no code implementations • 12 Mar 2024 • Chengzhi Shen, Martin J. Menten, Hrvoje Bogunović, Ursula Schmidt-Erfurth, Hendrik Scholl, Sobha Sivaprasad, Andrew Lotery, Daniel Rueckert, Paul Hager, Robbie Holland
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.
1 code implementation • 2 Feb 2024 • José Morano, Guilherme Aresta, Christoph Grechenig, Ursula Schmidt-Erfurth, Hrvoje Bogunović
The use of multimodal imaging has led to significant improvements in the diagnosis and treatment of many diseases.
no code implementations • 28 Dec 2023 • Taha Emre, Arunava Chakravarty, Antoine Rivail, Dmitrii Lachinov, Oliver Leingang, Sophie Riedl, Julia Mai, Hendrik P. N. Scholl, Sobha Sivaprasad, Daniel Rueckert, Andrew Lotery, Ursula Schmidt-Erfurth, Hrvoje Bogunović
Self-supervised learning (SSL) has emerged as a powerful technique for improving the efficiency and effectiveness of deep learning models.
no code implementations • 25 Jul 2023 • Taha Emre, Marzieh Oghbaie, Arunava Chakravarty, Antoine Rivail, Sophie Riedl, Julia Mai, Hendrik P. N. Scholl, Sobha Sivaprasad, Daniel Rueckert, Andrew Lotery, Ursula Schmidt-Erfurth, Hrvoje Bogunović
In the field of medical imaging, 3D deep learning models play a crucial role in building powerful predictive models of disease progression.
1 code implementation • 13 Jul 2023 • Marzieh Oghbaie, Teresa Araujo, Taha Emre, Ursula Schmidt-Erfurth, Hrvoje Bogunovic
Consequently, the accumulated positional information in each positional embedding can be generalized to the neighbouring slices, even for high-resolution volumes at the test time.
1 code implementation • 6 Jul 2023 • José Morano, Guilherme Aresta, Dmitrii Lachinov, Julia Mai, Ursula Schmidt-Erfurth, Hrvoje Bogunović
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.
no code implementations • 17 Apr 2023 • Arunava Chakravarty, Taha Emre, Oliver Leingang, Sophie Riedl, Julia Mai, Hendrik P. N. Scholl, Sobha Sivaprasad, Daniel Rueckert, Andrew Lotery, Ursula Schmidt-Erfurth, Hrvoje Bogunović
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.
no code implementations • 11 Jan 2023 • Robbie Holland, Oliver Leingang, Christopher Holmes, Philipp Anders, Rebecca Kaye, Sophie Riedl, Johannes C. Paetzold, Ivan Ezhov, Hrvoje Bogunović, Ursula Schmidt-Erfurth, Lars Fritsche, Hendrik P. N. Scholl, Sobha Sivaprasad, Andrew J. Lotery, Daniel Rueckert, Martin J. Menten
Age-related macular degeneration (AMD) is the leading cause of blindness in the elderly.
no code implementations • 8 Nov 2022 • Dmitrii Lachinov, Arunava Chakravarty, Christoph Grechenig, Ursula Schmidt-Erfurth, Hrvoje Bogunovic
Our method represents a time-invariant physical process and solves a large-scale problem of modeling temporal pixel-level changes utilizing NeuralODEs.
no code implementations • 26 Oct 2022 • Botond Fazekas, Dmitrii Lachinov, Guilherme Aresta, Julia Mai, Ursula Schmidt-Erfurth, Hrvoje Bogunovic
Bruch's membrane (BM) segmentation on optical coherence tomography (OCT) is a pivotal step for the diagnosis and follow-up of age-related macular degeneration (AMD), one of the leading causes of blindness in the developed world.
no code implementations • 8 Aug 2022 • Thomas Schlegl, Heiko Stino, Michael Niederleithner, Andreas Pollreisz, Ursula Schmidt-Erfurth, Wolfgang Drexler, Rainer A. Leitgeb, Tilman Schmoll
The automatic detection and localization of anatomical features in retinal imaging data are relevant for many aspects.
no code implementations • 4 Aug 2022 • Robbie Holland, Oliver Leingang, Hrvoje Bogunović, Sophie Riedl, Lars Fritsche, Toby Prevost, Hendrik P. N. Scholl, Ursula Schmidt-Erfurth, Sobha Sivaprasad, Andrew J. Lotery, Daniel Rueckert, Martin J. Menten
This is exacerbated in longitudinal image datasets that repeatedly image the same patient cohort to monitor their disease progression over time.
1 code implementation • 1 Jul 2022 • Botond Fazekas, Guilherme Aresta, Dmitrii Lachinov, Sophie Riedl, Julia Mai, Ursula Schmidt-Erfurth, Hrvoje Bogunovic
Optical coherence tomography (OCT) is a non-invasive 3D modality widely used in ophthalmology for imaging the retina.
1 code implementation • 30 Jun 2022 • Taha Emre, Arunava Chakravarty, Antoine Rivail, Sophie Riedl, Ursula Schmidt-Erfurth, Hrvoje Bogunović
Recent contrastive learning methods achieved state-of-the-art in low label regimes.
no code implementations • 13 Sep 2021 • Anna Breger, Felix Goldbach, Bianca S. Gerendas, Ursula Schmidt-Erfurth, Martin Ehler
The results underline the visual evaluation.
no code implementations • 2 Aug 2021 • Dmitrii Lachinov, Philipp Seeboeck, Julia Mai, Ursula Schmidt-Erfurth, Hrvoje Bogunovic
In medical imaging, there are clinically relevant segmentation tasks where the output mask is a projection to a subset of input image dimensions.
no code implementations • 11 Dec 2019 • Rhona Asgari, Sebastian Waldstein, Ferdinand Schlanitz, Magdalena Baratsits, Ursula Schmidt-Erfurth, Hrvoje Bogunović
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.
no code implementations • 21 Oct 2019 • Antoine Rivail, Ursula Schmidt-Erfurth, Wolf-Dieter Vogl, Sebastian M. Waldstein, Sophie Riedl, Christoph Grechenig, Zhichao Wu, Hrvoje Bogunović
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.
no code implementations • 2 Aug 2019 • José Ignacio Orlando, Anna Breger, Hrvoje Bogunović, Sophie Riedl, Bianca S. Gerendas, Martin Ehler, Ursula Schmidt-Erfurth
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.
no code implementations • 18 Jun 2019 • Rhona Asgari, José Ignacio Orlando, Sebastian Waldstein, Ferdinand Schlanitz, Magdalena Baratsits, Ursula Schmidt-Erfurth, Hrvoje Bogunović
We also introduce connections between each class-specific branch and the additional decoder to increase the regularization effect of this surrogate task.
no code implementations • 29 May 2019 • Philipp Seeböck, José Ignacio Orlando, Thomas Schlegl, Sebastian M. Waldstein, Hrvoje Bogunović, Sophie Klimscha, Georg Langs, Ursula Schmidt-Erfurth
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.
no code implementations • 24 Jan 2019 • Philipp Seeböck, David Romo-Bucheli, Sebastian Waldstein, Hrvoje Bogunović, José Ignacio Orlando, Bianca S. Gerendas, Georg Langs, Ursula Schmidt-Erfurth
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.
no code implementations • 23 Jan 2019 • José Ignacio Orlando, Philipp Seeböck, Hrvoje Bogunović, Sophie Klimscha, Christoph Grechenig, Sebastian Waldstein, Bianca S. Gerendas, Ursula Schmidt-Erfurth
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
1 code implementation • 22 Jan 2019 • Anna Breger, Jose Ignacio Orlando, Pavol Harar, Monika Dörfler, Sophie Klimscha, Christoph Grechenig, Bianca S. Gerendas, Ursula Schmidt-Erfurth, Martin Ehler
In two supervised learning problems, clinical image segmentation and music information classification, the application of our proposed augmented target loss functions increase the accuracy.
no code implementations • 31 Oct 2018 • Philipp Seeböck, Sebastian M. Waldstein, Sophie Klimscha, Hrvoje Bogunovic, Thomas Schlegl, Bianca S. Gerendas, René Donner, Ursula Schmidt-Erfurth, Georg Langs
A multi-scale deep denoising autoencoder is trained on healthy images, and a one-class support vector machine identifies anomalies in new data.
no code implementations • 8 May 2018 • Thomas Schlegl, Hrvoje Bogunovic, Sophie Klimscha, Philipp Seeböck, Amir Sadeghipour, Bianca Gerendas, Sebastian M. Waldstein, Georg Langs, Ursula Schmidt-Erfurth
The automatic detection of disease related entities in retinal imaging data is relevant for disease- and treatment monitoring.
18 code implementations • 17 Mar 2017 • Thomas Schlegl, Philipp Seeböck, Sebastian M. Waldstein, Ursula Schmidt-Erfurth, Georg Langs
Obtaining models that capture imaging markers relevant for disease progression and treatment monitoring is challenging.
Generative Adversarial Network Unsupervised Anomaly Detection
no code implementations • 2 Dec 2016 • Philipp Seeböck, Sebastian Waldstein, Sophie Klimscha, Bianca S. Gerendas, René Donner, Thomas Schlegl, Ursula Schmidt-Erfurth, Georg Langs
The identification and quantification of markers in medical images is critical for diagnosis, prognosis and management of patients in clinical practice.