Substance decomposition method, device and system

Abstract

The invention discloses a material decomposition method, device and system. The material decomposition method includes: collecting the projection data of the calibration phantom in two or more energy windows, and determining the corresponding value of the calibration phantom and the material decomposition implementation mode of the specified domain according to the projection data and the material decomposition implementation mode of the specified domain. Multi-energy data; set the ideal single-energy, and obtain the ideal single-energy data of the calibration phantom under the ideal single-energy by a preset method; train the corresponding neural network according to the multi-energy data, and the trained neural network reflects the multi-energy data and The mapping relationship between ideal single-energy data; based on the projection data of the material to be decomposed in the specified energy window and the trained neural network, the material to be decomposed is decomposed. According to the material decomposition method provided in the embodiment of the present invention, the material decomposition is performed through the artificial neural network, which improves the accuracy of the material decomposition.

Description

technical field [0001] The invention relates to the field of tomographic image reconstruction, in particular to a material decomposition method, device and system. Background technique [0002] With the development of X-ray detectors and imaging systems, dual-energy or multi-energy spectral CT (Computed Tomography, computerized tomography) has been widely used. Compared with the traditional single-energy CT, the spectral CT that uses the signal formed by the X-ray of two or more energy windows or energy channels to pass through the object to be measured can overcome the shortcomings of spectrum hardening and insufficient contrast. Starting from the underlying physical basis, it breaks the development bottleneck of traditional CT imaging in many application fields, improves the ability of X-ray CT images to distinguish substances and improves the ability of quantitative analysis of substance components. [0003] The photon counting detector has good energy resolution charact...

AI Technical Summary

Problems solved by technology

[0004] However, due to the non-ideal physical effects of photon counting detectors, such as charge sharing, pulse stacking and k-escape, etc., the energy spectrum will be deformed, which will bring errors to the decomposition model and affect the accuracy of material decomposition.

Images