University of Twente Student Theses
Automated Passive Marker Tracking for MR-Guided Endovascular Interventions
Braak, A.E. ter (2025) Automated Passive Marker Tracking for MR-Guided Endovascular Interventions.
|
PDF
8MB |
| Abstract: | Endovascular interventions provide a less invasive alternative to open surgery, generally guided by fluoroscopy, which exposes clinical staff and patients to ionizing radiation. Magnetic resonance imaging (MRI) offers a promising alternative, providing image guidance in any possible position and plane orientation, with excellent soft tissue contrast and free of ionizing radiation. However, the application of MRI guidance in endovascular interventions is still limited by challenges the visualization and tracking of the guidewire. This thesis addresses these challenges by developing an automated passive markertracking algorithm for interventional MRI (iMRI) suites, using a deep learning based detection approach combined with slice repositioning. The convolutional neural network (CNN) is trained with simulated representations of passive markers, which reduces the dependency on gaining extensive training data. The CNN automatically detects passive markers on real MR-images. The final solution combines the output from the CNN with a slice repositioning algorithm, and enables automated 3D passive marker tracking with a high accuracy. |
| Item Type: | Essay (Master) |
| Faculty: | TNW: Science and Technology |
| Subject: | 01 general works |
| Programme: | Biomedical Engineering MSc (66226) |
| Link to this item: | https://purl.utwente.nl/essays/106248 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page