Scale-Space and Edge Detection Using Anisotropic Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention
Instance-based generative biological shape modeling
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Hi-index | 0.00 |
We present an intensity-based non-rigid registration approach for normalizing 3D multi-channel microscopy images of cell nuclei. A main problem with cell nuclei images is that the intensity structure of different nuclei differs very much, thus an intensity-based registration scheme cannot be used directly. Instead, we first perform a segmentation of the images, smooth them by a Gaussian filter, and then apply an intensity-based algorithm. To improve the convergence rate of the algorithm, we propose an adaptive step length optimization scheme and also employ a multi-resolution scheme. Our approach has been successfully applied using 2D cell-like synthetic images, 3D phantom images as well as 3D multi-channel microscopy images representing different chromosome territories and gene regions (BACs). We also describe an extension of our approach which is applied for the registration of 3D+t (4D) image series of moving cell nuclei.