Any modal image registration method and equipment based on neural network

• Main Authors: FENG BAOQUAN, CHEN LIXIN
• Format: Patent
• Language: Chinese; English
• Published: 14.06.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses an arbitrary modal image registration method and device based on a neural network, and relates to the technical field of image registration, and the method can simulate the characteristics of a substance through the generated random substance information, carries out the mapping of the random substance information, and obtains an image before deformation. Deformation and mapping are carried out on the random material information based on a random deformation field, a post-deformation image is obtained, the pre-deformation image and the post-deformation image serve as input of a neural network, an output deformation field is obtained through registration of the neural network, the neural network is optimized by comparing the difference between the output deformation field and the random deformation field, and a trained training model is obtained. The training model obtained by the method of the invention can ignore the influence of modality, improve the accuracy of registration, reduce