发明名称 Multi-modality vertebra recognition
摘要 Systems, methods and computer program products to perform multi-modality vertebrae recognition are provided. Aspects of the present disclosure disclosed and described herein enable a multi-modality vertebrae recognition engine that recognizes vertebrae by using a three-stage recognition approach: landmark detection, global shape registration, and local pose adjustment. These stages cover the matching from local to global spine structures. The three stages are implemented by three modules in the hierarchical deformable model, the local appearance module, global geometry model, and local geometry model. According to one aspect of the present disclosure, the overall workflow can be understood as a three-stage top-down registration. The goal of the registration is: 1) to align the global shape of the spine model, and 2) to align the vertebrae poses with the local image structures around identified landmarks.
申请公布号 US9401020(B1) 申请公布日期 2016.07.26
申请号 US201514701769 申请日期 2015.05.01
申请人 London Health Science Centre Research Inc;General Electric Company 发明人 Li Shuo;Cai Yungliang;Osman Said;Landis Mark;Sharma Manas
分类号 G06K9/00;G06T7/00;G06F19/00;G06K9/62;G06T17/20;G06K9/48 主分类号 G06K9/00
代理机构 代理人
主权项 1. A computer-implemented method to recognize one or more anatomic structures in digital images, the method comprising: loading a pre-computed 3D spine mesh model with reference data comprising prior geometric measurements of the human spine; receiving image data comprising one or more images of at least one anatomic structure; generating, using a processor, one or more planar vertebra appearance templates using said one or more images; identifying vertebrae landmarks using image feature matching between said one or more images and said one or more planar vertebra appearance templates; computing, using a processor, the spine shape by aligning said vertebrae landmarks with said pre-computed 3D spine mesh model; identifying the orientation and dimension of said one or more anatomic structures using a triplanar model and group-wise registration; computing, using a processor, a 3D spine model using a hierarchical deformable model, said planar vertebra templates, said vertebra landmarks, and said spine shape; and display said computed 3D model of the spine on said computer.
地址 London CA US