Vision transformers for automated detection of diabetic peripheral neuropathy in corneal confocal microscopy images
Early detection and management of diabetic peripheral neuropathy (DPN) are critical to reducing associated morbidity and mortality. Corneal Confocal Microscopy (CCM) facilitates the imaging of corneal nerves to detect early and progressive nerve damage in DPN. However, its wider adoption has been li...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Imaging |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fimag.2025.1542128/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832548278912155648 |
|---|---|
| author | Chaima Ben Rabah Ioannis N. Petropoulos Rayaz A. Malik Ahmed Serag |
| author_facet | Chaima Ben Rabah Ioannis N. Petropoulos Rayaz A. Malik Ahmed Serag |
| author_sort | Chaima Ben Rabah |
| collection | DOAJ |
| description | Early detection and management of diabetic peripheral neuropathy (DPN) are critical to reducing associated morbidity and mortality. Corneal Confocal Microscopy (CCM) facilitates the imaging of corneal nerves to detect early and progressive nerve damage in DPN. However, its wider adoption has been limited by the subjectivity and time-intensive nature of manual nerve fiber quantification. This study investigates the diagnostic utility of state-of-the-art Vision Transformer (ViT) models for the binary classification of CCM images to distinguish between healthy controls and individuals with DPN. The ViT model's performance was also compared to ResNet50, a convolutional neural network (CNN) previously applied for DPN detection using CCM images. Using a dataset of approximately 700 CCM images, the ViT model achieved an AUC of 0.99, a sensitivity of 98%, a specificity of 92%, and an F1-score of 95%, outperforming previously reported methods. These findings highlight the potential of the ViT model as a reliable tool for CCM-based DPN diagnosis, eliminating the need for time-consuming manual image segmentation. Moreover, the results reinforce CCM's value as a non-invasive and precise imaging modality for detecting nerve damage, particularly in neuropathy-related conditions such as DPN. |
| format | Article |
| id | doaj-art-93341ed1a82443fdbbd82484a6337f43 |
| institution | Kabale University |
| issn | 2813-3315 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Imaging |
| spelling | doaj-art-93341ed1a82443fdbbd82484a6337f432025-02-03T06:33:24ZengFrontiers Media S.A.Frontiers in Imaging2813-33152025-02-01410.3389/fimag.2025.15421281542128Vision transformers for automated detection of diabetic peripheral neuropathy in corneal confocal microscopy imagesChaima Ben Rabah0Ioannis N. Petropoulos1Rayaz A. Malik2Ahmed Serag3AI Innovation Lab, Weill Cornell Medicine-Qatar, Doha, QatarDepartment of Medicine, Weill Cornell Medicine-Qatar, Doha, QatarDepartment of Medicine, Weill Cornell Medicine-Qatar, Doha, QatarAI Innovation Lab, Weill Cornell Medicine-Qatar, Doha, QatarEarly detection and management of diabetic peripheral neuropathy (DPN) are critical to reducing associated morbidity and mortality. Corneal Confocal Microscopy (CCM) facilitates the imaging of corneal nerves to detect early and progressive nerve damage in DPN. However, its wider adoption has been limited by the subjectivity and time-intensive nature of manual nerve fiber quantification. This study investigates the diagnostic utility of state-of-the-art Vision Transformer (ViT) models for the binary classification of CCM images to distinguish between healthy controls and individuals with DPN. The ViT model's performance was also compared to ResNet50, a convolutional neural network (CNN) previously applied for DPN detection using CCM images. Using a dataset of approximately 700 CCM images, the ViT model achieved an AUC of 0.99, a sensitivity of 98%, a specificity of 92%, and an F1-score of 95%, outperforming previously reported methods. These findings highlight the potential of the ViT model as a reliable tool for CCM-based DPN diagnosis, eliminating the need for time-consuming manual image segmentation. Moreover, the results reinforce CCM's value as a non-invasive and precise imaging modality for detecting nerve damage, particularly in neuropathy-related conditions such as DPN.https://www.frontiersin.org/articles/10.3389/fimag.2025.1542128/fullartificial intelligencediabetic neuropathycorneal confocal microscopyimage classificationdisease diagnosis |
| spellingShingle | Chaima Ben Rabah Ioannis N. Petropoulos Rayaz A. Malik Ahmed Serag Vision transformers for automated detection of diabetic peripheral neuropathy in corneal confocal microscopy images Frontiers in Imaging artificial intelligence diabetic neuropathy corneal confocal microscopy image classification disease diagnosis |
| title | Vision transformers for automated detection of diabetic peripheral neuropathy in corneal confocal microscopy images |
| title_full | Vision transformers for automated detection of diabetic peripheral neuropathy in corneal confocal microscopy images |
| title_fullStr | Vision transformers for automated detection of diabetic peripheral neuropathy in corneal confocal microscopy images |
| title_full_unstemmed | Vision transformers for automated detection of diabetic peripheral neuropathy in corneal confocal microscopy images |
| title_short | Vision transformers for automated detection of diabetic peripheral neuropathy in corneal confocal microscopy images |
| title_sort | vision transformers for automated detection of diabetic peripheral neuropathy in corneal confocal microscopy images |
| topic | artificial intelligence diabetic neuropathy corneal confocal microscopy image classification disease diagnosis |
| url | https://www.frontiersin.org/articles/10.3389/fimag.2025.1542128/full |
| work_keys_str_mv | AT chaimabenrabah visiontransformersforautomateddetectionofdiabeticperipheralneuropathyincornealconfocalmicroscopyimages AT ioannisnpetropoulos visiontransformersforautomateddetectionofdiabeticperipheralneuropathyincornealconfocalmicroscopyimages AT rayazamalik visiontransformersforautomateddetectionofdiabeticperipheralneuropathyincornealconfocalmicroscopyimages AT ahmedserag visiontransformersforautomateddetectionofdiabeticperipheralneuropathyincornealconfocalmicroscopyimages |