Anatomical prior based vertebra modelling for reappearance of human spines

Scoliosis is a disease caused by deformation of the spine, and precise imaging of human spine tissues is crucial and instructive for the subsequent treatment. Currently, radiographs are clinically used to monitor disease progress. However, radiation exposure is a safety concern and is undesirable for regular monitoring during rehabilitation intervention. In this study, we developed a novel technique to generate the 3D structure of human spine from a tracked freehand ultrasound scanning. First of all, we designed an approach for detection and location of every vertebra in the spine by firstly detecting the vertebral landmarks from the ultrasound B-scan sequence, then computing the size, location and posture of every vertebra and finally using a method of interpolation to form the whole spine according to the prior knowledge of vertebral anatomical structure. Deep learning based object detection methods were used to find the landmarks of the vertebrae, and those landmarks were then clustered to model every vertebra (i.e. computing its location, posture and real size). Due to the situations where the vertebra is not clearly seen, we therefore used the technique of interpolation to estimate the location of those missing vertebrae with respect to the anatomical prior. In addition, we reconnected all vertebral models and reappeared the whole spine in 3D space. With that, the Cobb angle could be easily measured. The phantom and experiments were also conducted to further verify the precision of the proposed approaches. The results have demonstrated its feasibility in the clinical practice of adolescent idiopathic scoliosis patients (2 = 09780