep neural networks in the prediction of the causative gene in IRD retinopathies from SD-OCT, with a high prediction accuracy. It is anticipated that deep neural networks will be integrated into general screening to support clinical/genetic diagnosis, as well as enrich the clinical education.",
author = "{Japan Eye Genetics Consortium} and Yu Fujinami-Yokokawa and Nikolas Pontikos and Lizhu Yang and Kazushige Tsunoda and Kazutoshi Yoshitake and Takeshi Iwata and Hiroaki Miyata and Kaoru Fujinami",
year = "2019",
month = "1",
day = "1",
doi = "10.1155/2019/1691064",
language = "English",
volume = "2019",
journal = "Journal of Ophthalmology",
issn = "2090-004X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques

AU - Japan Eye Genetics Consortium

AU - Fujinami-Yokokawa, Yu

AU - Pontikos, Nikolas

AU - Yang, Lizhu

AU - Tsunoda, Kazushige

AU - Yoshitake, Kazutoshi

AU - Iwata, Takeshi

AU - Miyata, Hiroaki

AU - Fujinami, Kaoru

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Purpose. To illustrate a data-driven deep learning approach to predicting the gene responsible for the inherited retinal disorder (IRD) in macular dystrophy caused by ABCA4 and RP1L1 gene aberration in comparison with retinitis pigmentosa caused by EYS gene aberration and normal subjects. Methods. Seventy-five subjects with IRD or no ocular diseases have been ascertained from the database of Japan Eye Genetics Consortium; 10 ABCA4 retinopathy, 20 RP1L1 retinopathy, 28 EYS retinopathy, and 17 normal patients/subjects. Horizontal/vertical cross-sectional scans of optical coherence tomography (SD-OCT) at the central fovea were cropped/adjusted to a resolution of 400 pixels/inch with a size of 750 × 500 pix 2 for learning. Subjects were randomly split following a 3: 1 ratio into training and test sets. The commercially available learning tool, Medic mind was applied to this four-class classification program. The classification accuracy, sensitivity, and specificity were calculated during the learning process. This process was repeated four times with random assignment to training and test sets to control for selection bias. For each training/testing process, the classification accuracy was calculated per gene category. Results. A total of 178 images from 75 subjects were included in this study. The mean training accuracy was 98.5%, ranging from 90.6 to 100.0. The mean overall test accuracy was 90.9% (82.0-97.6). The mean test accuracy per gene category was 100% for ABCA4, 78.0% for RP1L1, 89.8% for EYS, and 93.4% for Normal. Test accuracy of RP1L1 and EYS was not high relative to the training accuracy which suggests overfitting. Conclusion. This study highlighted a novel application of deep neural networks in the prediction of the causative gene in IRD retinopathies from SD-OCT, with a high prediction accuracy. It is anticipated that deep neural networks will be integrated into general screening to support clinical/genetic diagnosis, as well as enrich the clinical education.

AB - Purpose. To illustrate a data-driven deep learning approach to predicting the gene responsible for the inherited retinal disorder (IRD) in macular dystrophy caused by ABCA4 and RP1L1 gene aberration in comparison with retinitis pigmentosa caused by EYS gene aberration and normal subjects. Methods. Seventy-five subjects with IRD or no ocular diseases have been ascertained from the database of Japan Eye Genetics Consortium; 10 ABCA4 retinopathy, 20 RP1L1 retinopathy, 28 EYS retinopathy, and 17 normal patients/subjects. Horizontal/vertical cross-sectional scans of optical coherence tomography (SD-OCT) at the central fovea were cropped/adjusted to a resolution of 400 pixels/inch with a size of 750 × 500 pix 2 for learning. Subjects were randomly split following a 3: 1 ratio into training and test sets. The commercially available learning tool, Medic mind was applied to this four-class classification program. The classification accuracy, sensitivity, and specificity were calculated during the learning process. This process was repeated four times with random assignment to training and test sets to control for selection bias. For each training/testing process, the classification accuracy was calculated per gene category. Results. A total of 178 images from 75 subjects were included in this study. The mean training accuracy was 98.5%, ranging from 90.6 to 100.0. The mean overall test accuracy was 90.9% (82.0-97.6). The mean test accuracy per gene category was 100% for ABCA4, 78.0% for RP1L1, 89.8% for EYS, and 93.4% for Normal. Test accuracy of RP1L1 and EYS was not high relative to the training accuracy which suggests overfitting. Conclusion. This study highlighted a novel application of deep neural networks in the prediction of the causative gene in IRD retinopathies from SD-OCT, with a high prediction accuracy. It is anticipated that deep neural networks will be integrated into general screening to support clinical/genetic diagnosis, as well as enrich the clinical education.

UR - http://www.scopus.com/inward/record.url?scp=85065647185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065647185&partnerID=8YFLogxK

U2 - 10.1155/2019/1691064

DO - 10.1155/2019/1691064

M3 - Article

VL - 2019

JO - Journal of Ophthalmology

JF - Journal of Ophthalmology

SN - 2090-004X

M1 - 1691064

ER -