A Multimodal Image Registration Method Based on Synthesized Ultrasound Images

Abstract

The present invention provides a multimodal image registration method based on synthetic ultrasound images. According to magnetic resonance images and real ultrasound images, by constructing a generative confrontation network including a generator and a discriminator, a realistic synthetic ultrasound image is generated, and the The realistic synthetic ultrasound image and the real ultrasound image are registered to obtain registration parameters, and the registration parameters are applied to the magnetic resonance image to complete the final registration fusion of the magnetic resonance image and the ultrasound image. The method can synthesize ultrasound images from magnetic resonance images in real time, meeting the requirements of real-time image-guided surgery; the synthetic realistic ultrasound images are closer to real ultrasound images, with higher image quality and better preservation of important details; When the magnetic resonance image contains a tumor, it can still accurately synthesize a realistic ultrasound image; the final registration technology does not require a very complicated registration algorithm, and only needs a traditional simple registration algorithm to achieve a good registration effect.

Description

technical field [0001] The invention relates to the field of multi-modal image registration, in particular to a multi-modal image registration method based on synthetic ultrasonic images. Background technique [0002] Both ultrasound images and magnetic resonance images are currently widely used in the diagnosis of various medical cases, for example, to detect infarcts and tumors in the head, to detect acute and chronic changes in the liver, and to navigate various clinical procedures. Real-time imaging of the liver is essential for detection of lesions or clinical treatment. Scanning imaging with an ultrasound probe can meet the requirements of real-time imaging, and ultrasound imaging is non-invasive and causes less harm to the human body. However, compared with magnetic resonance images, ultrasound images have lower imaging quality, and magnetic resonance images can provide more anatomical details to better assist diagnosis and treatment. However, magnetic resonance imag...

AI Technical Summary

Problems solved by technology

However, simulating ultrasound images takes a lot of time, so this method cannot be used in real-time surgical navigation systems, and cannot accurately simulate the information of tumor regions, and missing tumors will lead to unstable image registration before and after resection.

The registration and fusion technology based on ultrasound simulation has become a research hotspot and has achieved certain results, but there are still some defects in the following aspects: it takes a lot of time to simulate a three-dimensional magnetic resonance image into a three-dimensional ultrasound image, and it does not Applicable to real-time image-guided surgical navigation system; when the magnetic resonance image contains a tumor, it cannot correctly simulate the ultrasound image of the tumor in the corresponding position

Images