Zobrazeno 1 - 10
of 4 692
pro vyhledávání: '"Erfurth A."'
Autor:
Chakravarty, Arunava, Emre, Taha, Lachinov, Dmitrii, Rivail, Antoine, Scholl, Hendrik, Fritsche, Lars, Sivaprasad, Sobha, Rueckert, Daniel, Lotery, Andrew, Schmidt-Erfurth, Ursula, Bogunović, Hrvoje
Predicting future disease progression risk from medical images is challenging due to patient heterogeneity, and subtle or unknown imaging biomarkers. Moreover, deep learning (DL) methods for survival analysis are susceptible to image domain shifts ac
Externí odkaz:
http://arxiv.org/abs/2409.20195
Autor:
Holland, Robbie, Taylor, Thomas R. P., Holmes, Christopher, Riedl, Sophie, Mai, Julia, Patsiamanidi, Maria, Mitsopoulou, Dimitra, Hager, Paul, Müller, Philip, Scholl, Hendrik P. N., Bogunović, Hrvoje, Schmidt-Erfurth, Ursula, Rueckert, Daniel, Sivaprasad, Sobha, Lotery, Andrew J., Menten, Martin J.
Clinicians spend a significant amount of time reviewing medical images and transcribing their findings regarding patient diagnosis, referral and treatment in text form. Vision-language models (VLMs), which automatically interpret images and summarize
Externí odkaz:
http://arxiv.org/abs/2407.08410
Autor:
Emre, Taha, Chakravarty, Arunava, Lachinov, Dmitrii, Rivail, Antoine, Schmidt-Erfurth, Ursula, Bogunović, Hrvoje
Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously preventing representational collapse. Equivariant contrastive learning, on the other hand, provides represent
Externí odkaz:
http://arxiv.org/abs/2405.09404
Autor:
Holland, Robbie, Kaye, Rebecca, Hagag, Ahmed M., Leingang, Oliver, Taylor, Thomas R. P., Bogunović, Hrvoje, Schmidt-Erfurth, Ursula, Scholl, Hendrik P. N., Rueckert, Daniel, Lotery, Andrew J., Sivaprasad, Sobha, Menten, Martin J.
Diseases are currently managed by grading systems, where patients are stratified by grading systems into stages that indicate patient risk and guide clinical management. However, these broad categories typically lack prognostic value, and proposals f
Externí odkaz:
http://arxiv.org/abs/2405.09549
Autor:
Shen, Chengzhi, Menten, Martin J., Bogunović, Hrvoje, Schmidt-Erfurth, Ursula, Scholl, Hendrik, Sivaprasad, Sobha, Lotery, Andrew, Rueckert, Daniel, Hager, Paul, Holland, Robbie
Analyzing temporal developments is crucial for the accurate prognosis of many medical conditions. Temporal changes that occur over short time scales are key to assessing the health of physiological functions, such as the cardiac cycle. Moreover, trac
Externí odkaz:
http://arxiv.org/abs/2403.07513
Autor:
Morano, José, Aresta, Guilherme, Grechenig, Christoph, Schmidt-Erfurth, Ursula, Bogunović, Hrvoje
The use of multimodal imaging has led to significant improvements in the diagnosis and treatment of many diseases. Similar to clinical practice, some works have demonstrated the benefits of multimodal fusion for automatic segmentation and classificat
Externí odkaz:
http://arxiv.org/abs/2402.01311
Autor:
Emre, Taha, Chakravarty, Arunava, Rivail, Antoine, Lachinov, Dmitrii, Leingang, Oliver, Riedl, Sophie, Mai, Julia, Scholl, Hendrik P. N., Sivaprasad, Sobha, Rueckert, Daniel, Lotery, Andrew, Schmidt-Erfurth, Ursula, Bogunović, Hrvoje
Self-supervised learning (SSL) has emerged as a powerful technique for improving the efficiency and effectiveness of deep learning models. Contrastive methods are a prominent family of SSL that extract similar representations of two augmented views o
Externí odkaz:
http://arxiv.org/abs/2312.16980
Autor:
Klaudia Birner, Gregor S. Reiter, Irene Steiner, Gábor Deák, Hamza Mohamed, Simon Schürer-Waldheim, Markus Gumpinger, Hrvoje Bogunović, Ursula Schmidt-Erfurth
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-11 (2024)
Abstract To examine the morphological impact of deep learning (DL)-quantified biomarkers on point-wise sensitivity (PWS) using microperimetry (MP) and optical coherence tomography (OCT) in intermediate AMD (iAMD). Patients with iAMD were examined by
Externí odkaz:
https://doaj.org/article/c56a2ad960164f47ba5b60b3aa1a1634
Autor:
Emese Sükei, Elisabeth Rumetshofer, Niklas Schmidinger, Andreas Mayr, Ursula Schmidt-Erfurth, Günter Klambauer, Hrvoje Bogunović
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-12 (2024)
Abstract Self-supervised learning has become the cornerstone of building generalizable and transferable artificial intelligence systems in medical imaging. In particular, contrastive representation learning techniques trained on large multi-modal dat
Externí odkaz:
https://doaj.org/article/e132d120c2c040fc82016fb1d5498e81
Autor:
Heiko Stino, Klaudia Birner, Laetitia Hinterhuber, Alexandra Struppe, Markus Gumpinger, Simon Schürer-Waldheim, Hrvoje Bogunovic, Ursula Schmidt-Erfurth, Andreas Pollreisz, Gregor S. Reiter
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-9 (2024)
Abstract To evaluate the intra- and interdevice repeatability of microperimetry (MP) assessments in patients with diabetic macular edema (DME) two consecutive MP testings (45 fovea-centered stimuli, 4–2 staircase strategy) were performed using MP3
Externí odkaz:
https://doaj.org/article/f8670c1a64bd4d3d8200cc68dfb54dec