Multimodal Deep Learning Model of Predicting Future Visual Field for Glaucoma Patients
Glaucoma is one of the most common reasons for blindness worldwide, especially in elderly people. Glaucoma can be monitored using visual field (VF) tests. Therefore, predicting the future VF to monitor progression of glaucoma is important. In this paper, we proposed a deep learning model to predict...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10050537/ |
| _version_ | 1811161981318594560 |
|---|---|
| author | Quang T. M. Pham Jong Chul Han Do Young Park Jitae Shin |
| author_facet | Quang T. M. Pham Jong Chul Han Do Young Park Jitae Shin |
| author_sort | Quang T. M. Pham |
| collection | DOAJ |
| description | Glaucoma is one of the most common reasons for blindness worldwide, especially in elderly people. Glaucoma can be monitored using visual field (VF) tests. Therefore, predicting the future VF to monitor progression of glaucoma is important. In this paper, we proposed a deep learning model to predict future VF based on previous VF and optical coherence tomography (OCT) images (including thickness map, vertical tomogram, and horizontal tomogram). The image data were analyzed using a ResNet-50 model. Image features and previous VFs were combined, and a long short-term memory (LSTM) network was used to predict future VF. A weighted method was used to detect noisy data. The proposed method was improved when applying weighted loss. The mean absolute error (MAE) was 3.31 ± 1.37, and the root mean square error (RMSE) was 4.58 ± 1.77. The model showed high performance when combining VF data and OCT image data. Furthermore, the model was useful for detecting and re-weighting noisy data. |
| first_indexed | 2024-04-10T06:22:42Z |
| format | Article |
| id | doaj.art-561e507f103b4adaae27dd24df3e8423 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T06:22:42Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-561e507f103b4adaae27dd24df3e84232023-03-02T00:00:38ZengIEEEIEEE Access2169-35362023-01-0111190491905810.1109/ACCESS.2023.324806510050537Multimodal Deep Learning Model of Predicting Future Visual Field for Glaucoma PatientsQuang T. M. Pham0https://orcid.org/0000-0003-1652-299XJong Chul Han1Do Young Park2https://orcid.org/0000-0001-6089-6898Jitae Shin3https://orcid.org/0000-0002-2599-3331Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Republic of KoreaDepartment of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of KoreaDepartment of Ophthalmology, Yeungnam University Hospital, Yeungnam University College of Medicine, Daegu, Republic of KoreaDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Republic of KoreaGlaucoma is one of the most common reasons for blindness worldwide, especially in elderly people. Glaucoma can be monitored using visual field (VF) tests. Therefore, predicting the future VF to monitor progression of glaucoma is important. In this paper, we proposed a deep learning model to predict future VF based on previous VF and optical coherence tomography (OCT) images (including thickness map, vertical tomogram, and horizontal tomogram). The image data were analyzed using a ResNet-50 model. Image features and previous VFs were combined, and a long short-term memory (LSTM) network was used to predict future VF. A weighted method was used to detect noisy data. The proposed method was improved when applying weighted loss. The mean absolute error (MAE) was 3.31 ± 1.37, and the root mean square error (RMSE) was 4.58 ± 1.77. The model showed high performance when combining VF data and OCT image data. Furthermore, the model was useful for detecting and re-weighting noisy data.https://ieeexplore.ieee.org/document/10050537/Deep learningglaucomaOCTvisual field |
| spellingShingle | Quang T. M. Pham Jong Chul Han Do Young Park Jitae Shin Multimodal Deep Learning Model of Predicting Future Visual Field for Glaucoma Patients IEEE Access Deep learning glaucoma OCT visual field |
| title | Multimodal Deep Learning Model of Predicting Future Visual Field for Glaucoma Patients |
| title_full | Multimodal Deep Learning Model of Predicting Future Visual Field for Glaucoma Patients |
| title_fullStr | Multimodal Deep Learning Model of Predicting Future Visual Field for Glaucoma Patients |
| title_full_unstemmed | Multimodal Deep Learning Model of Predicting Future Visual Field for Glaucoma Patients |
| title_short | Multimodal Deep Learning Model of Predicting Future Visual Field for Glaucoma Patients |
| title_sort | multimodal deep learning model of predicting future visual field for glaucoma patients |
| topic | Deep learning glaucoma OCT visual field |
| url | https://ieeexplore.ieee.org/document/10050537/ |
| work_keys_str_mv | AT quangtmpham multimodaldeeplearningmodelofpredictingfuturevisualfieldforglaucomapatients AT jongchulhan multimodaldeeplearningmodelofpredictingfuturevisualfieldforglaucomapatients AT doyoungpark multimodaldeeplearningmodelofpredictingfuturevisualfieldforglaucomapatients AT jitaeshin multimodaldeeplearningmodelofpredictingfuturevisualfieldforglaucomapatients |