Delayed CT image generation method based on deep learning algorithm

Abstract

The invention belongs to the technical field of medical images, and particularly relates to a delayed CT (T2CT) image generation method based on the deep learning algorithm. The method comprises the following steps: S1, collecting T2PET, T1PET and T1CT images of a patient; s2, inputting the acquired T2PET, T1PET and T1CT images into the proposed multi-resolution registration convolutional neural network, and then outputting three deformation fields including large, medium and small deformation quantities; s3, fusing the three deformation fields including the large deformation quantity, the medium deformation quantity and the small deformation quantity output in the step S2 into one deformation field; and S4, inputting the deformation field and the input T1CT image into a space conversion network to generate a T2CT image. The method has the advantages that attenuation correction can be performed in delayed PET scanning, and meanwhile, the T2CT image is generated to avoid additional CT scanning of the patient, so that the X-ray radiation dose suffered by the patient is reduced.

Description

technical field [0001] The invention belongs to the technical field of medical images, and in particular relates to a delayed CT image generation method based on a deep learning algorithm. Background technique [0002] Positron emission tomography / computed tomography (PET / CT) systems provide critical information for radiation therapy planning, which can be used to aid decision-making in tumor diagnosis, prognosis, and staging. PET is a noninvasive diagnostic tool that provides information on metabolism and function. CT is an X-ray tomographic technique that provides anatomical representation of lesions with high spatial resolution. [0003] Before a PET scan, the body is injected with an imaging agent, such as a positron radionuclide, which is then pushed into a ring of detectors. The positron radionuclide injected into the human body decays to produce positrons, which annihilate with the electrons in the tissue, producing two pairs of gamma photons with 511 kiloelectron v...

AI Technical Summary

Problems solved by technology

Although it can reduce the X-ray dose received by the patient during the entire image acquisition stage and reduce the physical and psychological pressure on the patient, the disadvantage is that according to clinical needs, there is a problem of insufficient accuracy of the obtained CT images.

Images