Publications by authors named "Adnan M Abdulazeez"
Article Synopsis
- Early diagnosis and monitoring of eye diseases are crucial, and this study focuses on using computer-aided detection (CAD) techniques for effective diagnosis through pixel-level classification via semantic segmentation.
- The research introduces three U-Net models for multi-class semantic segmentation, utilizing transfer learning and combining outputs from MSU-Net and BU-Net to create binary masks for key retinal regions like the optic disc and cup.
- Results from training nine pre-trained models on the HRF dataset, which includes various annotated regions, show high accuracy (87.7% pixel accuracy, 87% IoU), aiding in the early diagnosis of glaucoma and related optic nerve disorders.
Information-based image processing and computer vision methods are utilized in several healthcare organizations to diagnose diseases. The irregularities in the visual system are identified over fundus images with a fundus camera. Among ophthalmology diseases, glaucoma is the most common case leading to neurodegenerative illness.
View Article and Find Full Text PDF