Automatic Reconstruction of 3D Geometry Using Projections and a Geometric Prior Model
MICCAI '99 Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention
Interactive Medical Image Segmentation with United Snakes
MICCAI '99 Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention
Automatic Contour Detection by Encoding Knowledge into Active Contour Models
WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Multi-component heart reconstruction from volumetric imaging
Proceedings of the 2008 ACM symposium on Solid and physical modeling
Automatic extraction of 3d dynamic left ventricle model from 2d rotational angiocardiogram
MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III
Hi-index | 0.00 |
Individual 3D boundary element models can be used in solving inverse problems in electro- and magnetocardiographic measurements. In some cases 3D data, such as Magnetic Resonance (MR) or Computed Tomography (CT) images, are not available. Therefore, it would be useful to be able to use 2D images such as X-ray projections for creating 3D models. The aim of this work was to develop a software package for creating a 3D boundary element heart model from two orthogonal X-ray projections. The biplane fluoroscopy images from a patient are digitized and the images are enhanced with different image processing techniques. The patient heart outline is segmented from the X-ray projections. The outline is compared with virtual X-ray projections created from a prior 3D model segmented from MR images. The difference between the outlines is used to deform the prior model. The quality of the digitized X-ray projections was noticeably improved and thus the heart outline segmentation was facilitated. The deformation method implemented is robust and provides good results even when the source parameters contain errors.