Search Results for author:
Found 32 papers, 13 papers with code
RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models
To address this, we propose RetFiner, an SSL vision-language refinement scheme that improves the representations of existing FMs and enables their efficient and direct adaptation to specific populations for improved downstream performance.
PiPViT: Patch-based Visual Interpretable Prototypes for Retinal Image Analysis
Background and Objective: Prototype-based methods improve interpretability by learning fine-grained part-prototypes; however, their visualization in the input pixel space is not always consistent with human-understandable biomarkers.
MIRAGE: Multimodal foundation model and benchmark for comprehensive retinal OCT image analysis
Artificial intelligence (AI) has become a fundamental tool for assisting clinicians in analyzing ophthalmic images, such as optical coherence tomography (OCT).
Automatic detection and prediction of nAMD activity change in retinal OCT using Siamese networks and Wasserstein Distance for ordinality
In this work, we proposed deep learning models for the two tasks of the public MARIO Challenge at MICCAI 2024, designed to detect and forecast changes in nAMD severity with longitudinal retinal OCT. For the first task, we employ a Vision Transformer (ViT) based Siamese Network to detect changes in AMD severity by comparing scan embeddings of a patient from different time points.
Forecasting Disease Progression with Parallel Hyperplanes in Longitudinal Retinal OCT
Moreover, deep learning (DL) methods for survival analysis are susceptible to image domain shifts across scanners.
Comparative Analysis of Data Augmentation for Retinal OCT Biomarker Segmentation
Data augmentation plays a crucial role in addressing the challenge of limited expert-annotated datasets in deep learning applications for retinal Optical Coherence Tomography (OCT) scans.
Specialist vision-language models for clinical ophthalmology
The resulting model, RetinaVLM, can be instructed to write reports that significantly outperform those written by leading foundation medical VLMs in disease staging (F1 score of 0. 63 vs. 0. 11) and patient referral (0. 67 vs. 0. 39), and approaches the diagnostic performance of junior ophthalmologists (who achieve 0. 77 and 0. 78 on the respective tasks).
Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations
Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously preventing representational collapse.
Deep-learning-based clustering of OCT images for biomarker discovery in age-related macular degeneration (Pinnacle study report 4)
Overall, contrastive learning enabled the automatic proposal of AMD biomarkers that go beyond the set used by clinically established grading systems.
Spatiotemporal Representation Learning for Short and Long Medical Image Time Series
Moreover, tracking longer term developments that occur over months or years in evolving processes, such as age-related macular degeneration (AMD), is essential for accurate prognosis.
RRWNet: Recursive Refinement Network for effective retinal artery/vein segmentation and classification
The framework consists of a fully convolutional neural network that recursively refines semantic segmentation maps, correcting manifest classification errors and thus improving topological consistency.
Ranked #1 on
Artery/Veins Retinal Vessel Segmentation
on HRF
Deep Multimodal Fusion of Data with Heterogeneous Dimensionality via Projective Networks
The use of multimodal imaging has led to significant improvements in the diagnosis and treatment of many diseases.
3DTINC: Time-Equivariant Non-Contrastive Learning for Predicting Disease Progression from Longitudinal OCTs
Self-supervised learning (SSL) has emerged as a powerful technique for improving the efficiency and effectiveness of deep learning models.
SAMedOCT: Adapting Segment Anything Model (SAM) for Retinal OCT
The Segment Anything Model (SAM) has gained significant attention in the field of image segmentation due to its impressive capabilities and prompt-based interface.
Pretrained Deep 2.5D Models for Efficient Predictive Modeling from Retinal OCT
In the field of medical imaging, 3D deep learning models play a crucial role in building powerful predictive models of disease progression.
Self-supervised learning via inter-modal reconstruction and feature projection networks for label-efficient 3D-to-2D segmentation
Moreover, the proposed SSL method allows further improvement of this performance by up to 23%, and we show that the SSL is beneficial regardless of the network architecture.
PALM: Open Fundus Photograph Dataset with Pathologic Myopia Recognition and Anatomical Structure Annotation
Our databases comprises 1200 images with associated labels for the pathologic myopia category and manual annotations of the optic disc, the position of the fovea and delineations of lesions such as patchy retinal atrophy (including peripapillary atrophy) and retinal detachment.
Morph-SSL: Self-Supervision with Longitudinal Morphing to Predict AMD Progression from OCT
We develop a Deep Learning (DL) model to predict the future risk of conversion of an eye from iAMD to nAMD from its current OCT scan.
AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challenge
Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible.
Clustering disease trajectories in contrastive feature space for biomarker discovery in age-related macular degeneration
Age-related macular degeneration (AMD) is the leading cause of blindness in the elderly.
Metadata-enhanced contrastive learning from retinal optical coherence tomography images
This is exacerbated in longitudinal image datasets that repeatedly image the same patient cohort to monitor their disease progression over time.
TINC: Temporally Informed Non-Contrastive Learning for Disease Progression Modeling in Retinal OCT Volumes
Recent contrastive learning methods achieved state-of-the-art in low label regimes.
REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening
Here we release a multi-annotation, multi-quality, and multi-device color fundus image dataset for glaucoma analysis on an original challenge -- Retinal Fundus Glaucoma Challenge 2nd Edition (REFUGE2).
ADAM Challenge: Detecting Age-related Macular Degeneration from Fundus Images
The ADAM challenge consisted of four tasks which cover the main aspects of detecting and characterizing AMD from fundus images, including detection of AMD, detection and segmentation of optic disc, localization of fovea, and detection and segmentation of lesions.
U-Net with spatial pyramid pooling for drusen segmentation in optical coherence tomography
In the second approach, the surrounding retinal layers (outer boundary retinal pigment epithelium (OBRPE) and Bruch's membrane (BM)) are segmented and the remaining space between these two layers is extracted as drusen.
Modeling Disease Progression In Retinal OCTs With Longitudinal Self-Supervised Learning
Longitudinal imaging is capable of capturing the static ana\-to\-mi\-cal structures and the dynamic changes of the morphology resulting from aging or disease progression.
REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one.
An amplified-target loss approach for photoreceptor layer segmentation in pathological OCT scans
Supervised deep learning models trained with standard loss functions are usually able to characterize only the most common disease appeareance from a training set, resulting in suboptimal performance and poor generalization when dealing with unseen lesions.
Multiclass segmentation as multitask learning for drusen segmentation in retinal optical coherence tomography
We also introduce connections between each class-specific branch and the additional decoder to increase the regularization effect of this surrogate task.
Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT
We propose to take advantage of this property using bayesian deep learning, based on the assumption that epistemic uncertainties will correlate with anatomical deviations from a normal training set.
Using CycleGANs for effectively reducing image variability across OCT devices and improving retinal fluid segmentation
Among the several sources of variability the ML models have to deal with, a major factor is the acquisition device, which can limit the ML model's generalizability.
U2-Net: A Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans
In this paper, we introduce a Bayesian deep learning based model for segmenting the photoreceptor layer in pathological OCT scans.
Ranked #4 on
Image Matting
on AIM-500
