The biomedical community has shown a continued interest in automated detection of Diabetic Retinopathy (DR), with new imaging techniques, evolving diagnostic criteria, and advancing computing methods. Existing state of the art for detecting DR-related lesions tends to emphasize different, specific approaches for each type of lesion. However, recent research has aimed at general frameworks adaptable for large classes of lesions. In this paper, we follow this latter trend by exploring a very flexible framework, based upon two-tiered feature extraction (low-level and mid-level) from images and Support Vector Machines. The main contribution of this work is the evaluation of BossaNova, a recent and powerful mid-level image characterization technique, which we contrast with previous art based upon classical Bag of Visual Words (BoVW). The new technique using BossaNova achieves a detection performance (measured by area under the curve - AUC) of 96.4% for hard exudates, and 93.5% for red lesions using a cross-dataset training/testing protocol.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC.2014.6943550 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Research on grading detection methods for diabetic retinopathy based on deep learning.
Pak J Med Sci
January 2025
Juan Chen, Department of Ophthalmology, Affiliated Hospital of Hangzhou Normal University, Hangzhou, Zhejiang, China.
Objective: To design a deep learning-based model for early screening of diabetic retinopathy, predict the condition, and provide interpretable justifications.
Methods: The experiment's model structure is designed based on the Vision Transformer architecture which was initiated in March 2023 and the first version was produced in July 2023 at Affiliated Hospital of Hangzhou Normal University. We use the publicly available EyePACS dataset as input to train the model.
Frequency of undiagnosed hypertension among diabetic patients with micro vascular complications.
Pak J Med Sci
January 2025
Syed Khurram Shehzad, Department of Medicine, Lahore Medical and Dental College, Lahore, Pakistan.
Objectives: To determine the frequency of undiagnosed hypertension among the diabetic patients with micro vascular complications.
Method: This is a descriptive case series conducted at Department of Medicine, Ghurki Trust Teaching Hospital, in this six month stud which enrolled 213 patients between 18-60 years from March 28, 2021 to September 28, 2021, having diabetes with microvascular complications. These patients were not previously diagnosed as hypertensives.
Purpose: To develop an algorithm using routine clinical laboratory measurements to identify people at risk for systematic underestimation of glycated hemoglobin (HbA1c) due to p.Val68Met glucose-6-phosphate dehydrogenase (G6PD) deficiency.
Methods: We analyzed 122,307 participants of self-identified Black race across four large cohorts with blood glucose, HbA1c, and red cell distribution width measurements from a single blood draw.
Chondroitin Sulphate-Chitosan Based Nanogels Loaded with Naringenin-β-Cyclodextrin Complex as Potential Tool for the Treatment of Diabetic Retinopathy: A Formulation Study.
Int J Nanomedicine
January 2025
Department of Drug Sciences, University of Pavia, Pavia, 27100, Italy.
Purpose: The main purpose of the study was the formulation development of nanogels (NHs) composed of chondroitin sulfate (CS) and low molecular weight chitosan (lCH), loaded with a naringenin-β-cyclodextrin complex (NAR/β-CD), as a potential treatment for early-stage diabetic retinopathy.
Methods: Different formulations of NHs were prepared by varying polymer concentration, lCH ratio, and pH and, then, characterized for particle size, zeta potential, particle concentration (particles/mL) and morphology. Cytotoxicity and internalization were assessed in vitro using Human Umbilical Vein Endothelial Cells (HUVEC).
Association Between HbA1c Levels and the Severity of Diabetic Retinopathy.
Cureus
December 2024
Department of Ophthalmology, College of Medicine, Qassim University, Kingdom of Saudi Arabia, Buraidah, SAU.
Background: Diabetic retinopathy (DR) is a significant microvascular complication of diabetes mellitus (DM), contributing to visual impairment and blindness worldwide. Understanding the factors associated with the severity of DR is crucial for effective prevention and management. This study aimed to explore the association between hemoglobin A1c (HbA1c) level and other parameters with different stages of DR.
View Article and Find Full Text PDFWant 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!