System for automatically analyzing dopamine transporter PET image based on CT structure image

Abstract

The invention discloses a system for automatically analyzing a dopamine transporter PET image based on a CT structure image. The system comprises an image acquisition module, an image preprocessing module, a DAT-PET functional image automatic segmentation module and a bilateral striatum sub-partition automatic numerical value extraction and calculation module. And based on the CT structure image, fine automatic segmentation of a striatum region and striatum sub-partitions (including front and rear shell cores on both sides and front and rear caudal cores on both sides) in the DAT-PET function image is carried out. The invention comprises performing fine automatic segmentation and three-dimensional reconstruction display on striatum of a DAT-PET functional image by a synchronously scanned CT structural image, and automatically calculating developer uptake values and uptake value ratios of striatum sub-partitions. Clinical doctors can be effectively assisted in interpreting the DAT-PET functional image, a reliable basis is provided for diagnosis and differential diagnosis of Parkinson's syndrome, and the invention has high robustness.

Description

technical field [0001] The invention relates to the technical fields of medical image processing and nuclear medicine, in particular to a system for automatically analyzing PET images of dopamine transporters based on CT structural images. Background technique [0002] Parkinson's Disease (PD) is the second most common neurodegenerative disease after Alzheimer's disease. PD is a chronic progressive disease. Patients gradually lose the ability to work and autonomous activities. In the advanced stage of the disease, the patient becomes stiff, difficult to move, paralyzed in bed, and often dies of various complications such as pneumonia in the end, which brings great pain to the patient. Great pain, while bringing serious mental and economic burdens to families and society. At present, the prevalence of PD among people over 65 years old in my country is as high as 1.7%. And it is predicted that among the 5 most populous countries in Europe and the 10 most populous countries i...

AI Technical Summary

Problems solved by technology

[0004] The main challenges faced by the existing technology are as follows: 1. The uptake value of striatal DAT imaging agent in patients with Parkinson's syndrome can be significantly reduced, and striatum segmentation based solely on DAT-PET functional images will lead to a large amount of information in the lesion area Lost; 2. Different human brain structures, especially the striatal structure, are quite different. Using the template constructed from the normal DAT-PET functional image to segment the DAT-PET functional image will inevitably cause the real striatal structure to be stretched or Distortion and subtle structural changes are likely to affect the diagnostic results of DAT-PET functional images; 3. Now more methods are used for registration and segmentation based on MRI structural images, but in non-PET / MR synchronous examination equipment scanning In some cases, the patient's PET and MRI data are not completely matched, and the use of such images for registration and segmentation will also cause large errors

Moreover, this type of method cannot be applied to patients who lack MRI scan data of the head

Images