Medical image multi-modal registration method based on space-time intelligent agent

Abstract

The invention relates to a medical image multi-modal registration method of a space-time intelligent agent. The method includes: inputting the dynamic images and the solid-state images of different modes into the constructed neural network; extracting high-level abstract features of the image through a convolutional neural network module in the neural network; then, enabling a convolution long-short-term memory network module to automatically extract time sequence and space information among sequences in the high-level abstract features; outputting the current state value and the probability distribution of the strategy action after passing through the neural network, implementing the action with the maximum probability on the dynamic image by the space-time intelligent agent, and circularly registering before the current state value reaches a threshold value until the circulation is finished; and finally carrying out Monte Carlo sampling on the registration image to obtain a final registration result. According to the convolution long-short-term memory model, the spatial relationship and the time sequence information in the image are captured through convolution, and the registration precision is higher.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a multimodal registration method for medical images based on a spatiotemporal agent. Background technique [0002] Multimodal medical image processing is a research hotspot in current image processing, which is of great significance for clinical diagnosis and treatment. Images of different modalities provide different information about patients, anatomical images (such as CT, MRI) provide information on the anatomical structure of the human body, and functional images (such as SPECT, PET) provide functional information on the distribution of radioactive concentrations in the human body. The information needs to be synthesized to obtain a fusion image with more comprehensive information. To obtain useful fused images, images of different modalities need to be registered. [0003] Medical image registration is to find a certain spatial transformation, so that the corresponding poi...

AI Technical Summary

Problems solved by technology

Methods based on deep learning have high requirements on the quality and quantity of data, but medical image registration datasets are difficult to find and are usually small datasets

Images