retinal imaging

A ResNet is All You Need? Modeling A Strong Baseline for Detecting Referable Diabetic Retinopathy in Fundus Images

With no other methodological innovation than a carefully designed training, our ResNet model achieved an AUC = 0.955 (0.953 - 0.956) on a combined test set of 61007 test images from different public datasets, which is in line or even better than what other more complex deep learning models reported in the literature.

Assessing Coarse-to-Fine Deep Learning Models for Optic Disc and Cup Segmentation in Fundus Images

We experimentally validate whether using coarse-to-fine models instead of one-stage models is appropriate or not for segmenting the optic disc and the optic cup in color fundus images. We observed that models trained with the right amount of data can perform much better than coarse-to-find approaches.

Improving foveal avascular zone segmentation in fluorescein angiograms by leveraging manual vessel labels from public color fundus pictures

We developed a deep learning approach that leverages vessel segmentations from color fundus photographs to improve FAZ segmentation in FA images.

Linking Function and Structure with ReSenseNet: Predicting Retinal Sensitivity from Optical Coherence Tomography using Deep Learning

We present ReSenseNet, a 3D to 2D deep neural network that is able to predict microperimetry maps from OCT images.

AGE Challenge: Angle Closure Glaucoma Evaluation in Anterior Segment Optical Coherence Tomography

This is the summary publication of the AGE challenge on angle closure glaucoma detection from OCT scans of the anterior segment.

Automated Quantification of Photoreceptor alteration in macular disease using Optical Coherence Tomography and Deep Learning

We introduced a fully automated approach to segment the photorceptor layer, evaluate its thickness and track potential disruptions using an ensemble of deep neural networks.

Reducing image variability across OCT devices with unsupervised unpaired learning for improved segmentation of retina

We applied CycleGANs to reduce the covariate shift of models trained on one OCT vendor and evaluated on a different one. And it works quite well!

On Orthogonal Projections for Dimension Reduction and Applications in Augmented Target Loss Functions for Learning Problems

Anna introduced a new mathematical approach for dimensionality reduction that we incorporated into loss functions to augment target information and improve performance.

Multiclass Segmentation as Multitask Learning for Drusen Segmentation in Retinal Optical Coherence Tomography

We posed a multiclass segmentation task as a single multitask model with binary segmentation targets. Our results indicate that this approach might be useful to deal with "sandwiched" structures.

An Amplified-Target Loss Approach for Photoreceptor Layer Segmentation in Pathological OCT Scans

We introduce an augmented target loss function framework for photoreceptor layer segmentation that penalizes errors in the central area of each B-scan. It allows to significantly improve performance with respect to the standard loss functions.