Abstract
Diabetes can cause microvessel impairment. However, these conjunctival pathological changes are not easily recognized, limiting their potential as independent diagnostic indicators. Therefore, we designed a deep learning model to explore the relationship between conjunctival features and diabetes, and to advance automated identification of diabetes through conjunctival images. Images were collected from patients with type 2 diabetes and healthy volunteers. A hierarchical multi-tasking network model (HMT-Net) was developed using conjunctival images, and the model was systematically evaluated and compared with other algorithms. The sensitivity, specificity, and accuracy of the HMT-Net model to identify diabetes were 78.70%, 69.08%, and 75.15%, respectively. The performance of the HMT-Net model was significantly better than that of ophthalmologists. The model allowed sensitive and rapid discrimination by assessment of conjunctival images and can be potentially useful for identifying diabetes.
Highlights
Since bulbar conjunctiva is the only blood vessel in the body that can be seen directly without using any equipment, bulbar conjunctival vessels can be used as a feasible window for studying diabetes
Based on previous observation of diabetic conjunctiva
The hierarchical multi-tasking network model (HMT-Net) model designed in the present study can locate several associations between conjunctival images and diabetes, which provides the possibility for automatic screening of diabetes by deep learning analysis of conjunctival images in the future
Summary
Key challenges in developing an effective deep learning system are that a large number of annotated training samples are needed for supervised learning[11,12], and the high cost to obtain enough high-quality, clinical samples To overcome these challenges, we developed a novel and personalized algorithm called the hierarchical multi-task network (HMT-Net) for identifying diabetes using. Based on previous observation of diabetic conjunctiva This algorithm can overcome data insufficiency and is sufficiently accurate compared with traditional models. It reduces the dependence on big datasets and can be conveniently applied to the medical setting
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
