Identifying Peripheral Neuropathy in Colour Fundus Photographs Based on Deep Learning
The aim of this study was to develop and validate a deep learning-based system to detect peripheral neuropathy (DN) from retinal colour images in people with diabetes. Retinal images from 1561 people with diabetes were used to predictDN diagnosed on vibration perception threshold. A total of 189 had...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/11/1943 |
| _version_ | 1797510691069886464 |
|---|---|
| author | Diego R. Cervera Luke Smith Luis Diaz-Santana Meenakshi Kumar Rajiv Raman Sobha Sivaprasad |
| author_facet | Diego R. Cervera Luke Smith Luis Diaz-Santana Meenakshi Kumar Rajiv Raman Sobha Sivaprasad |
| author_sort | Diego R. Cervera |
| collection | DOAJ |
| description | The aim of this study was to develop and validate a deep learning-based system to detect peripheral neuropathy (DN) from retinal colour images in people with diabetes. Retinal images from 1561 people with diabetes were used to predictDN diagnosed on vibration perception threshold. A total of 189 had diabetic retinopathy (DR), 276 had DN, and 43 had both DR and DN. 90% of the images were used for training and validation and 10% for testing. Deep neural networks, including Squeezenet, Inception, and Densenet were utilized, and the architectures were tested with and without pre-trained weights. Random transform of images was used during training. The algorithm was trained and tested using three sets of data: all retinal images, images without DR and images with DR. Area under the ROC curve (AUC) was used to evaluate performance. The AUC to predict DN on the whole cohort was 0.8013 (±0.0257) on the validation set and 0.7097 (±0.0031) on the test set. The AUC increased to 0.8673 (±0.0088) in the presence of DR. The retinal images can be used to identify individuals with DN and provides an opportunity to educate patients about their DN status when they attend DR screening. |
| first_indexed | 2024-03-10T05:34:56Z |
| format | Article |
| id | doaj.art-ef0f54e0eb31403fae121aa4516d6668 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T05:34:56Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-ef0f54e0eb31403fae121aa4516d66682023-11-22T23:00:03ZengMDPI AGDiagnostics2075-44182021-10-011111194310.3390/diagnostics11111943Identifying Peripheral Neuropathy in Colour Fundus Photographs Based on Deep LearningDiego R. Cervera0Luke Smith1Luis Diaz-Santana2Meenakshi Kumar3Rajiv Raman4Sobha Sivaprasad5Cambridge Consultants, Science Park, Milton Road, Cambridge CB4 0DW, UKCambridge Consultants, Science Park, Milton Road, Cambridge CB4 0DW, UKCambridge Consultants, Science Park, Milton Road, Cambridge CB4 0DW, UKShri Bhagwan Mahavir Department of Vitreoretinal Services, Sankara Nethralaya, No. 41 (Old 18), College Road, Chennai 600 006, IndiaShri Bhagwan Mahavir Department of Vitreoretinal Services, Sankara Nethralaya, No. 41 (Old 18), College Road, Chennai 600 006, IndiaNIHR Moorfields Biomedical Research Centre, 162 City Road, London EC1V 2PD, UKThe aim of this study was to develop and validate a deep learning-based system to detect peripheral neuropathy (DN) from retinal colour images in people with diabetes. Retinal images from 1561 people with diabetes were used to predictDN diagnosed on vibration perception threshold. A total of 189 had diabetic retinopathy (DR), 276 had DN, and 43 had both DR and DN. 90% of the images were used for training and validation and 10% for testing. Deep neural networks, including Squeezenet, Inception, and Densenet were utilized, and the architectures were tested with and without pre-trained weights. Random transform of images was used during training. The algorithm was trained and tested using three sets of data: all retinal images, images without DR and images with DR. Area under the ROC curve (AUC) was used to evaluate performance. The AUC to predict DN on the whole cohort was 0.8013 (±0.0257) on the validation set and 0.7097 (±0.0031) on the test set. The AUC increased to 0.8673 (±0.0088) in the presence of DR. The retinal images can be used to identify individuals with DN and provides an opportunity to educate patients about their DN status when they attend DR screening.https://www.mdpi.com/2075-4418/11/11/1943diabetesdeep learningdiabetic neuropathydiabetic retinopathy |
| spellingShingle | Diego R. Cervera Luke Smith Luis Diaz-Santana Meenakshi Kumar Rajiv Raman Sobha Sivaprasad Identifying Peripheral Neuropathy in Colour Fundus Photographs Based on Deep Learning Diagnostics diabetes deep learning diabetic neuropathy diabetic retinopathy |
| title | Identifying Peripheral Neuropathy in Colour Fundus Photographs Based on Deep Learning |
| title_full | Identifying Peripheral Neuropathy in Colour Fundus Photographs Based on Deep Learning |
| title_fullStr | Identifying Peripheral Neuropathy in Colour Fundus Photographs Based on Deep Learning |
| title_full_unstemmed | Identifying Peripheral Neuropathy in Colour Fundus Photographs Based on Deep Learning |
| title_short | Identifying Peripheral Neuropathy in Colour Fundus Photographs Based on Deep Learning |
| title_sort | identifying peripheral neuropathy in colour fundus photographs based on deep learning |
| topic | diabetes deep learning diabetic neuropathy diabetic retinopathy |
| url | https://www.mdpi.com/2075-4418/11/11/1943 |
| work_keys_str_mv | AT diegorcervera identifyingperipheralneuropathyincolourfundusphotographsbasedondeeplearning AT lukesmith identifyingperipheralneuropathyincolourfundusphotographsbasedondeeplearning AT luisdiazsantana identifyingperipheralneuropathyincolourfundusphotographsbasedondeeplearning AT meenakshikumar identifyingperipheralneuropathyincolourfundusphotographsbasedondeeplearning AT rajivraman identifyingperipheralneuropathyincolourfundusphotographsbasedondeeplearning AT sobhasivaprasad identifyingperipheralneuropathyincolourfundusphotographsbasedondeeplearning |