Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants
Retinopathy of prematurity (ROP) is a disease that can cause blindness in premature infants. It is characterized by immature vascular growth of the retinal blood vessels. However, early detection and treatment of ROP can significantly improve the visual acuity of high-risk patients. Thus, early diag...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/9/9/1444 |
| _version_ | 1797416706269773824 |
|---|---|
| author | Yo-Ping Huang Spandana Vadloori Hung-Chi Chu Eugene Yu-Chuan Kang Wei-Chi Wu Shunji Kusaka Yoko Fukushima |
| author_facet | Yo-Ping Huang Spandana Vadloori Hung-Chi Chu Eugene Yu-Chuan Kang Wei-Chi Wu Shunji Kusaka Yoko Fukushima |
| author_sort | Yo-Ping Huang |
| collection | DOAJ |
| description | Retinopathy of prematurity (ROP) is a disease that can cause blindness in premature infants. It is characterized by immature vascular growth of the retinal blood vessels. However, early detection and treatment of ROP can significantly improve the visual acuity of high-risk patients. Thus, early diagnosis of ROP is crucial in preventing visual impairment. However, several patients refrain from treatment owing to the lack of medical expertise in diagnosing the disease; this is especially problematic considering that the number of ROP cases is on the rise. To this end, we applied transfer learning to five deep neural network architectures for identifying ROP in preterm infants. Our results showed that the VGG19 model outperformed the other models in determining whether a preterm infant has ROP, with 96% accuracy, 96.6% sensitivity, and 95.2% specificity. We also classified the severity of the disease; the VGG19 model showed 98.82% accuracy in predicting the severity of the disease with a sensitivity and specificity of 100% and 98.41%, respectively. We performed 5-fold cross-validation on the datasets to validate the reliability of the VGG19 model and found that the VGG19 model exhibited high accuracy in predicting ROP. These findings could help promote the development of computer-aided diagnosis. |
| first_indexed | 2024-03-09T06:08:01Z |
| format | Article |
| id | doaj.art-2c76e89f1f2f4dd8b8eee7bbe4f65968 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T06:08:01Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-2c76e89f1f2f4dd8b8eee7bbe4f659682023-12-03T12:01:33ZengMDPI AGElectronics2079-92922020-09-0199144410.3390/electronics9091444Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm InfantsYo-Ping Huang0Spandana Vadloori1Hung-Chi Chu2Eugene Yu-Chuan Kang3Wei-Chi Wu4Shunji Kusaka5Yoko Fukushima6Department of Electrical Engineering, National Taipei University of Technology, Taipei 10608, TaiwanDepartment of Electrical Engineering, National Taipei University of Technology, Taipei 10608, TaiwanDepartment of Information and Communication Engineering, Chaoyang University of Technology, Taichung 41349, TaiwanDepartment of Ophthalmology, Chang Gung Memorial Hospital, Linkou 33305, TaiwanDepartment of Ophthalmology, Chang Gung Memorial Hospital, Linkou 33305, TaiwanDepartment of Ophthalmology, Faculty of Medicine, Kindai University, Osaka 577-8502, JapanDepartment of Ophthalmology, Osaka University, Osaka 565-0871, JapanRetinopathy of prematurity (ROP) is a disease that can cause blindness in premature infants. It is characterized by immature vascular growth of the retinal blood vessels. However, early detection and treatment of ROP can significantly improve the visual acuity of high-risk patients. Thus, early diagnosis of ROP is crucial in preventing visual impairment. However, several patients refrain from treatment owing to the lack of medical expertise in diagnosing the disease; this is especially problematic considering that the number of ROP cases is on the rise. To this end, we applied transfer learning to five deep neural network architectures for identifying ROP in preterm infants. Our results showed that the VGG19 model outperformed the other models in determining whether a preterm infant has ROP, with 96% accuracy, 96.6% sensitivity, and 95.2% specificity. We also classified the severity of the disease; the VGG19 model showed 98.82% accuracy in predicting the severity of the disease with a sensitivity and specificity of 100% and 98.41%, respectively. We performed 5-fold cross-validation on the datasets to validate the reliability of the VGG19 model and found that the VGG19 model exhibited high accuracy in predicting ROP. These findings could help promote the development of computer-aided diagnosis.https://www.mdpi.com/2079-9292/9/9/1444deep neural networkstransfer learningretinopathy of prematurityretinal fundus images |
| spellingShingle | Yo-Ping Huang Spandana Vadloori Hung-Chi Chu Eugene Yu-Chuan Kang Wei-Chi Wu Shunji Kusaka Yoko Fukushima Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants Electronics deep neural networks transfer learning retinopathy of prematurity retinal fundus images |
| title | Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants |
| title_full | Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants |
| title_fullStr | Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants |
| title_full_unstemmed | Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants |
| title_short | Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants |
| title_sort | deep learning models for automated diagnosis of retinopathy of prematurity in preterm infants |
| topic | deep neural networks transfer learning retinopathy of prematurity retinal fundus images |
| url | https://www.mdpi.com/2079-9292/9/9/1444 |
| work_keys_str_mv | AT yopinghuang deeplearningmodelsforautomateddiagnosisofretinopathyofprematurityinpreterminfants AT spandanavadloori deeplearningmodelsforautomateddiagnosisofretinopathyofprematurityinpreterminfants AT hungchichu deeplearningmodelsforautomateddiagnosisofretinopathyofprematurityinpreterminfants AT eugeneyuchuankang deeplearningmodelsforautomateddiagnosisofretinopathyofprematurityinpreterminfants AT weichiwu deeplearningmodelsforautomateddiagnosisofretinopathyofprematurityinpreterminfants AT shunjikusaka deeplearningmodelsforautomateddiagnosisofretinopathyofprematurityinpreterminfants AT yokofukushima deeplearningmodelsforautomateddiagnosisofretinopathyofprematurityinpreterminfants |