Volumetric Image Registration From Invariant Keypoints
- 3 July 2017
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 26 (10), 4900-4910
- https://doi.org/10.1109/tip.2017.2722689
Abstract
We present a method for image registration based on 3D scale- and rotation-invariant keypoints. The method extends the scale invariant feature transform (SIFT) to arbitrary dimensions by making key modifications to orientation assignment and gradient histograms. Rotation invariance is proven mathematically. Additional modifications are made to extrema detection and keypoint matching based on the demands of image registration. Our experiments suggest that the choice of neighborhood in discrete extrema detection has a strong impact on image registration accuracy. In head MR images, the brain is registered to a labeled atlas with an average Dice coefficient of 92%, outperforming registration from mutual information as well as an existing 3D SIFT implementation. In abdominal CT images, the spine is registered with an average error of 4.82 mm. Furthermore, keypoints are matched with high precision in simulated head MR images exhibiting lesions from multiple sclerosis. These results were achieved using only affine transforms, and with no change in parameters across a wide variety of medical images. This paper is freely available as a cross-platform software library.Keywords
Funding Information
- National Cancer Institute, National Institutes of Health (U01CA190214, 5U01CA190214)
This publication has 23 references indexed in Scilit:
- Multiple Kernel Point Set RegistrationIEEE Transactions on Medical Imaging, 2015
- Decomposing cerebral blood flow MRI into functional and structural components: A non-local approach based on predictionNeuroImage, 2015
- Efficient and robust model-to-image alignment using 3D scale-invariant featuresMedical Image Analysis, 2012
- Object Recognition using 3D SIFT in Complex CT VolumesPublished by British Machine Vision Association and Society for Pattern Recognition ,2010
- A 3-dimensional sift descriptor and its application to action recognitionPublished by Association for Computing Machinery (ACM) ,2007
- Histograms of Oriented Gradients for Human DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Invariant Features from Interest Point GroupsPublished by British Machine Vision Association and Society for Pattern Recognition ,2002
- Scale-space theory: a basic tool for analyzing structures at different scalesJournal of Applied Statistics, 1994
- 3-D moment forms: their construction and application to object identification and positioningIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
- A Combined Corner and Edge DetectorPublished by British Machine Vision Association and Society for Pattern Recognition ,1988