diabetic retinopathy
PulseAugur coverage of diabetic retinopathy — every cluster mentioning diabetic retinopathy across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
FDA warns GLP-1 drugs like Ozempic linked to rare vision loss condition · 2 sources tracked
The U.S. Food and Drug Administration (FDA) has issued a new warning for GLP-1 drugs, including Ozempic and Wegovy, due to a rare but serious eye condition known as non-arteritic anterior ischemic optic neuropathy (NAIO…
-
New D2Mamba Model Excels at Segmenting Tiny Retinal Lesions
Researchers have developed D$^2$Mamba, a novel deep learning model designed for segmenting small and irregularly shaped lesions in retinal images, specifically for diabetic retinopathy. This model integrates non-causal …
-
New GUES method tackles domain shift in diabetic retinopathy grading
Researchers have introduced a novel approach called Generative Unadversarial Examples (GUES) to address domain shift challenges in clinical applications, specifically for Diabetic Retinopathy (DR) grading. This method t…
-
New GNN Improves Retinal Disease Classification with Enhanced Interpretability
Researchers have developed a novel dual-hub heterogeneous graph neural network (GNN) designed for multi-label retinal screening. This GNN aims to improve the interpretability of multimodal fusion by explicitly modeling …
-
New deep learning framework improves diabetic retinopathy grading
Researchers have developed CalibCause, a novel deep learning framework designed to improve the grading of diabetic retinopathy. This framework addresses limitations in current systems by incorporating quality gating, ex…
-
New privileged learning framework improves ocular disease screening with single-eye images
Researchers have developed a novel privileged learning framework to improve the screening of ocular diseases using colour fundus photography (CFP). This method trains a teacher model using images from both eyes, which c…
-
AI diagnostic performance varies with camera hardware, study finds
A new study published on arXiv highlights significant performance disparities in AI systems used for diagnosing diabetic retinopathy, stemming from differences in camera equipment. Researchers found that retinal images …
-
New CF-NODE framework enhances AI model adaptation for medical imaging
Researchers have developed CF-NODE, a new framework for adapting AI models to new domains, specifically for diabetic retinopathy grading. Unlike existing methods that rely on prediction confidence or batch statistics, C…
-
New Graph Method Boosts Retinal Disease Prediction Interpretability
Researchers have developed a novel biology-informed heterogeneous graph representation to improve the interpretability of machine learning models for predicting diabetic retinopathy. This method models retinal vessel se…
-
DR-LabStack integrates diverse diabetic retinopathy prediction models
Researchers have developed DR-LabStack, a web system designed to integrate multiple pretrained diabetic retinopathy prediction models. This system, built with React and Flask, standardizes the interface for diverse mode…
-
Foundation models show no consistent advantage over CNNs for eye disease detection
A new research paper evaluates the effectiveness of foundation models (FMs) for detecting diabetic macular edema (DME) from fundus images. The study found that while FMs like RETFound and FLAIR were tested, they did not…
-
Medical AI models need better uncertainty quantification, study finds
A new research paper explores uncertainty quantification in medical foundation models, comparing domain-specific models with general ones. The study found that pre-training on high-quality, domain-specific datasets usin…
-
Vision foundation models show promise for explainable diabetic retinopathy classification
Researchers have developed an explainable framework for classifying diabetic retinopathy (DR) using vision foundation models. The study evaluated DINOv2, CLIP, and Vision Transformer backbones with various transfer lear…
-
Ordinal diffusion model generates realistic medical images with ordered disease progression
Researchers have developed an ordinal latent diffusion model designed to generate color fundus images, specifically addressing the continuous nature of disease progression in ophthalmology. Unlike standard conditional d…
-
LinkedIn's 'AI slop' flag hits 1M clicks; Oman launches AI diabetic screening
LinkedIn's feature allowing users to flag posts as "AI slop" has surpassed one million clicks, as reported by Chief Product Officer Hari Srinivasan. Separately, Oman has launched a national AI initiative to screen diabe…
-
New metric quantifies explanation consistency in medical AI fairness
Researchers have introduced a new metric called the Explanation Consistency Score (ECS) to evaluate fairness in medical imaging models. This score, based on Jensen-Shannon divergence, quantifies how similar the attribut…
-
New hybrid deep learning model improves diabetic retinopathy grading
Researchers have developed ORViT-DR, a novel hybrid deep learning framework designed to enhance the grading of diabetic retinopathy from low-resolution retinal images. This approach integrates convolutional feature extr…
-
AI model enhances diabetic retinopathy grading with uncertainty awareness
Researchers have developed a new pipeline for automated diabetic retinopathy (DR) grading that incorporates lesion-aware preprocessing, ordinal predictions, and uncertainty estimation. The system uses a specific feature…
-
New PARAGraph framework improves diabetic retinopathy grading
Researchers have developed a novel framework called PARAGraph for grading diabetic retinopathy (DR). This hierarchical graph-based approach models lesion types and their spatial relationships within an image, anchored t…
-
AI revolutionizes early disease detection in cancer, heart care
Artificial intelligence is revolutionizing early disease detection across critical health areas like cancer, diabetic retinopathy, and heart disease. AI systems analyze medical images and patient data to identify subtle…