1 code implementation • 30 Jan 2024 • Vladyslav Andriiashen, Robert van Liere, Tristan van Leeuwen, K. Joost Batenburg
We show how a calibrated image generation model can be used to quantitatively evaluate the effect of the X-ray exposure time on the performance of the inspection system.
no code implementations • 1 Sep 2023 • Jiayang Shi, Daniel M. Pelt, K. Joost Batenburg
As an alternative, we propose a multi-stage deep learning method for artifact removal, in which neural networks are applied to several domains, similar to a classical CT processing pipeline.
2 code implementations • 9 Jun 2023 • Maximilian B. Kiss, Sophia B. Coban, K. Joost Batenburg, Tristan van Leeuwen, Felix Lucka
We fill this gap by providing the community with a versatile, open 2D fan-beam CT dataset suitable for developing ML techniques for a range of image reconstruction tasks.
1 code implementation • 22 May 2023 • Vladyslav Andriiashen, Robert van Liere, Tristan van Leeuwen, K. Joost Batenburg
X-ray scattering is known to be computationally expensive to simulate, and this effect can heavily influence the accuracy of a generated X-ray image.
2 code implementations • 8 Dec 2020 • Ajinkya Kadu, Tristan van Leeuwen, K. Joost Batenburg
We introduce single-shot X-ray tomography that aims to estimate the target image from a single cone-beam projection measurement.
1 code implementation • 13 Nov 2020 • Richard Schoonhoven, Allard A. Hendriksen, Daniël M. Pelt, K. Joost Batenburg
Neural network pruning techniques can substantially reduce the computational cost of applying convolutional neural networks (CNNs).
no code implementations • 1 Oct 2020 • Marinus J. Lagerwerf, Daniel M. Pelt, Willem Jan Palenstijn, K. Joost Batenburg
Moreover, we show that the training time of an NN-FDK network is orders of magnitude lower than the considered deep neural networks, with only a slight reduction in reconstruction accuracy.
no code implementations • 3 Jul 2020 • Marinus J. Lagerwerf, Allard A. Hendriksen, Jan-Willem Buurlage, K. Joost Batenburg
To overcome this issue, we propose Noise2Filter, a learned filter method that can be trained using only the measured data, and does not require any additional training data.
no code implementations • 15 May 2020 • Maureen van Eijnatten, Leonardo Rundo, K. Joost Batenburg, Felix Lucka, Emma Beddowes, Carlos Caldas, Ferdia A. Gallagher, Evis Sala, Carola-Bibiane Schönlieb, Ramona Woitek
This study showed the feasibility of deep learning based deformable registration of longitudinal abdominopelvic CT images via a novel incremental training strategy based on simulated deformations.
1 code implementation • 31 Jan 2020 • Allard A. Hendriksen, Daniel M. Pelt, K. Joost Batenburg
Recovering a high-quality image from noisy indirect measurements is an important problem with many applications.