Windyga P, Garreau M, Shah M, Le Breton H, Coatrieux J L
Computer Vision Laboratory, University of Central Florida, School of Computer Science, Orlando 32816, USA.
Med Biol Eng Comput. 1998 Mar;36(2):158-64. doi: 10.1007/BF02510737.
A method for 3D reconstruction of the coronary arteries from two radiographic images is presented. A novel technique for matching image structures is the main contribution of the work. After a comprehensive study of the knowledge required to approach this problem, an automatic method, which includes both numeric and symbolic procedures to solve geometric ambiguities, is developed. In the proposed method, all possible (virtual) reconstructions are first obtained. Their validity is evaluated by means of a priori knowledge about the 3D object and its projections. From the set of chosen possible solutions, the most likely solution is selected. The method is tested using real images and is implemented in a platform that allows further clinical validation.
本文提出了一种从两张X光图像重建冠状动脉三维模型的方法。一种用于匹配图像结构的新技术是这项工作的主要贡献。在全面研究了解决该问题所需的知识后，开发了一种自动方法，该方法包括解决几何模糊性的数值和符号程序。在所提出的方法中，首先获得所有可能的（虚拟）重建。通过关于三维物体及其投影的先验知识来评估它们的有效性。从选定的可能解集中，选择最可能的解。该方法使用真实图像进行了测试，并在一个允许进一步临床验证的平台上实现。
