27 citations
- Norwegian University of Science and TechnologyNO7 papers
- University of OsloNO2 papers
- Bjerknes Centre for Climate ResearchNO1 paper
- Dutch Cancer SocietyNL1 paper
- Earth Science Institute of the Slovak Academy of SciencesSK1 paper
- Federal Institute of HydrologyDE1 paper
- Haukeland University HospitalNO1 paper
- Imperial College LondonGB1 paper
- King's College LondonGB1 paper
- Met OfficeGB1 paper
- NOAA Oceanic and Atmospheric ResearchUS1 paper
- Norwegian Institute for Nature ResearchNO1 paper
8 papers
FedGIN: Federated Learning with Dynamic Global Intensity Non-linear Augmentation for Organ Segmentation using Multi-modal Images
Sachin Dudda Nagaraju, Ashkan Moradi, Bendik Skarre Abrahamsen +1
Medical image segmentation plays a crucial role in AI-assisted diagnostics, surgical planning, and treatment monitoring. Accurate and robust segmentation models are essential for e…
Optimizing Federated Learning Configurations for MRI Prostate Segmentation and Cancer Detection: A Simulation Study
Ashkan Moradi, Fadila Zerka, Joeran S. Bosma +7
Purpose: To develop and optimize a federated learning (FL) framework across multiple clients for biparametric MRI prostate segmentation and clinically significant prostate cancer (…
The unbearable lightness of Restricted Boltzmann Machines: Theoretical Insights and Biological Applications
Giovanni di Sarra, Barbara Bravi, Yasser Roudi
Restricted Boltzmann Machines are simple yet powerful neural networks. They can be used for learning structure in data, and are used as a building block of more complex neural arch…
Choose Your Explanation: A Comparison of SHAP and GradCAM in Human Activity Recognition
Felix Tempel, Daniel Groos, Espen Alexander F. Ihlen +2
Explaining machine learning (ML) models using eXplainable AI (XAI) techniques has become essential to make them more transparent and trustworthy. This is especially important in hi…
A novel imaging setup for hybrid radiotherapy tailored PET/MR in patients with head and neck cancer
R. M. Winter, O. Engelsen, O. J. Bratting +4
Purpose: Radiotherapy commonly relies on CT, but there is growing interest in using hybrid PET/MR. Therefore, dedicated hardware setups have been proposed for PET/MR systems which…
Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative Measures
Felix Tempel, Espen Alexander F. Ihlen, Lars Adde +1
In Human Activity Recognition (HAR), understanding the intricacy of body movements within high-risk applications is essential. This study uses SHapley Additive exPlanations (SHAP)…