A5008826782- Retinal Imaging and Analysis
- Retinal Diseases and Treatments
- Glaucoma and retinal disorders
- Optical Coherence Tomography Applications
- Retinal and Optic Conditions
- Retinal Development and Disorders
- Neonatal Health and Biochemistry
- Ophthalmology and Visual Impairment Studies
- Hemoglobinopathies and Related Disorders
- Systemic Lupus Erythematosus Research
- Ocular Oncology and Treatments
- Intraocular Surgery and Lenses
- Connexins and lens biology
- Ocular Diseases and Behçet’s Syndrome
- melanin and skin pigmentation
- Adversarial Robustness in Machine Learning
- Neurofibromatosis and Schwannoma Cases
- Ophthalmology and Visual Health Research
- Anomaly Detection Techniques and Applications
- Bacillus and Francisella bacterial research
- Methemoglobinemia and Tumor Lysis Syndrome
- Brain Tumor Detection and Classification
- Vascular Malformations and Hemangiomas
- Ocular and Laser Science Research
- Iron Metabolism and Disorders
National Eye Institute
2015-2025
National Institutes of Health
2015-2025
University of Illinois Chicago
2018-2019
New York Eye and Ear Infirmary
2017
University of Rochester
2012-2015
Purpose: To examine relationships between retinal structure and visual function in geographic atrophy (GA) by analyzing spatial agreement absolute scotomas macular structure, focusing on (1) choroidal hypertransmission, a key feature of complete pigment epithelium outer (cRORA), (2) fundus autofluorescence (FAF)–defined GA. Methods: Mesopic microperimetry (using novel T-shaped pattern) multimodal imaging were recorded longitudinally phase II GA trial. Horizontal vertical optical coherence...
Introduction - Retinal layer segmentation in optical coherence tomography (OCT) images is an important approach for detecting and prognosing disease. Automating using robust machine learning techniques lead to computationally efficient solutions significantly reduces the cost of labor-intensive labeling, which traditionally performed by trained graders at a reading center, sometimes aided semi-automated algorithms. Although several algorithms have been proposed since revival deep learning,...
Importance Existing therapies to slow geographic atrophy (GA) enlargement in age-related macular degeneration (AMD) have relatively modest anatomic efficacy, require intravitreal administration, and increase the risk of neovascular AMD. Additional therapeutic approaches are desirable. Objective To evaluate safety possible efficacy oral minocycline, a microglial inhibitor, for treatment GA Design, Setting, Participants This was phase 2, prospective, single-arm, 45-month, nonrandomized...
Convolutional neural networks (CNNs) have been widely applied to medical images. However, images are vulnerable adversarial attacks by perturbations that undetectable human experts. This poses significant security risks and challenges CNN-based applications in clinic practice. In this work, we quantify the scale of perturbation imperceptible clinical practitioners investigate cause vulnerability CNNs. Specifically, discover noise (i.e., irrelevant or corrupted discriminative information)...
To identify features correlating with drusenoid pigment epithelial detachment (DPED) progression in the Age-Related Eye Disease Study 2 Ancillary spectral-domain optical coherence tomography study cohort.In this retrospective analysis of a prospective longitudinal study, eyes intermediate age-related macular degeneration and DPEDs were followed longitudinally annual multimodal imaging.Thirty-one 25 participants (mean age 72.6 years) OCT substudy (A2A study) had DPED identified color fundus...
Purpose: To evaluate the quality and efficacy of Ban Phaeo Mobile Eye Clinic (BPMEC) model in providing cataract surgery to rural Thailand.Methods: Retrospective review 4-week postoperative visual acuity (VA) 7040 patients receiving unilateral at 75 sites from October 2008 March 2011. BPMEC conducted screening, surgery, follow-up partnering local hospitals that otherwise do not offer eye care. The primary outcome was achievement VA ≥20/70, which secondarily analyzed by extraction method...
Purpose: Spectral Domain Optical Coherence Tomography (SD-OCT) images are a series of Bscans which capture the volume retina and reveal structural information. Diseases outer cause changes to retinal layers evident on SD-OCT images, revealing disease etiology risk factors for progression. Quantitative thickness information provide relevant data that important aspects pathogenesis. Manually labeling these is extremely laborious, time consuming costly. Recently, deep learning algorithms have...
Purpose: Spectral Domain Optical Coherence Tomography (SD-OCT) is a much utilized imaging modality in retina clinics to inspect the integrity of retinal layers patients with age related macular degeneration. Spectralis and Cirrus are two most widely used SD-OCT vendors. Due stark difference intensities signal noise ratio's between images captured by instruments, model trained on from one instrument performs poorly other instrument. Methods: In this work, we explore performance an algorithm...
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...
Purpose: This study aimed to develop an algorithm for automated detection of drusenoid pigment epithelial detachments (DPEDs) in optical coherence tomography (OCT) volumes patients with age-related macular degeneration (AMD) and compare its performance against traditional reading center grading on color-fundus photographs (CFPs). Methods: Eyes a range AMD severities, excluding neovascular disease, were imaged using spectral-domain OCT (SD-OCT) paired CFPs followed annually up 5 years. DPEDs...