Low-dose SPECT image reconstruction method and system
By using the masked autoencoder model MAE in SPECT imaging for image reconstruction, the problem of image quality degradation under low dose conditions is solved, image quality and diagnostic accuracy are improved, while reducing radiation exposure to patients.
CN119693488APending Publication Date: 2025-03-25PEKING UNIVERSITY THIRD HOSPITAL (THE THIRD CLINICAL MEDICAL SCHOOL OF PEKING UNIVERSITY)
7 Cites 1 Cited by
Patent Information
- Application Number
- CN202510201137.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-24
- Publication Date
- 2025-03-25
AI Technical Summary
Technical Problem
Traditional SPECT imaging technology reduces image quality under low dose conditions, resulting in a decrease in Poisson noise, ray artifacts and spatial resolution, affecting the accuracy of clinical diagnosis.
Method used
The image reconstruction method based on the mask autoencoder model MAE is adopted. By obtaining projected images of multiple scanning angles, converting them into multiple first string patterns, and inputting the image reconstruction model to obtain multiple second string patterns, and finally reconstructing the tomographic map of the target part based on these string patterns.
Benefits of technology
Improves image quality of SPECT imaging at low dose conditions, enhances the accuracy of clinical diagnosis, and reduces radiation exposure to patients.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention relates to a low-dose SPECT image reconstruction method and system. The method comprises the following steps: acquiring a plurality of projection images corresponding to a plurality of scanning angles when a target part of a patient is subjected to SPECT imaging scanning; converting the plurality of projection drawings into a plurality of first chordal diagrams, and inputting the plurality of first chordal diagrams into an image reconstruction model to obtain a plurality of second chordal diagrams; wherein the image reconstruction model is obtained by performing model training on a mask auto-encoder model MAE based on a plurality of sample chordal diagrams, a three-dimensional encoder and a three-dimensional decoder are adopted as an encoder and a decoder of the mask auto-encoder model MAE, and the plurality of sample chordal diagrams are obtained by processing a plurality of sample projection diagrams; and reconstructing based on the plurality of second chordal diagrams to obtain a fault diagram of the target part.
Need to check novelty before this filing date? Find Prior Art