HYBRID EVENT: You can participate in person at Rome, Italy or Virtually from your home or work.

3rd Edition of

International Ophthalmology Conference

March 10-12, 2025 | Rome, Italy

IOC 2022

Identifying diabetes from conjunctival images using a novel hierarchical multi-task network

Speaker at International  Ophthalmology Conference 2022 - Xinyue Li
Shanghai Children ‘s Hospital, China
Title : Identifying diabetes from conjunctival images using a novel hierarchical multi-task network

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(Figure). 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(Table). The model allowed sensitive and rapid discrimination by assessment of conjunctival images and can be potentially useful for identifying diabetes.

Biography:

Xinyue Li is a junior doctor in Shanghai Children ‘s Hospital. The objectives of her research are (i) application of deep learning in ophthalmology and (ii) myopia in children. She has Phd degree from Harbin Medical University in ophthalmology. She speaks Chinese and English.

Watsapp