一种高度自动化的三维ct 数据腰椎分割方法.pdf

第32 卷第3期 东 北 大 学 学 报 ( 自 然 科 学 版 ) Vol132, No. 3 2 0 1 1 年 3 月 Journal of Northeastern U ni ersity( Natural Science) Mar. 2 0 1 1 CT 1 2 2 1, 2, 3 赵 凯, 王之琼 , 康 雁 , 赵 宏 ( 1. , 110819; 2. , 110819; 3. , 110179) : , , CT CT , # , , # , # # : ; CT ; ; ; : TP 391. 4 : A : 1005-3026( 2011) 03-0340-04 A Highly Automatic Lumbar Vertebrae Segmentation Method Using 3D CT Data 1 2 2 1, 2, 3 ZH A O K ai , WA N G Zhi-qiong , KA N G Yan , ZHA O H ong ( 1. School of Information Science Engineering , Northeastern Uni ersity, Shenyang 110819, China; 2. School of Sino-Dutch Biomedical and Information Engineering , Northeastern Uni ersity, Shenyang 110819, China; 3. National Engineering Research Center for Digital Medical Imaging De ice, Sheny ang 110179, China. Corresponding author : KA NG Yan, E-mail: kangy @ neusoft. com) Abstract: Computer image processing technology is commonly used in clinical diagnoses of lumbar ertebrae problems and in medical research to segment single lumbar ertebrae w ith 3D CT images. Problems w ith existing segmentation methods include the inability to completely segment, failure to process all the data, or an excessi e need for hand labor. A new method was proposed to segment indi idual lumber ertebrae using CT images. The entire backbone is first segmented from CT images, and then each single centrum and inter ertebral facet joints are