109 citations · 186 across the 8 of their papers we have counts for
8 papers
SR-GAN for SR-gamma: super resolution of photon calorimeter images at collider experiments
Johannes Erdmann, Aaron van der Graaf, Florian Mausolf +1
We study single-image super-resolution algorithms for photons at collider experiments based on generative adversarial networks. We treat the energy depositions of simulated electro…
Accurate and fast deep learning dose prediction for a preclinical microbeam radiation therapy study using low-statistics Monte Carlo simulations
Florian Mentzel, Jason Paino, Micah Barnes +13
Microbeam radiation therapy (MRT) utilizes coplanar synchrotron radiation beamlets and is a proposed treatment approach for several tumour diagnoses that currently have poor clinic…
A step towards treatment planning for microbeam radiation therapy: fast peak and valley dose predictions with 3D U-Nets
Florian Mentzel, Micah Barnes, Kevin Kröninger +9
Fast and accurate dose predictions are one of the bottlenecks in treatment planning for microbeam radiation therapy (MRT). In this paper, we propose a machine learning (ML) model b…
Fast and accurate dose predictions for novel radiotherapy treatments in heterogeneous phantoms using conditional 3D-UNet generative adversarial networks
Florian Mentzel, Kevin Kröninger, Michael Lerch +8
Novel radiotherapy techniques like synchrotron X-ray microbeam radiation therapy (MRT), require fast dose distribution predictions that are accurate at the sub-mm level, especially…
No more glowing in the dark: How deep learning improves exposure date estimation in thermoluminescence dosimetry
Florian Mentzel, Evelin Derugin, Hannah Jansen +4
The time- or temperature-resolved detector signal from a thermoluminescence dosimeter can reveal additional information about circumstances of an exposure to ionizing irradiation.…
Maximum performance of strange-jet tagging at hadron colliders
Johannes Erdmann, Olaf Nackenhorst, Sonja Verena Zeißner
The maximum achievable performance of strange-jet tagging at hadron colliders and the loss in performance in different detector designs is estimated based on simulated truth jets f…
From the Bottom to the Top -- Reconstruction of Events with Deep Learning
Johannes Erdmann, Tim Kallage, Kevin Kröninger +1
The reconstruction of top-quark pair-production () events is a prerequisite for many top-quark measurements. We use a deep neural network, trained with Monte-Carlo simula…
A likelihood-based reconstruction algorithm for top-quark pairs and the KLFitter framework
Johannes Erdmann, Stefan Guindon, Kevin Kroeninger +4
A likelihood-based reconstruction algorithm for arbitrary event topologies is introduced and, as an example, applied to the single-lepton decay mode of top-quark pair production. T…