DK: Den grundlæggende tanke bag Abrahams projekt er at kombinere registerdata med automatiseret billedanalyse ved brug af kunstig intelligens – deep learning.
UK: Abraham's project involves deep learning-based medical image segmentation for routine radiotherapy planning and to establish new dose-response relationships from historical data. The project has a focus on interactive methods for continual learning. Structures investigated include blood vessels in the lungs, organs at risk and cardiac sub-structures.
Arbejdsgrupper Publikationer- RootPainter3D: Interactive-machine-learning enables rapid and accurate contouring for radiotherapy Med Phys. 2022 Jan;49(1):461-473 2022
- Gating has a negligible impact on dose delivered in MRI-guided online adaptive radiotherapy of prostate cancer Radiother Oncol. 2022 May;170:205-212 2022
- Interfractional dose accumulation for MR-guided liver SBRT: Variation among algorithms is highly patient- and fraction-dependent Radiotherapy and Oncology 2022