deep learning

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.

A deep learning model for brain vessel segmentation\ in 3DRA with arteriovenous malformations

We train the first deep learning model for segmenting brain arteries from 3D rotational angiographies in cases with brain arterio-venous malformations.

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.

Cómo entrenar bien un baseline - Experiencias y recomendaciones desde la aplicación de deep learning en oftalmología

Cuando aplicamos inteligencia artificial en medicina, solemos seguir uno de dos enfoques: o bien utilizar modelos que ya existen para resolver un problema nuevo, o bien proponer un modelo nuevo para resolver problemas que ya existen. En todos los …

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.

SketchZooms: Deep multi-view descriptors for matching line drawings

We develop a deep neural network that automatically extracts contextual features from patches in sketches, trained with 3D models rendered with non-photorealistic techniques. Our method is able to find dense correspondences between real world sketches!

Automated lumen segmentation using multi-frame convolutional neural networks in intravascular ultrasound datasets

We developed a deep learning based pipeline to segment the lumen boundary in IVUS datasets based on multiframes inputs.

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.