Automatic Rib Positioning Method in CT Images
Efficiently, accurately and automatically positioningthe ribs in CT images and giving tips of which rib it is on cross-sectionalplane will be very helpful for doctors clinical diagnosis.This paper presented a new method of automatic rib positioningand extraction in CT images. According to the anatomicalcharacteristics of ribs, the first rib will presents as a sloping linegradually when we slice the sagittal plane images from thesubcentral position of the body to the right or left side, while theother ribs will present as small ovals at that time. Based on thisfeature, we did the Hough transform on a series of sagittal planesand performed an automatic detection to find the first rib. Whenfinding the first rib, the corresponding plane was defined as theKey Saggital Plane (KSP), and we positioned the ribs and definedthe initial seed point of each rib on this plane. The rib extractionwas a kind of tracing-based one using the initial seeds definedabove. We evaluated our method on 21 chest CT data sets,including 11 cases of male and 10 cases of female. The age rangewas from 18 to 90, among which 12 cases were over the age of 55.Besides, the osteoporosis patients were involved. We tested ouralgorithms on the PC with XP-Pro/SP2, P4-3.0GHz, 2.0GBMemory. It was proved that the average number of the extractedribs is 11.5 of each side, and the positioning was correct. From the efficiency point of view, the average number of image slices ofone patient was 104, and the running time of the algorithm was4.95 seconds.
Hong Li Jun Li Shinong Pan Qiyong Guo Jiren Liu Yan Kang
School of Information Science & Engineering Northeastern University Shenyang, China National Engineering Research Center for Digitization Medical Imaging Device Department of Radiology Shengjing Hospital of China Medical University Shenyang, China Sino-Dutch Biomedical and Information Engineering School Northeastern University Shenyang, China
国际会议
成都
英文
1-4
2010-06-18（万方平台首次上网日期，不代表论文的发表时间）