Sheng-Fang Huang, H. Chao, Cheng-Chin Hsu, Shan-Fong Yang, P. Kao
{"title":"A computer-aided diagnosis system for whole body bone scan using single photon emission computed tomography","authors":"Sheng-Fang Huang, H. Chao, Cheng-Chin Hsu, Shan-Fong Yang, P. Kao","doi":"10.1109/ISBI.2009.5193104","DOIUrl":null,"url":null,"abstract":"Tc-99m MDP whole body bone scan using single photon emission computed tomography (SPECT) is an important and general method to investigate the spreading of malignant tumors. However, it is time-consuming for doctors to perform three-dimensional (3D) assessment using SPECT images. Therefore, a computer-aided diagnosis (CAD) system is required to identify suspicious locations of bone abnormalities. In this study, we developed a 3D-based segmentation method and a quantitative scheme to detect the findings of possible abnormalities. In this method, we designed a new data structure called bone graph that characterizes scanned images as graph, where by tracking this graph, we can extract the morphological features from the entire skeleton. The proposed scheme automatically extracts the skeletal structure of human spine, and can be adopted to assist nuclear medicine physicians to identify the potential locations of bone lesions.","PeriodicalId":272938,"journal":{"name":"2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISBI.2009.5193104","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
Tc-99m MDP whole body bone scan using single photon emission computed tomography (SPECT) is an important and general method to investigate the spreading of malignant tumors. However, it is time-consuming for doctors to perform three-dimensional (3D) assessment using SPECT images. Therefore, a computer-aided diagnosis (CAD) system is required to identify suspicious locations of bone abnormalities. In this study, we developed a 3D-based segmentation method and a quantitative scheme to detect the findings of possible abnormalities. In this method, we designed a new data structure called bone graph that characterizes scanned images as graph, where by tracking this graph, we can extract the morphological features from the entire skeleton. The proposed scheme automatically extracts the skeletal structure of human spine, and can be adopted to assist nuclear medicine physicians to identify the potential locations of bone lesions.