Automatic extraction of proximal femur contours from calibrated X-ray images: a Bayesian inference approach

Author(s):  
Xiao Dong ◽  
Guoyan Zheng
1992 ◽  
Vol 33 (5) ◽  
pp. 477-481 ◽  
Author(s):  
P. Hübsch ◽  
H. Kocanda ◽  
S. Youssefzadeh ◽  
B. Schneider ◽  
F. Kainberger ◽  
...  

Measurements of bone mineral density (BMD) of the proximal femur (including femoral neck, Ward's triangle and trochanteric region) were compared with the Singh index grading in 40 normal subjects (20 male, 20 female) and in 116 patients (18 male, 98 female) referred for assessment of possible osteoporosis. Additionally, the BMD and the Singh index of 12 cadaver specimens (6 male, 6 female) of the proximal femur were compared with each other and with the histomorphology of the femoral necks of the specimens. Although there was a good correlation of Singh index with BMD in the group of male patients with suspected osteoporosis and in the series of bone specimens, there was a poor correlation in the group of female patients as well as in the normal controls and in the patient population as a whole. There was also poor correlation of Singh index values with histomorphologic data, whereas the BMD measurements correlated well with the amount of calcified bone found histologically in the femoral necks of the bone specimens. We conclude that the Singh index cannot be used to predict BMD of the proximal femur accurately.


Author(s):  
Kwang Baek Kim ◽  
Doo Heon Song ◽  
Sang-Seok Yun

Early detection of subtle fracture is important particularly for the senior citizens’ quality of life. Naked eye examination from X-ray image may cause false negatives due to operator subjectivity thus computer vision based automatic detection software is much needed in practice.  In this paper, we propose an automatic extraction method for suspisious wrist fracture regions. We apply K-means in pixel clustering to form the candidate part of possible fracture from wrist X-ray image automatically. This method can recover previously detected patterned false cases with edge detection method after fuzzy stretching. The proposed method is successful in 16 out of 20 tested cases in experiment.


Sign in / Sign up

Export Citation Format

Share Document