Annotation and segmentation of diabetic retinopathy lesions: an explainable AI application
In person: 23 February 2022 • 5:30 PM - 7:00 PM PST
Diabetic Retinopathy (DR) is a major cause of visual impairment among the working-age population with a high prevalence rate. This disease is characterized by 10 major lesions on fundus examination according to the International Clinical Diabetic Retinopathy scale (ICDRS). DR can be diagnosed with computer-aided diagnosis methods such as deep neural networks (DNN). The approach of this study is to segment DR-associated lesions with DNN models and predict severity grades using segmented lesions. A dataset of 143 images was used to produce lesion annotated masks. The proposed toolbox will include task-based DNN models for segmenting lesions. Then, models will be combined to predict disease grade according to ICDRS.
Univ. of Waterloo (Canada)
Hoda Kheradfallah is masters student in the school of Optometry, University of Waterloo. She works on automated diabetic retinopathy diagnosis through deep learning. Hoda graduated from Sharif University of Technology, Tehran , Iran in the level of BSc of Electrical Engineering. Her passion for medical image and signal processing caused her to apply the latest developments in the Neural Networks for retinal image analysis and improve the performance of existing models for detection of diabetic retinopathy disease with fungus image processing. In this conference she plans to present her achievements, the proposed toolbox and future steps.