Deep learning neural network model system for multi-modal image synthesis

Abstract

The invention relates to a deep learning neural network model system for multi-modal image synthesis. The deep learning neural network model system comprises: a multi-resolution residual deep neural network formed by combining a residual deep neural network (RDNN) and a multi-resolution optimization strategy; an RDNN, wherein the RDNN comprises A convolution layers, B falling layers, C batch Normalization layers and D long-term residual error connections, wherein the convolutional layer is used for extracting image features; a falling layer for avoiding network overfitting; and a batch normalization layer for standardizing the input of the corresponding convolution kernel. The long-term residual connections are used for retaining structure information in the input image; convolutional layers are arranged on the two sides of each falling-off layer, and each falling-off layer is connected with the adjacent convolutional layers on the two sides; one convolution layer is arranged between each falling layer and the corresponding batch normalization layer; the falling layers, the convolution layers and the batch normalization layers are connected in sequence; one end of each long-term residual connection is connected between the corresponding convolution layer and the corresponding batch normalization layer; and the other end is connected between the other group of corresponding convolutional layers and the corresponding batch normalization layer.

Description

technical field [0001] The invention relates to the technical field of medical image processing and guided treatment, in particular to a deep learning neural network model system for multimodal image synthesis. Background technique [0002] Adaptive Radio Therapy (ART) technology based on CBCT images can increase the irradiation of radiation to the tumor, and at the same time, protect the organs at risk near the tumor. However, the HU accuracy of CBCT images in the prior art is low, the resolution of soft tissues is low, and there are serious artifacts. Therefore, in order to realize adaptive radiotherapy (ART), synthetic CT (sCT) images with high HU accuracy and structural fidelity based on CBCT images are firstly required. [0003] U-Net and some other deep learning networks have been widely used in the task of sCT image generation. The study showed that the HU accuracy of the generated sCT images was significantly improved, and dose calculations could be performed based...

AI Technical Summary

Problems solved by technology

Second, the above network lacks constraints to improve the structural fidelity of sCT images

Images