Multi-modal brain MRI image bidirectional conversion method based on multi-generation and multi-confrontation

Abstract

The invention provides a multi-modal brain MRI image bidirectional conversion method based on multi-generation and multi-confrontation. The method comprises the steps that an input image (T1/T2) and acorresponding pathological label are fused through a convolution network and serve as input data of a converter; T1 modal data is input and converted into a T2 modal image through a T2 modal converter; T2 modal data is input and converted into a T1 modal image through a T1 modal converter; confrontation loss between an output image and a real image is constructed; loop verification loss is constructed to achieve the verification of the effectiveness of the converter; content loss between the output image and the real image is constructed, so that the result is closer to the real image; edge loss is introduced to constrain the edges of the real image and output image; the difference between semantic segmentation results of the output image and real image is taken as shape loss to keep theshape consistency. The multi-modal brain MRI image bidirectional conversion method based on the multi-generation and the multi-confrontation can perform bidirectional conversion on multi-modal brain MRI data, and also ensure the invariance of the texture, structure and pathology of the images.

Description

technical field [0001] The invention belongs to a medical image processing method, which performs bidirectional conversion on multimodal brain MRI images in combination with pathological labels corresponding to medical images, multiple generative confrontation networks and multiple image loss functions. Background technique [0002] Medical imaging technology is an important part of modern medicine, with different imaging techniques (eg, X-ray, CT, MRI). Medical images of various modalities are provided for clinical diagnosis and medical research. Among them, magnetic resonance imaging is widely used in clinical treatment and medical image analysis due to its safety and richness of visual features. So far, MRI has not been found to have definite harm to the human body. In addition, MRI technology can obtain different contrast images of the same anatomical structure by setting different parameters, and the functions of these images are different. For example, T1-weighted ima...

AI Technical Summary

Problems solved by technology

However, the high demand for analysis using multiple modalities is not always met in clinical and research due to missing modality and modality inconsistency between different clinical centers

(2) The cost of obtaining MR images is high

Time and financial costs of long examinations and difficulty keeping patients still during scans (e.g. pediatric patients and elderly patients)

These existing problems greatly limit the application of magnetic resonance imaging technology in clinical treatment, and have a negative impact on the quality of diagnosis and treatment

Images