Efficient Prealignment of CT Scans for Registration through a Bodypart RegressorDownload PDF

16 Apr 2019 (modified: 05 May 2023)MIDL Abstract 2019Readers: Everyone
Keywords: SSBR, self-supervised bodypart regressor, registration, prealignment
Abstract: Convolutional neural networks have not only been applied for classification of voxels, objects, or images, for instance, but have also been proposed as a bodypart regressor. We pick up this underexplored idea and evaluate its value for registration: A CNN is trained to output the relative height within the human body in axial CT scans, and the resulting scores are used for quick alignment between different timepoints. Preliminary results confirm that this allows both fast and robust prealignment compared with iterative approaches.
Code Of Conduct: I have read and accept the code of conduct.
Remove If Rejected: Remove submission from public view if paper is rejected.
3 Replies

Loading