Equivariant Filters for Efficient Tracking in 3D Imaging
Authors:
- 21 September 2021
- book chapter
- Published by Springer Nature
- Vol. 12904, 193-202
Abstract
We demonstrate an object tracking method for 3D images with fixed computational cost and state-of-the-art performance. Previous methods predicted transformation parameters from convolutional layers. We instead propose an architecture that neither flattens convolutional features nor uses fully connected layers, but instead relies on equivariant filters to preserve transformations between inputs and outputs (e.g., rotations/translations of inputs rotate/translate outputs). The transformation is then derived in closed form from the outputs of the filters. This method is useful for applications requiring low latency, such as real-time tracking. We demonstrate our model on synthetically augmented adult brain MRI, as well as fetal brain MRI, which is the intended use-case.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Slice-to-volume medical image registration: A surveyMedical Image Analysis, 2017
- The WU-Minn Human Connectome Project: An overviewNeuroImage, 2013
- Motion-Compensation Techniques in Neonatal and Fetal MR ImagingAmerican Journal of Neuroradiology, 2012
- PROMO: Real‐time prospective motion correction in MRI using image‐based trackingMagnetic Resonance in Medicine, 2009
- Real-time 3D image registration for functional MRIMagnetic Resonance in Medicine, 1999
- Motion correction with PROPELLER MRI: Application to head motion and free-breathing cardiac imagingMagnetic Resonance in Medicine, 1999
- Automated Image Registration: I. General Methods and Intrasubject, Intramodality ValidationJournal of Computer Assisted Tomography, 1998
- Least-Squares Fitting of Two 3-D Point SetsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1987
- Closed-form solution of absolute orientation using unit quaternionsJournal of the Optical Society of America A, 1987
- A solution for the best rotation to relate two sets of vectorsActa Crystallographica Section A, 1976