Three-dimensional image tubular structure segmentation image fracture restoration method and system based on deep learning network

The embodiment of the invention provides a three-dimensional image tubular structure segmentation image fracture restoration method and system based on a deep learning network, and the method comprises the following steps: S1, collecting three-dimensional image data, and carrying out the preprocessing of the three-dimensional image data; S2, resampling the preprocessed three-dimensional image data, and generating three-dimensional data of a plurality of candidate regions of interest; S3, inputting the three-dimensional data of all candidate regions of interest into a target organ extraction deep learning network to obtain a target organ segmentation map in each region of interest; and S4, performing distance transformation on the target organ segmentation image to obtain a distance transformation image, inputting the target organ segmentation image and the distance transformation image into a fracture repair deep learning network together to obtain a fracture repair image of each region of interest, and splic