Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques
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. S...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Journal of Ophthalmology |
| Online Access: | http://dx.doi.org/10.1155/2019/1691064 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832564792400805888 |
|---|---|
| author | Yu Fujinami-Yokokawa Nikolas Pontikos Lizhu Yang Kazushige Tsunoda Kazutoshi Yoshitake Takeshi Iwata Hiroaki Miyata Kaoru Fujinami on behalf of Japan Eye Genetics Consortium |
| author_facet | Yu Fujinami-Yokokawa Nikolas Pontikos Lizhu Yang Kazushige Tsunoda Kazutoshi Yoshitake Takeshi Iwata Hiroaki Miyata Kaoru Fujinami on behalf of Japan Eye Genetics Consortium |
| author_sort | Yu Fujinami-Yokokawa |
| collection | DOAJ |
| description | 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 pix2 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. |
| format | Article |
| id | doaj-art-fe92b4a47d6e4e8792d1798179935582 |
| institution | Kabale University |
| issn | 2090-004X 2090-0058 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Ophthalmology |
| spelling | doaj-art-fe92b4a47d6e4e8792d17981799355822025-02-03T01:10:16ZengWileyJournal of Ophthalmology2090-004X2090-00582019-01-01201910.1155/2019/16910641691064Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning TechniquesYu Fujinami-Yokokawa0Nikolas Pontikos1Lizhu Yang2Kazushige Tsunoda3Kazutoshi Yoshitake4Takeshi Iwata5Hiroaki Miyata6Kaoru Fujinami7on behalf of Japan Eye Genetics Consortium8Laboratory of Visual Physiology, Division of Vision Research, National Institute of Sensory Organs, National Hospital Organization Tokyo Medical Center, Tokyo 152-8902, JapanLaboratory of Visual Physiology, Division of Vision Research, National Institute of Sensory Organs, National Hospital Organization Tokyo Medical Center, Tokyo 152-8902, JapanLaboratory of Visual Physiology, Division of Vision Research, National Institute of Sensory Organs, National Hospital Organization Tokyo Medical Center, Tokyo 152-8902, JapanLaboratory of Visual Physiology, Division of Vision Research, National Institute of Sensory Organs, National Hospital Organization Tokyo Medical Center, Tokyo 152-8902, JapanDivision of Molecular and Cellular Biology, National Institute of Sensory Organs, National Tokyo Medical Center, Tokyo 152-8902, JapanDivision of Molecular and Cellular Biology, National Institute of Sensory Organs, National Tokyo Medical Center, Tokyo 152-8902, JapanGraduate School of Health Management, Keio University, Tokyo 160-0016, JapanLaboratory of Visual Physiology, Division of Vision Research, National Institute of Sensory Organs, National Hospital Organization Tokyo Medical Center, Tokyo 152-8902, JapanLaboratory of Visual Physiology, Division of Vision Research, National Institute of Sensory Organs, National Hospital Organization Tokyo Medical Center, Tokyo 152-8902, JapanPurpose. 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 pix2 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.http://dx.doi.org/10.1155/2019/1691064 |
| spellingShingle | Yu Fujinami-Yokokawa Nikolas Pontikos Lizhu Yang Kazushige Tsunoda Kazutoshi Yoshitake Takeshi Iwata Hiroaki Miyata Kaoru Fujinami on behalf of Japan Eye Genetics Consortium Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques Journal of Ophthalmology |
| title | Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques |
| title_full | Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques |
| title_fullStr | Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques |
| title_full_unstemmed | Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques |
| title_short | Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques |
| title_sort | prediction of causative genes in inherited retinal disorders from spectral domain optical coherence tomography utilizing deep learning techniques |
| url | http://dx.doi.org/10.1155/2019/1691064 |
| work_keys_str_mv | AT yufujinamiyokokawa predictionofcausativegenesininheritedretinaldisordersfromspectraldomainopticalcoherencetomographyutilizingdeeplearningtechniques AT nikolaspontikos predictionofcausativegenesininheritedretinaldisordersfromspectraldomainopticalcoherencetomographyutilizingdeeplearningtechniques AT lizhuyang predictionofcausativegenesininheritedretinaldisordersfromspectraldomainopticalcoherencetomographyutilizingdeeplearningtechniques AT kazushigetsunoda predictionofcausativegenesininheritedretinaldisordersfromspectraldomainopticalcoherencetomographyutilizingdeeplearningtechniques AT kazutoshiyoshitake predictionofcausativegenesininheritedretinaldisordersfromspectraldomainopticalcoherencetomographyutilizingdeeplearningtechniques AT takeshiiwata predictionofcausativegenesininheritedretinaldisordersfromspectraldomainopticalcoherencetomographyutilizingdeeplearningtechniques AT hiroakimiyata predictionofcausativegenesininheritedretinaldisordersfromspectraldomainopticalcoherencetomographyutilizingdeeplearningtechniques AT kaorufujinami predictionofcausativegenesininheritedretinaldisordersfromspectraldomainopticalcoherencetomographyutilizingdeeplearningtechniques AT onbehalfofjapaneyegeneticsconsortium predictionofcausativegenesininheritedretinaldisordersfromspectraldomainopticalcoherencetomographyutilizingdeeplearningtechniques |