The Construction of an Individualized Spinal 3D Model Based on the X-ray Recognition

The actual work is devoted to the construction of an individualized mathematical model of the spine, based on the X-ray images in the frontal and sagittal projections using deep learning convolutional neural networks. The semantic segmentation of X-ray images using the convolutional neural network U-Net is performed, also justifying the choice of network parameters and architecture. All stages of the individualized 30 model building are described, the results of each stage are presented. The model is constructed to subsequently determine the type and the extent of scoliosis with the aim of designing and implementing of the Cheneau corset