Real time tracking of 3D organ surfaces using single MR image and limited optical viewing

Authors:
Dan Wang;Ahmed H. Tewfik
Affiliations:
Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN;Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN
Venue:
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Year:
2010

Citing 5
Cited 1

A Method for Registration of 3-D Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
A Real-Time Algorithm for Medical Shape Recovery

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Multimodal 3D Shape Recovery from Texture, Silhouette and Shadow Information

3DPVT '06 Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)
Sparse representation of deformable 3D organs

ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
In vivo tracking of 3D organs using spherical harmonics and subspace clustering

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing

Sparse representation of deformable 3D organs with spherical harmonics and structured dictionary

Journal of Biomedical Imaging - Special issue on Machine Learning in Medical Imaging

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents the first demonstration of real time 3D tracking of organ deformation based on one-sided, limited view needlescopic optical imaging and a single preoperative MRIICT scan. The reconstruction is based on the empirical observation that the spherical harmonic coefficients corresponding to distorted surfaces of any given organ lie in lower dimensional spaces that can be learned during training. The paper discusses the details of the selection of the limited optical views and the registration of the real time partial optical images with the single pre-operative MRIlCT scan. Finally, it demonstrates the first experimental 3D reconstruction of exvivo kidneys based on a single MRI scan with 1 mm resolution and real time single side optical imagery achieving spatial resolution of better than 2 mm, even on the hidden organ surface, or less than 1.85% relative error.