Prediction of Different Eye Diseases Based on Fundus Photography via Deep Transfer Learning
With recent advancements in machine learning, especially in deep learning, the prediction of eye diseases based on fundus photography using deep convolutional neural networks (DCNNs) has attracted great attention. However, studies focusing on identifying the right disease among several candidates, w...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/10/23/5481 |
| _version_ | 1797507672744919040 |
|---|---|
| author | Chen Guo Minzhong Yu Jing Li |
| author_facet | Chen Guo Minzhong Yu Jing Li |
| author_sort | Chen Guo |
| collection | DOAJ |
| description | With recent advancements in machine learning, especially in deep learning, the prediction of eye diseases based on fundus photography using deep convolutional neural networks (DCNNs) has attracted great attention. However, studies focusing on identifying the right disease among several candidates, which is a better approximation of clinical diagnosis in practice comparing with the case that aims to distinguish one particular eye disease from normal controls, are limited. The performance of existing algorithms for multi-class classification of fundus images is at most mediocre. Moreover, in many studies consisting of different eye diseases, labeled images are quite limited mainly due to privacy concern of patients. In this case, it is infeasible to train huge DCNNs, which usually have millions of parameters. To address these challenges, we propose to utilize a lightweight deep learning architecture called MobileNetV2 and transfer learning to distinguish four common eye diseases, including Glaucoma, Maculopathy, Pathological Myopia, and Retinitis Pigmentosa, from normal controls using a small training data. We also apply a visualization approach to highlight the loci that are most related to the disease labels to make the model more explainable. The highlighted area chosen by the algorithm itself may give some hints for further fundus image studies. Our experimental results show that our system achieves an average accuracy of 96.2%, sensitivity of 90.4%, and specificity of 97.6% on the test data via five independent runs, and outperforms two other deep learning-based algorithms both in terms of accuracy and efficiency. |
| first_indexed | 2024-03-10T04:52:47Z |
| format | Article |
| id | doaj.art-e1d56cb09eda420c99aad0ef5548758a |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-10T04:52:47Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-e1d56cb09eda420c99aad0ef5548758a2023-11-23T02:34:51ZengMDPI AGJournal of Clinical Medicine2077-03832021-11-011023548110.3390/jcm10235481Prediction of Different Eye Diseases Based on Fundus Photography via Deep Transfer LearningChen Guo0Minzhong Yu1Jing Li2Department of Computer and Data Sciences, Case Western Reserve University, Cleveland, OH 44106, USADepartment of Ophthalmology, University Hospitals, Case Western Reserve University, Cleveland, OH 44101, USADepartment of Computer and Data Sciences, Case Western Reserve University, Cleveland, OH 44106, USAWith recent advancements in machine learning, especially in deep learning, the prediction of eye diseases based on fundus photography using deep convolutional neural networks (DCNNs) has attracted great attention. However, studies focusing on identifying the right disease among several candidates, which is a better approximation of clinical diagnosis in practice comparing with the case that aims to distinguish one particular eye disease from normal controls, are limited. The performance of existing algorithms for multi-class classification of fundus images is at most mediocre. Moreover, in many studies consisting of different eye diseases, labeled images are quite limited mainly due to privacy concern of patients. In this case, it is infeasible to train huge DCNNs, which usually have millions of parameters. To address these challenges, we propose to utilize a lightweight deep learning architecture called MobileNetV2 and transfer learning to distinguish four common eye diseases, including Glaucoma, Maculopathy, Pathological Myopia, and Retinitis Pigmentosa, from normal controls using a small training data. We also apply a visualization approach to highlight the loci that are most related to the disease labels to make the model more explainable. The highlighted area chosen by the algorithm itself may give some hints for further fundus image studies. Our experimental results show that our system achieves an average accuracy of 96.2%, sensitivity of 90.4%, and specificity of 97.6% on the test data via five independent runs, and outperforms two other deep learning-based algorithms both in terms of accuracy and efficiency.https://www.mdpi.com/2077-0383/10/23/5481eye diseasesmulti-class classificationdeep learningtransfer learning |
| spellingShingle | Chen Guo Minzhong Yu Jing Li Prediction of Different Eye Diseases Based on Fundus Photography via Deep Transfer Learning Journal of Clinical Medicine eye diseases multi-class classification deep learning transfer learning |
| title | Prediction of Different Eye Diseases Based on Fundus Photography via Deep Transfer Learning |
| title_full | Prediction of Different Eye Diseases Based on Fundus Photography via Deep Transfer Learning |
| title_fullStr | Prediction of Different Eye Diseases Based on Fundus Photography via Deep Transfer Learning |
| title_full_unstemmed | Prediction of Different Eye Diseases Based on Fundus Photography via Deep Transfer Learning |
| title_short | Prediction of Different Eye Diseases Based on Fundus Photography via Deep Transfer Learning |
| title_sort | prediction of different eye diseases based on fundus photography via deep transfer learning |
| topic | eye diseases multi-class classification deep learning transfer learning |
| url | https://www.mdpi.com/2077-0383/10/23/5481 |
| work_keys_str_mv | AT chenguo predictionofdifferenteyediseasesbasedonfundusphotographyviadeeptransferlearning AT minzhongyu predictionofdifferenteyediseasesbasedonfundusphotographyviadeeptransferlearning AT jingli predictionofdifferenteyediseasesbasedonfundusphotographyviadeeptransferlearning |