Publicaties

1 - 10 of 2209 resultaten

Zoek term:

Image Compositing for Segmentation of Surgical Tools Without Manual Annotations. KU Leuven

Luis C Garcia-Peraza-Herrera, Lucas Fidon, Claudia D'Ettorre, Danail Stoyanov, Tom Vercauteren, Sebastien Ourselin
Producing manual, pixel-accurate, image segmentation labels is tedious and time-consuming. This is often a rate-limiting factor when large amounts of labeled images are required, such as for training deep convolutional networks for instrument-background segmentation in surgical scenes. No large datasets comparable to industry standards in the computer vision community are available for this task. To circumvent this problem, we propose to ...

Neural probabilistic logic programming in DeepProbLog KU Leuven

Robin Manhaeve, Sebastijan Dumancic, Angelika Kimmig, Thomas Demeester, Luc De Raedt
We introduce DeepProbLog, a neural probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques of the underlying probabilistic logic programming language ProbLog can be adapted for the new language. We theoretically and experimentally demonstrate that DeepProbLog supports (i) both symbolic and subsymbolic representations and inference, (ii) program ...

StkTokens: Enforcing well-bracketed control flow and stack encapsulation using linear capabilities Vrije Universiteit Brussel

LAU SKORSTENGAARD, Dominique Devriese, LARS BIRKEDAL

We propose and study StkTokens: A new calling convention that provably enforces well-bracketed control flow and local state encapsulation on a capability machine. The calling convention is based on linear capabilities: A type of capabilities that are prevented from being duplicated by the hardware. In addition to designing and formalizing this new calling convention, we also contribute a new way to formalize and prove that it effectively ...

Detection of parathyroid adenomas with multiphase 4DCT Vrije Universiteit Brussel

Steven Raeymaeckers, Yannick De Brucker, Tim Vanderhasselt, Nico Buls, Johan De Mey

BACKGROUND: Four-dimensional computed tomography (4DCT) is a commonly performed examination in the management of primary hyperparathyroidism, combining three-dimensional imaging with enhancement over time as the fourth dimension. We propose a novel technique consisting of 16 different contrast phases instead of three or four different phases. The main aim of this study was to ascertain whether this protocol allows the detection of parathyroid ...

Designing Interpretable Recurrent Neural Networks for Video Reconstruction Via Deep Unfolding Vrije Universiteit Brussel

Van Huynh Luong, Boris Joseph Joukovsky, Nikos Deligiannis
Deep unfolding methods design deep neural networks as learned variations of optimization algorithms through the unrolling of their iterations. These networks have been shown to achieve faster convergence and higher accuracy than the original optimization methods. In this line of research, this paper presents novel interpretable deep recurrent neural networks (RNNs), designed by the unfolding of iterative algorithms that solve the task of ...

Toward the inclusion of end-to-end security in the OM2M platform Vrije Universiteit Brussel

Simone Patonico, Thanh Long Nguyen, Placide Shabisha, An Braeken, Kris Steenhaut

The exponential growth in the number of Internet of things (IoT) devices and their potential in many applications in a vast number of domains fuelled the development of different IoT platforms, supported by big companies and industry groups. These platforms are able to provide reliable services to IoT devices and reduce the time to market for the targeted applications. Unfortunately, these proprietary solutions fragment the IoT market and ...

Hilbert sEMG data scanning for hand gesture recognition based on deep learning Vrije Universiteit Brussel

Panagiotis Tsinganos, Bruno Cornelis, Bart Jansen, Jan Paul Cornelis, Athanassios Skodras
Deep learning has transformed the field of data analysis by dramatically improving the state of the art in various classification and prediction tasks, especially in the area of computer vision. In biomedical engineering, a lot of new work is directed toward surface electromyography (sEMG)-based gesture recognition, often addressed as an image classification problem using convolutional neural networks (CNNs). In this paper, we utilize the ...

Computational strategies to combat COVID-19: useful tools to accelerate SARS-CoV-2 and coronavirus research. KU Leuven

Franziska Hufsky, Kevin Lamkiewicz, Alexandre Almeida, Abdel Aouacheria, Cecilia Arighi, Alex Bateman, Jan Baumbach, Niko Beerenwinkel, Christian Brandt, Marco Cacciabue, et al.
SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) is a novel virus of the family Coronaviridae. The virus causes the infectious disease COVID-19. The biology of coronaviruses has been studied for many years. However, bioinformatics tools designed explicitly for SARS-CoV-2 have only recently been developed as a rapid reaction to the need for fast detection, understanding and treatment of COVID-19. To control the ongoing COVID-19 ...