Medical Image Processing Method and System, Device and Medium

A medical image processing system, comprising:

• a first medical image acquisition apparatus configured to acquire raw data;
• and
• a processor configured to:
• subject the raw data to image reconstruction to generate an image;
• preprocess the generated image to provide a preprocessed image;
• and
• input the preprocessed image into a trained image optimization model to obtain a target image such that a resolution of the target image is higher than a resolution of the generated image;
• wherein the image optimization model is obtained by training a diffusion model using a training process having high-dose high-resolution image data as a starting point and target high-resolution image data as an endpoint of a diffusion process, the raw data being acquired via the first medical image acquisition apparatus, and the high-dose high-resolution image data used to train the diffusion model being acquired via a second medical imaging apparatus,
• wherein under equivalent external conditions, an image generated by the second medical imaging apparatus has higher resolution than an image generated by the first medical image acquisition apparatus, and
• wherein the processor is further configured to cause the medical image processing system to output the target image with a resolution equivalent to an image generated by the second medical imaging apparatus.

An electronic device, comprising:

• one or more processors;
• and
• a memory configured to store computer-readable instructions that, when executed via the one or more processors, causes the electronic device to:
• acquire raw data;
• subject the raw data to image reconstruction to generate an image;
• preprocess the generated image to provide a preprocessed image;
• input the preprocessed image into a trained image optimization model to obtain a target image such that a resolution of the target image is higher than a resolution of the generated image,
• wherein the image optimization model is obtained by training a diffusion model using a training process having high-dose high-resolution image data as a starting point and target high-resolution image data as an endpoint of a diffusion process, the raw data being acquired via a first medical imaging device, and the high-dose high-resolution image data being acquired via a second medical imaging device,
• wherein under equivalent external conditions, an image generated by the second medical imaging device has a higher resolution than an image generated by the first medical imaging device;
• and
• output the target image with a resolution equivalent to an image generated by the second medical imaging device.