PET Dynamic Image Generation With Adaptive Frame Extension
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current PET/CT image quality control is manual and time-consuming, leading to inefficiencies when quality issues are detected in reconstructed images, especially for dynamic images that take hours to acquire, affecting doctor's work efficiency.
Innovation Solution
A method for generating medical images that includes obtaining a PET dynamic image, performing quality analysis to determine a single frame image, extending the frame duration if quality criteria are not met, and constructing a target single frame image using additional scanning data to ensure quality thresholds are exceeded, with adjustments based on body parameters and SNR analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual quality control is performed on PET images, then image quality can be assessed, but the process is time-consuming and reduces work efficiency
Solution Approach 1:
The system performs self-assessment of image quality through automatic analysis algorithms that evaluate PET images against predefined quality criteria, eliminating the need for manual quality control and significantly reducing time consumption while maintaining assessment accuracy
Solution Approach 2:
The manual mechanical process of quality assessment by radiologists is replaced with automated computational algorithms that analyze image quality metrics, coincidence event counts, and reconstruction parameters to objectively evaluate image quality without human intervention
2Manufacturing precision
If dynamic PET images with long acquisition time are reconstructed and quality issues are detected, then image quality can be ensured, but the reconstruction time increases significantly
Solution Approach 1:
The system performs preliminary quality assessment during the scanning process itself, evaluating image quality metrics and coincidence event counts in real-time before complete reconstruction is finalized, allowing early detection of quality issues and preventing unnecessary full reconstruction time consumption
Solution Approach 2:
The system implements feedback mechanisms where quality assessment results from preliminary analysis are used to guide subsequent reconstruction decisions, automatically adjusting reconstruction parameters or triggering re-scanning only when quality thresholds are not met, thereby optimizing the balance between image quality and reconstruction time
3Manufacturing precision
If the frame duration is extended to increase coincidence event count, then image quality improves, but the scanning time increases
Solution Approach 1:
The system dynamically adjusts frame duration based on real-time assessment of coincidence event counts and image quality metrics, extending the duration only when quality thresholds are not met and reducing it when sufficient events are accumulated, optimizing the balance between image quality and scanning time for each specific case
Solution Approach 2:
The system changes the frame duration parameter adaptively during the scanning process based on measured coincidence event rates and image quality assessments, adjusting this critical parameter to achieve optimal image quality while minimizing unnecessary scanning time extension
Data Source
AI summary
A medical image generation method is provided. A PET dynamic image of a target part of a scanned object is obtained, a quality analysis is performed on the PET dynamic image to determine a first single frame image that meets quality enhancement requirements, the first single frame image corresponding to an initial single frame duration. A second set of scanning data corresponding to a first single frame duration of the PET dynamic image are obtained when a count of coincidence events corresponding to the first single frame image is less than a count threshold. The first single frame duration is obtained by extending the initial single frame duration. A target single frame image of the target part is constructed based on the second set of scanning data, and the count of coincidence events corresponding to the second set of scanning data is greater than or equal to the count threshold.