Perfusion imaging system and method

Abstract

The invention provides a perfusion imaging system, and is used for perfusion imaging. The system includes a data acquisition module used for acquiring a perfusion image data set; a preprocessing module used for preprocessing the perfusion image data set; and a focus segmentation module which is used for performing focus segmentation based on the preprocessed perfusion image data set and comprises a first neural network and a second neural network which are cascaded, wherein the first neural network generates perfusion parameters, and the second neural network performs focus segmentation according to the perfusion parameters. The system can improve the stability of perfusion parameter generation and the accuracy of focus segmentation, and can be suitable for perfusion imaging of the brain or other anatomical structures.

Description

technical field [0001] The present invention relates to medical imaging, and more particularly to systems and methods for perfusion imaging. Background technique [0002] In medical imaging, perfusion imaging provides a functional inspection method, which evaluates the blood perfusion state of tissue microcirculation according to the principle that blood flow changes are closely related to the normal physiological functions of tissues and organs and their pathological changes, such as Evaluate pathological or physiological changes such as cerebral infarction and tumors, which in turn contribute to the diagnosis and treatment of diseases. Currently, the commonly used medical imaging modalities for perfusion imaging include computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and so on. Taking CT perfusion imaging as an example, during rapid intravenous bolus injection of contrast agent, the region of interest is scanned continuously...

AI Technical Summary

Problems solved by technology

[0004] In the cerebral perfusion imaging method provided in the prior art, the cerebral perfusion parameters are affected by many factors such as the arterial input function (AIF), the model calculation method, etc., and the repeatability is poor

When determining the brain infarction area in the parametric image, medical personnel need to rely on the experience of manual judgment, which depends on the experience of the medical personnel, there are subjective differences, and it takes a long time, the accuracy is low, and the operability is poor

Images