The cervical spine is a highly flexible anatomy and therefore vulnerable to injuries. Unfortunately, a large number of injuries in lateral cervical X-ray images remain undiagnosed due to human errors. Computer-aided injury detection has the potential to reduce the risk of misdiagnosis. Towards building an automatic injury detection system, in this paper, we propose a deep learning-based fully automatic framework for segmentation of cervical vertebrae in X-ray images. The framework first localizes the spinal region in the image using a deep fully convolutional neural network. Then vertebra centers are localized using a novel deep probabilistic spatial regression network. Finally, a novel shape-aware deep segmentation network is used to segment the vertebrae in the image. The framework can take an X-ray image and produce a vertebrae segmentation result without any manual intervention. Each block of the fully automatic framework has been trained on a set of 124 X-ray images and tested on another 172 images, all collected from real-life hospital emergency rooms. A Dice similarity coefficient of 0.84 and a shape error of 1.69 mm have been achieved.

The CYP 17 and CYP 19 genes encode 17alpha-hydroxylase/17,20-lyase and aromatase, respectively, both involved in sex hormone synthesis. We investigated the association between 2 common polymorphisms in 1) the promoter region (T-->C substitution) of CYP 17, and 2) exon 3 (G-->A) of CYP 19, bone mineral density (BMD) and serum androgen/estradiol, in a case-control study of 252 postmenopausal women aged 64.5 +/- 9.2 yr (mean +/- SD). There was no significant difference in serum estradiol concentrations between cases (n = 136) and controls (n = 116). The CYP 19 genotype was significantly associated with serum estradiol (P = 0.002). Women with the AA genotype had higher serum estradiol concentrations compared with those with the GG genotype (P = 0.03). In older women, those with the CYP 19 GA and GG genotypes had an increased prevalence of osteoporosis (P = 0.04) and fractures (P = 0.003). We found no significant association between CYP 17 genotype and serum androgens and estradiol concentrations. However, a significant association was seen between BMD values at the femoral neck with CYP 17 genotype in cases (P = 0.04) and in the whole study population (P = 0.012). Subjects with the CC genotype had significantly lower BMD (mean +/- SD: TT, 0.7 +/- 0.16; CC, 0.6 +/- 0.08 g/cm(2); P = 0.006). In conclusion, both CYP 17 and CYP 19 are candidate genes for osteoporosis in postmenopausal women.