In vivo imaging experiments often require automated detection and tracking of changes in the specimen. These tasks canbe hindered by variations in the position and orientation of the specimen relative to the microscope, as well as by linearand nonlinear tissue deformations. We propose a feature-based registration method, coupled with optimaltransformations, designed to address these problems in 3D time-lapse microscopy images. Features are detected as localregions of maximum intensity in source and target image stacks, and their bipartite intensity dissimilarity matrix is usedas an input to the Hungarian algorithm to establish initial correspondences. A random sampling refinement method isemployed to eliminate outliers, and the resulting set of corresponding features is used to determine an optimaltranslation, rigid, affine, or B-spline transformation for the registration of the source and target images. Accuracy of theproposed algorithm was tested on fluorescently labeled axons imaged over a 68-day period with a two-photon laserscanning microscope. To that end, multiple axons in individual stacks of images were traced semi-manually andoptimized in 3D, and the distances between the corresponding traces were measured before and after the registration.The results show that there is a progressive improvement in the registration accuracy with increasing complexity of thetransformations. In particular, sub-micrometer accuracy (2-3 voxels) was achieved with the regularized affine and Bsplinetransformations.
展开▼
