A5039817860- Retinal Imaging and Analysis
- Traumatic Brain Injury Research
- Retinal Diseases and Treatments
- Corneal surgery and disorders
- Psychosomatic Disorders and Their Treatments
- Retinal and Optic Conditions
- Intraocular Surgery and Lenses
- Ocular Surface and Contact Lens
- Noise Effects and Management
- Hematopoietic Stem Cell Transplantation
- Risk Perception and Management
- Digital Imaging for Blood Diseases
- Glaucoma and retinal disorders
- Imbalanced Data Classification Techniques
- Corneal Surgery and Treatments
- Ocular Infections and Treatments
National Eye Institute
2020-2024
National Institutes of Health
2020-2024
Joint Base San Antonio
2013
Since 2015, US government and related personnel have reported dizziness, pain, visual problems, cognitive dysfunction after experiencing intrusive sounds head pressure. The has labeled these anomalous health incidents (AHIs).
Abstract Objective Reticular pseudodrusen (RPD), a key feature of age-related macular degeneration (AMD), are poorly detected by human experts on standard color fundus photography (CFP) and typically require advanced imaging modalities such as autofluorescence (FAF). The objective was to develop evaluate the performance novel multimodal, multitask, multiattention (M3) deep learning framework RPD detection. Materials Methods A developed detect presence accurately using CFP alone, FAF or both,...
Timely disease diagnosis is challenging due to increasing burdens and limited clinician availability. AI shows promise in accuracy but faces real-world application issues insufficient validation clinical workflows diverse populations. This study addresses gaps medical downstream accountability through a case on age-related macular degeneration (AMD) severity classification. We designed implemented an AI-assisted diagnostic workflow for AMD, comparing performance with without assistance among...
Objective Reticular pseudodrusen (RPD), a key feature of age-related macular degeneration (AMD), are poorly detected by human experts on standard color fundus photography (CFP) and typically require advanced imaging modalities such as autofluorescence (FAF). The objective was to develop evaluate the performance novel 'M3' deep learning framework RPD detection. Materials Methods A M3 developed detect presence accurately using CFP alone, FAF or both, employing >8000 CFP-FAF image pairs...