Multimodal-Based Non-Contact High Intraocular Pressure Detection Method
This study proposes a deep learning-based, non-contact method for detecting elevated intraocular pressure (IOP) by integrating Scheimpflug images with corneal biomechanical features. Glaucoma, the leading cause of irreversible blindness worldwide, requires accurate IOP monitoring for early diagnosis...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/14/4258 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849251886591377408 |
|---|---|
| author | Zibo Lan Ying Hu Shuang Yang Jiayun Ren He Zhang |
| author_facet | Zibo Lan Ying Hu Shuang Yang Jiayun Ren He Zhang |
| author_sort | Zibo Lan |
| collection | DOAJ |
| description | This study proposes a deep learning-based, non-contact method for detecting elevated intraocular pressure (IOP) by integrating Scheimpflug images with corneal biomechanical features. Glaucoma, the leading cause of irreversible blindness worldwide, requires accurate IOP monitoring for early diagnosis and effective treatment. Traditional IOP measurements are often influenced by corneal biomechanical variability, leading to inaccurate readings. To address these limitations, we present a multi-modal framework incorporating CycleGAN for data augmentation, Swin Transformer for visual feature extraction, and the Kolmogorov–Arnold Network (KAN) for efficient fusion of heterogeneous data. KAN approximates complex nonlinear relationships with fewer parameters, making it effective in small-sample scenarios with intricate variable dependencies. A diverse dataset was constructed and augmented to alleviate data scarcity and class imbalance. By combining Scheimpflug imaging with clinical parameters, the model effectively integrates multi-source information to improve high IOP prediction accuracy. Experiments on a real-world private hospital dataset show that the model achieves a diagnostic accuracy of 0.91, outperforming traditional approaches. Grad-CAM visualizations identify critical anatomical regions, such as corneal thickness and anterior chamber depth, that correlate with IOP changes. These findings underscore the role of corneal structure in IOP regulation and suggest new directions for non-invasive, biomechanics-informed IOP screening. |
| format | Article |
| id | doaj-art-bbae045a8a0748d2bf08824017bc0dff |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-bbae045a8a0748d2bf08824017bc0dff2025-08-20T03:56:47ZengMDPI AGSensors1424-82202025-07-012514425810.3390/s25144258Multimodal-Based Non-Contact High Intraocular Pressure Detection MethodZibo Lan0Ying Hu1Shuang Yang2Jiayun Ren3He Zhang4School of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, ChinaDepartment of Ophthalmology, The Forth People’s Hospital of Shenyang, Huanggu District, No. 20 Huanghenan Street, Shenyang 110031, ChinaSchool of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, ChinaThis study proposes a deep learning-based, non-contact method for detecting elevated intraocular pressure (IOP) by integrating Scheimpflug images with corneal biomechanical features. Glaucoma, the leading cause of irreversible blindness worldwide, requires accurate IOP monitoring for early diagnosis and effective treatment. Traditional IOP measurements are often influenced by corneal biomechanical variability, leading to inaccurate readings. To address these limitations, we present a multi-modal framework incorporating CycleGAN for data augmentation, Swin Transformer for visual feature extraction, and the Kolmogorov–Arnold Network (KAN) for efficient fusion of heterogeneous data. KAN approximates complex nonlinear relationships with fewer parameters, making it effective in small-sample scenarios with intricate variable dependencies. A diverse dataset was constructed and augmented to alleviate data scarcity and class imbalance. By combining Scheimpflug imaging with clinical parameters, the model effectively integrates multi-source information to improve high IOP prediction accuracy. Experiments on a real-world private hospital dataset show that the model achieves a diagnostic accuracy of 0.91, outperforming traditional approaches. Grad-CAM visualizations identify critical anatomical regions, such as corneal thickness and anterior chamber depth, that correlate with IOP changes. These findings underscore the role of corneal structure in IOP regulation and suggest new directions for non-invasive, biomechanics-informed IOP screening.https://www.mdpi.com/1424-8220/25/14/4258non-contact high IOP detectiondeep learningmulti-modal modelScheimpflug imaging |
| spellingShingle | Zibo Lan Ying Hu Shuang Yang Jiayun Ren He Zhang Multimodal-Based Non-Contact High Intraocular Pressure Detection Method Sensors non-contact high IOP detection deep learning multi-modal model Scheimpflug imaging |
| title | Multimodal-Based Non-Contact High Intraocular Pressure Detection Method |
| title_full | Multimodal-Based Non-Contact High Intraocular Pressure Detection Method |
| title_fullStr | Multimodal-Based Non-Contact High Intraocular Pressure Detection Method |
| title_full_unstemmed | Multimodal-Based Non-Contact High Intraocular Pressure Detection Method |
| title_short | Multimodal-Based Non-Contact High Intraocular Pressure Detection Method |
| title_sort | multimodal based non contact high intraocular pressure detection method |
| topic | non-contact high IOP detection deep learning multi-modal model Scheimpflug imaging |
| url | https://www.mdpi.com/1424-8220/25/14/4258 |
| work_keys_str_mv | AT zibolan multimodalbasednoncontacthighintraocularpressuredetectionmethod AT yinghu multimodalbasednoncontacthighintraocularpressuredetectionmethod AT shuangyang multimodalbasednoncontacthighintraocularpressuredetectionmethod AT jiayunren multimodalbasednoncontacthighintraocularpressuredetectionmethod AT hezhang multimodalbasednoncontacthighintraocularpressuredetectionmethod |