Abstract
Vertebral compression fracture is a deformity of vertebral bodies found on lateral spine images. To diagnose vertebral compression fracture, accurate measurement of vertebral compression ratio is required. Therefore, rapid and accurate segmentation of vertebra is important for measuring the vertebral compression ratio. In this study, we used 339 data of lateral thoracic and lumbar vertebra images for training and testing a deep learning model for segmentation. The result of segmentation by the model was compared with the manual measurement, which is performed by a specialist. As a result, the average sensitivity of the dataset was 0.937, specificity was 0.995, accuracy was 0.992, and dice similarity coefficient was 0.929, area under the curve of receiver operating characteristic curve was 0.987, and the precision recall curve was 0.916. The result of correlation analysis shows no statistical difference between the manually measured vertebral compression ratio and the vertebral compression ratio using the data segmented by the model in which the correlation coefficient was 0.929. In addition, the Bland–Altman plot shows good equivalence in which VCR values are in the area within average ± 1.96. In conclusion, vertebra segmentation based on deep learning is expected to be helpful for the measurement of vertebral compression ratio.
Highlights
Vertebral compression fractures (VCFs), a deformity of vertebral bodies found on lateral spine imaging, are most commonly seen in osteoporosis [1, 2].The clinical diagnosis of the VCF is determined by the patient presenting with back pain, followed by the spinal images with a fracture in the body of the thoracolumbar or lumbar vertebra [3]
We performed comparative analysis on the Vertebral compression ratio (VCR) calculated based on the data on vertebral area manually segmented by the specialists and the VCR calculated by predicted data from trained vertebral segmentation model
Bland Altman plot analysis indicates that the reliability between the VCRs measured by the specialists and predicted by the model, enabling us to confirm that the model for the vertebral segmentation using lateral spine X-ray images is useful in measuring VCR
Summary
Vertebral compression fractures (VCFs), a deformity of vertebral bodies found on lateral spine imaging, are most commonly seen in osteoporosis [1, 2].The clinical diagnosis of the VCF is determined by the patient presenting with back pain, followed by the spinal images with a fracture in the body of the thoracolumbar or lumbar vertebra [3]. An accurate segmentation in spinal images is essential to measure VCR. It is labor-intensive for the spine specialists to manually segment the images, but they may produce the differences in radiographic images [12]. As the deep learning model developments are recently in progress and the fast, accurate segmentation become widely available, the specialists can save time with the automatic segmentation models and produce more consistent images. Segmentation on spinal radiographic images is currently in continuous progress; studies on how the segmented data are clinically used have not been in progress yet. We segmented the lateral vertebral images using deep learning and produced an algorithm measuring VCR based on the segmented vertebral data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
