Convolutional neural network-based medical image registration method and system, and electronic device

Abstract

The invention relates to a convolutional neural network-based medical image registration method and system, and an electronic device. The method comprises the steps of a: introducing a tensor column to a weight matrix of a full connection layer of a convolutional neural network to obtain a tensor convolutional neural network; b: obtaining at least two to-be-registered images with parameters t, andobtaining an image sub-module of the at least two to-be-registered images, wherein the parameters t represent 3D model rigid body transformation parameters corresponding to the to-be-registered images, and the image sub-module is a difference value of the at least two to-be-registered images in a local part; and c: inputting the image sub-module to the tensor convolutional neural network, calculating a parameter relationship, about the parameters t, between the at least two to-be-registered images by the tensor convolutional neural network according to the image sub-module, and performing registration on the at least two to-be-registered images according to the parameter relationship. The network training time can be shortened and the image registration precision can be improved.

Description

technical field [0001] The present application relates to the technical field of image registration, in particular to a convolutional neural network-based medical image registration method, system and electronic equipment. Background technique [0002] Image registration is the process of matching and superimposing two or more images acquired at different times, different imaging devices or under different conditions. It has been widely used in remote sensing data analysis, computer vision, image processing and other fields. With the wide application of deep learning in the field of image recognition, the application of deep learning in the field of image registration has become a new hot spot. In registration applications involving neural networks, convolutional neural networks usually imply a large number of neurons and involve thousands of parameters. With the application of hundreds of layers of neural networks, the number of parameters reaches tens of millions or even ...

AI Technical Summary

Problems solved by technology

However, if you want to achieve high accuracy, you must use a large, diverse and accurately labeled training data set, but such data sets are expensive

And because the training of the convolutional neural network requires real label values ​​manually marked by human experts, it not only costs a lot, but sometimes there are problems such as misclassification due to human subjective factors, so it faces the lack of training data

Images