In recent years, many image analysis algorithms have been presented to assist Diabetic Retinopathy (DR) screening. The goal was usually to detect healthy examination records automatically, in order to reduce the number of records that should be analyzed by retinal experts. In this paper, a novel application is presented: these algorithms are used to 1) discover image characteristics that sometimes cause an expert to disagree with his/her peers and 2) warn the expert whenever these characteristics are detected in an examination record. In a DR screening program, each examination record is only analyzed by one expert, therefore analyzing disagreements among experts is challenging. A statistical framework, based on Parzen-windowing and the Patrick-Fischer distance, is presented to solve this problem. Disagreements among eleven experts from the Ophdiat screening program were analyzed, using an archive of 25,702 examination records.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC.2012.6347351 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Child Maltreatment Evaluations Following Out-of-Hospital Cardiac Arrests.
Acad Pediatr
January 2025
Department of Pediatrics, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania; Safe Place and PolicyLab, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania; Perelman School of Medicine at the University of Pennsylvania, Philadelphia, Pennsylvania.
Objectives: In children admitted after an out-of-hospital cardiac arrest (OHCA), this study 1) determines the proportion that undergo: physical abuse and toxin exposure evaluation, child protection team (CPT) consultation, and child protective services (CPS) referral, and 2) evaluates the association between demographic, social, clinical characteristics with CPT consultation and CPS referral.
Methods: Retrospective chart review was conducted of children < 4 years old admitted following an OHCA between November 2012 and February 2023. Associations between demographics, caregiver social risk factors, and clinical characteristics with CPT consultation and CPS referral were examined using logistic regression.
WGAN-GP for Synthetic Retinal Image Generation: Enhancing Sensor-Based Medical Imaging for Classification Models.
Sensors (Basel)
December 2024
Computer Science Department, Instituto Nacional de Astrofísica Óptica y Electrónica, Luis Enrrique Erro No. 1, Sta. María Tonantzintla, Puebla 72840, Mexico.
Accurate synthetic image generation is crucial for addressing data scarcity challenges in medical image classification tasks, particularly in sensor-derived medical imaging. In this work, we propose a novel method using a Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) and nearest-neighbor interpolation to generate high-quality synthetic images for diabetic retinopathy classification. Our approach enhances training datasets by generating realistic retinal images that retain critical pathological features.
View Article and Find Full Text PDFDeep learning model for automatic detection of different types of microaneurysms in diabetic retinopathy.
Eye (Lond)
January 2025
Department of Surgical Sciences, University of Turin, Turin, Italy.
Purpose: This study aims to develop a deep-learning-based software capable of detecting and differentiating microaneurysms (MAs) as hyporeflective or hyperreflective on structural optical coherence tomography (OCT) images in patients with non-proliferative diabetic retinopathy (NPDR).
Methods: A retrospective cohort of 249 patients (498 eyes) diagnosed with NPDR was analysed. Structural OCT scans were obtained using the Heidelberg Spectralis HRA + OCT device.
Development and psychometric properties of a quality of life assessment tool for Chinese patients undergoing intravitreal injection (IVI-QoL-23).
Retina
January 2025
Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital, Tianjin, China.
Purpose: To develop and assess the psychometric properties of a quality of life (QoL) assessment tool for Chinese patients treated with intravitreal injection (IVI) of anti-vascular endothelial growth factor (anti-VEGF).
Methods: We developed a 31-item IVI-QoL questionnaire using semi- structured patient interviews and expert panel consultation, drawing on a study of the literature. After pretesting on a subset of patients undergoing IVI, the questionnaire was pared down to 23 items.
Assessment of glaucoma with retinal nerve fiber layer optical density ratios from volumetric optical coherence tomography across various analytical radii.
Expert Rev Med Devices
January 2025
Joint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Objective: To explore the impact of glaucoma on the retinal nerve fiber layer (RNFL) optical density ratio (ODR) by volumetric optical coherence tomography (OCT) under different analytical radii.
Methods: Twenty-five eyes identified as healthy and 57 eyes with a glaucoma diagnosis (23 mild and 34 moderate-advanced cases) underwent volumetric OCT scans centered at the optic nerve head. Cross-sectional images were obtained through 5 distinct analytical circles with varying radii.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!