Computerized-Assisted Scoliosis Diagnosis Based on Faster R-CNN and ResNet for the Classification of Spine X-Ray Images.

Abstract

In order to reduce the subjectivity of preoperative diagnosis and achieve accurate and rapid classification of idiopathic scoliosis and thereby improving the standardization and automation of spinal surgery diagnosis, we implement the Faster R-CNN and ResNet to classify patient spine images. In this paper, the images are based on spine X-ray imaging obtained by our radiology department. We compared the results with the orthopedic surgeon's measurement results for verification and analysis and finally presented the grading results for performance evaluation. The final experimental results can meet the clinical needs, and a fast and robust deep learning-based scoliosis diagnosis algorithm for scoliosis can be achieved without manual intervention using the X-ray scans. This can give rise to a computerized-assisted scoliosis diagnosis based on X-ray imaging, which has strong potential in clinical utility applied to the field of orthopedics.