Zobrazeno 1 - 10
of 4 124
pro vyhledávání: '"Zinkernagel AS"'
Autor:
Pissas, Theodoros, Márquez-Neila, Pablo, Wolf, Sebastian, Zinkernagel, Martin, Sznitman, Raphael
This work explores the effectiveness of masked image modelling for learning representations of retinal OCT images. To this end, we leverage Masked Autoencoders (MAE), a simple and scalable method for self-supervised learning, to obtain a powerful and
Externí odkaz:
http://arxiv.org/abs/2405.14788
Autor:
Ghamsarian, Negin, El-Shabrawi, Yosuf, Nasirihaghighi, Sahar, Putzgruber-Adamitsch, Doris, Zinkernagel, Martin, Wolf, Sebastian, Schoeffmann, Klaus, Sznitman, Raphael
In recent years, the landscape of computer-assisted interventions and post-operative surgical video analysis has been dramatically reshaped by deep-learning techniques, resulting in significant advancements in surgeons' skills, operation room managem
Externí odkaz:
http://arxiv.org/abs/2312.06295
Autor:
Ghamsarian, Negin, Wolf, Sebastian, Zinkernagel, Martin, Schoeffmann, Klaus, Sznitman, Raphael
Semantic Segmentation plays a pivotal role in many applications related to medical image and video analysis. However, designing a neural network architecture for medical image and surgical video segmentation is challenging due to the diverse features
Externí odkaz:
http://arxiv.org/abs/2312.03409
Publikováno v:
International Journal of Retina and Vitreous, Vol 10, Iss 1, Pp 1-7 (2024)
Abstract Purpose To assess the accuracy of High-Resolution OCT in detecting biomarkers associated with central serous chorioretinopathy (CSC) compared to standard OCT. Methods We conducted a cross-sectional study involving CSC patients who underwent
Externí odkaz:
https://doaj.org/article/0b20d3e86b5e4e609ca1389f7cef4e84
Autor:
Ghamsarian, Negin, Tejero, Javier Gamazo, Neila, Pablo Márquez, Wolf, Sebastian, Zinkernagel, Martin, Schoeffmann, Klaus, Sznitman, Raphael
Models capable of leveraging unlabelled data are crucial in overcoming large distribution gaps between the acquired datasets across different imaging devices and configurations. In this regard, self-training techniques based on pseudo-labeling have b
Externí odkaz:
http://arxiv.org/abs/2307.16660
Autor:
Jungo, Alain, Doorenbos, Lars, Da Col, Tommaso, Beelen, Maarten, Zinkernagel, Martin, Márquez-Neila, Pablo, Sznitman, Raphael
Purpose: A fundamental problem in designing safe machine learning systems is identifying when samples presented to a deployed model differ from those observed at training time. Detecting so-called out-of-distribution (OoD) samples is crucial in safet
Externí odkaz:
http://arxiv.org/abs/2304.05040
Autor:
Tejero, Javier Gamazo, Zinkernagel, Martin S., Wolf, Sebastian, Sznitman, Raphael, Neila, Pablo Márquez
Annotating new datasets for machine learning tasks is tedious, time-consuming, and costly. For segmentation applications, the burden is particularly high as manual delineations of relevant image content are often extremely expensive or can only be do
Externí odkaz:
http://arxiv.org/abs/2303.11678
Autor:
Zinkernagel, Henrik
Publikováno v:
Annalen der Physik, 2022, 534 (9), pp. 2200283 (1-6)
This essay explores the relations between aesthetics and motivation, primarily in quantum physics, focusing on the notions of play, beauty, and the joy of insight. The motivating role of these notions is examined both historically among the quantum p
Externí odkaz:
http://arxiv.org/abs/2303.09413
Autor:
Alejandro Gómez-Mejia, Mariano Orlietti, Andrea Tarnutzer, Srikanth Mairpady Shambat, Annelies S. Zinkernagel
Publikováno v:
mSphere, Vol 9, Iss 10 (2024)
ABSTRACT The human pathobiont Streptococcus pyogenes forms biofilms and causes infections, such as pharyngotonsillitis and necrotizing fasciitis. Bacterial biofilms are more resilient to antibiotic treatment, and new therapeutic strategies are needed
Externí odkaz:
https://doaj.org/article/090ca32e6e4142708f637e2585f22d53
Autor:
Nadia Keller, Mathilde Boumasmoud, Federica Andreoni, Andrea Tarnutzer, Manuela von Matt, Thomas C. Scheier, Jana Epprecht, David Weller, Alejandro Gómez-Mejia, Markus Huemer, Donata von Reibnitz, Duveken B. Y. Fontein, Ewerton Marques-Maggio, Reto A. Schuepbach, Srikanth Mairpady-Shambat, Silvio D. Brugger, Annelies S. Zinkernagel
Publikováno v:
mSphere, Vol 9, Iss 9 (2024)
ABSTRACT Group A Streptococcus (GAS) necrotizing fasciitis (NF) is a difficult-to-treat bacterial infection associated with high morbidity and mortality despite extensive surgery and targeted antibiotic treatment. Difficult-to-treat infections are of
Externí odkaz:
https://doaj.org/article/a3445359d53a4465884d6865a96d6df4