Retinal Imaging | José Ignacio Orlando

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!

David Romo-Bucheli, Philipp Seeböck, José Ignacio Orlando, Bianca S. Gerendas, Sebastian M. Waldstein, U Schmidt-Erfurth, Hrvoje Bogunović

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.

Anna Breger, José Ignacio Orlando, Pavol Harar, Monika Dörfler, Sophie Klimscha, Christoph Grechenig, Bianca S. Gerendas, Ursula Schmidt-Erfurth, Martin Ehler

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.

Rhona Asgari, José Ignacio Orlando, Sebastian M. Waldstein, Ferdinand Schlanitz, Magdalena Baratsits, Ursula Schmidt-Erfurth, Hrvoje Bogunović

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.

José Ignacio Orlando, Anna Breger, Hrvoje Bogunović, Sophie Riedl, Bianca S. Gerendas, Martin Ehler, Ursula Schmidt-Erfurth

Foveal Avascular Zone Segmentation in Clinical Routine Fluorescein Angiographies Using Multitask Learning

We introduced a multitask learning y-shaped neural network that simultaneously segment the FAZ in FA images and predict a distance map. This extra branch aids to improve results in clinical routine images.

Dominik Hofer, José Ignacio Orlando, Philipp Seeböck, Georgios Mylonas, Felix Goldbach, Amir Sadeghipour, Bianca S. Gerendas, Ursula Schmidt-Erfurth

REFUGE challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs

This is the summary publication of the REFUGE challenge on glaucoma detection in color fundus photographs.

José Ignacio Orlando, Huazhu Fu, João Barbossa Breda, Karel Van Keer, Deepti R. Bathula, Andrés Diaz-Pinto, Ruogu Fang, Pheng-Ann Heng, Jeyoung Kim, JoonHo Lee, Joonseok Lee, Xiaoxiao Li, Peng Liu, Shuai Lu, Balamurali Murugesan, Valery Naranjo, Sai Samarth R. Phaye, Sharath M. Shankaranarayana, Apoorva Sikka, Jaemin Son, Anton Van Den Hengel, Shujun Wang, Junyan Wu, Zifeng Wu, Guanghui Xu, Yongli Xu, Pengshuai Yin, Fei Li, Yanwu Xu, Xiulan Zhang, Hrvoje Bogunović

U2-Net: A Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans

We developed a Bayesian U-Net model for photoreceptor layer segmentation in OCT that predicts epistemic uncertainty maps highlighting potential areas of error in the segmentation.

José Ignacio Orlando, Philipp Seeböck, Hrvoje Bogunović, Sophie Klimscha, Christoph Grechenig, Sebastian M. Waldstein, Bianca S. Gerendas, Ursula Schmidt-Erfurth

Using CycleGANs for effectively reducing image variability across OCT devices and improving retinal fluid segmentation

We used CycleGANs to translate OCT images from one vendor to another. This approach allows us to increase the performance of fluid segmentation models trained on one vendor and evaluated on another.

Philipp Seeböck, David Romo-Bucheli, Sebastian Waldstein, Hrvoje Bogunović, José Ignacio Orlando, Bianca S. Gerendas, Georg Langs, Ursula Schmidt-Erfurth

Linking Function and Structure: Prediction of Retinal Sensitivity in AMD from OCT using Deep Learning

We propose a deep learning methodology to predict retinal sensitivity from OCT volumes.

Philipp Seeböck, Wolf-Dieter Vogl, Sebastian M Waldstein, Magdalena Baratsits, José Ignacio Orlando, Thomas Alten, Hrvoje Bogunovic, Mustafa Arikan, Georgios Mylonas, Ursula Schmidt-Erfurth

Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT

We used epistemic uncertainty estimates to discover potential abnormalities in diseased OCT scans. The uncertainty maps are obtained by a Bayesian U-Net trained on healthy OCT scans with weak labels of the retinal layers.

Philipp Seeböck, José Ignacio Orlando, Thomas Schlegl, Sebastian M. Waldstein, Hrvoje Bogunović, Sophie Klimscha, Georg Langs, Ursula Schmidt-Erfurth