http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Automatic Extraction of Vertebral Endplates from Scoliotic Radiographs Using Customized Filter
Anitha H.,Karunakar A. K.,Dinesh K. V. N. 대한의용생체공학회 2014 Biomedical Engineering Letters (BMEL) Vol.4 No.2
Purpose The scoliosis diagnosing system needs radio-graphicinformation in terms of spinal curvature estimated usingCobb’s definition. The evaluation process and treatmentanalysis depends on the reliability and reproducibility of thespine curvature in the frontal view. Methods Manual identification of end vertebrae and otheranatomical features required for the estimation of spinalcurvature causes variability and unreliability at higher rate. This paper proposes an automated system to extract therequired anatomical features using customized filter. Thecustomized filter used in this paper is a combination ofanisotropic, sigmoid and differential filter. Combination ofthese filters automatically extracts the anatomical features interms of required vertebral endplates. Automatic identificationof these endplates eliminates the human intervention involvedin the quantification of Cobb angle. Results and Conclusions Analysis of the results revealssignificant difference between the observer variabilitybetween manual, computer assisted and computerized imageunderstanding system in terms of inter and intra crosscorrelation coefficient ratio (ICCR).