A5012603029- Medical Image Segmentation Techniques
- Medical Imaging Techniques and Applications
- Medical Imaging and Analysis
- AI in cancer detection
- Reservoir Engineering and Simulation Methods
- Radiomics and Machine Learning in Medical Imaging
- Opportunistic and Delay-Tolerant Networks
- Mobile Ad Hoc Networks
- Stochastic processes and statistical mechanics
- Advanced Neural Network Applications
- Machine Learning in Healthcare
- Cooperative Communication and Network Coding
- Public Relations and Crisis Communication
- Complex Network Analysis Techniques
- Opinion Dynamics and Social Influence
- Advanced MRI Techniques and Applications
- Energy Efficient Wireless Sensor Networks
- Geological Modeling and Analysis
- Advanced Vision and Imaging
- Diffusion and Search Dynamics
- Media Studies and Communication
- CO2 Sequestration and Geologic Interactions
Uppsala University
2006-2023
Elekta (Sweden)
2022
Image registration is a fundamental medical image analysis task, and wide variety of approaches have been proposed. However, only few studies comprehensively compared on range clinically relevant tasks. This limits the development methods, adoption research advances into practice, fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing multi-task data set for comprehensive characterisation deformable algorithms. A continuous evaluation...
A wireless multi-hop sensor network, in which node positions are fixed, may fail to transmit a message over longer distances. This could occur, for example, due low density or small transmission range. In mobile systems where nodes allowed move, it is natural expect better reachability, with the condition that messages not time-critical and propagation delays permitted. order understand relation of mobility range, we study simple network model active sensors move according independent...
Spatiotemporal imaging has applications in e.g. cardiac diagnostics, surgical guidance, and radiotherapy monitoring, In this paper, we explain the temporal motion by identifying underlying dynamics, only based on sequential images. Our dynamical model maps inputs of observed high-dimensional images to a low-dimensional latent space wherein linear relationship between hidden state process lower-dimensional representation holds. For this, use conditional variational auto-encoder (CVAE)...
Our anatomy is in constant motion. With modern MR imaging it possible to record this motion real-time during an ongoing radiation therapy session. In paper we present image registration method that exploits the sequential nature of 2D images estimate corresponding displacement field. The employs several discriminative correlation filters independently track specific points. Together with a sparse-to-dense interpolation scheme can then are trained online, and our modality agnostic. For use...
Image registration is a fundamental medical image analysis task, and wide variety of approaches have been proposed. However, only few studies comprehensively compared on range clinically relevant tasks. This limits the development methods, adoption research advances into practice, fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing multi-task data set for comprehensive characterisation deformable algorithms. A continuous evaluation...
Intra-interventional imaging is a tool for monitoring and guiding ongoing treatment sessions. Ideally one would like the full 3D image at high temporal resolution, this however not possible due to acquisition time. In study, we consider scenario when observations are sparse consist only of 2D slices through volume. Given 2D-2D registrations between predefined volume observations, propose method estimate motion. This motion enables reconstruction anatomy. Our relies on conditioning-based...
Spatiotemporal imaging has applications in e.g. cardiac diagnostics, surgical guidance, and radiotherapy monitoring, In this paper, we explain the temporal motion by identifying underlying dynamics, only based on sequential images. Our dynamical model maps inputs of observed high-dimensional images to a low-dimensional latent space wherein linear relationship between hidden state process lower-dimensional representation holds. For this, use conditional variational auto-encoder (CVAE)...