| 摘要 |
<p num="1"><br/><br/><br/>Structures are delineated in medical or other images. First, various tissue <br/>types present in the image are statistically described using a maximum <br/>likelihood classifier. Second, the tissue of interest is described using an <br/>exemplar, which is derived either from an anatomical atlas or from user input. <br/>Third, the structure of interest is morphologically described. The process can <br/>be iterated until a desired level of accuracy is achieved.<br/>
|
