Deep Learning | José Ignacio Orlando

Improving realism in patient-specific abdominal ultrasound simulation using CycleGANs

We applied CycleGANs to improve realism in ultrasound simulation based on ray-casting methods.

Santiago Vitale, José Ignacio Orlando, Emmanuel Iarussi, Ignacio Larrabide

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

An ensemble deep learning based approach for red lesion detection in fundus images

We introduced a hybrid red lesion detection model based on a combination of deep learning based features and hand crafted descriptors.

José Ignacio Orlando, Elena Prokofyeva, Mariana Del Fresno, Matthew B. Blaschko

Aprendizaje automático para asistencia al diagnóstico de enfermedades visuales basado en imágenes de fondo de ojo (Machine learning for ophthalmic screening and diagnostics from fundus images)

My PhD thesis.

José Ignacio Orlando