| 发明名称 | Finding similar coronary angiograms in a database | ||
| 摘要 | Embodiments relate to finding similar coronary angiograms in a database of coronary angiograms. An aspect includes receiving angiography data for a coronary artery, processing the angiography data to identify one or more semantic features of the coronary artery, and identifying one or more nearest coronary angiograms for each of the one or more semantic features from the database of coronary angiograms. The method also includes receiving a disease attribute associated with each of the one or more nearest coronary angiograms. | ||
| 申请公布号 | US9135272(B2) | 申请公布日期 | 2015.09.15 |
| 申请号 | US201314045869 | 申请日期 | 2013.10.04 |
| 申请人 | International Business Machines Corporation | 发明人 | Syeda-Mahmood Tanveer F.;Wang Fei;Beymer David J. |
| 分类号 | G06K9/00;G06F17/30;G06K9/46;G06K9/62 | 主分类号 | G06K9/00 |
| 代理机构 | Cantor Colburn LLP | 代理人 | Cantor Colburn LLP ;Toub Libby |
| 主权项 | 1. A computer implemented method for finding similar coronary angiograms in a database of coronary angiograms comprising: receiving, by a processor, angiography data for a coronary artery; processing, by the processor, the angiography data to identify one or more semantic features of the coronary artery, wherein the one or more semantic features comprise at least one of the following: a number of significant junctions in the coronary artery;a thickness of the coronary artery;a number of trifurcations in the coronary artery,a tortuosity of the coronary artery,a length of one or more segments of the coronary artery; andlumen variations across the coronary artery; identifying, by the processor, one or more nearest coronary angiograms for each of the one or more semantic features from the database of coronary angiograms; and receiving a disease attribute associated with each of the one or more nearest coronary angiograms. | ||
| 地址 | Armonk NY US | ||