Brain Metabolism Mapping Using MRI-dPET Co-Registration and MCIF
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Analyzing medical images, particularly FDG-PET scans, is labor-intensive and requires specialized training, limiting the speed and accuracy of medical diagnosis.
Innovation Solution
A computer-implemented method using machine learning techniques, including 3D-CNN and RNN, to co-register MRI and dPET data, segment anatomical portions, and calculate a model-corrected input function (MCIF) for precise metabolic mapping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of medical images is performed by trained individuals, then diagnostic accuracy is improved, but labor intensity and time consumption increase
Solution Approach 1:
The system enables automated self-service analysis where the AI model independently processes medical images, performs segmentation, and generates diagnostic reports without requiring manual intervention from trained professionals, thereby maintaining accuracy while improving efficiency
Solution Approach 2:
The patent replaces the mechanical process of manual image analysis by trained individuals with an automated AI-based system that uses machine learning algorithms to perform the same diagnostic functions, eliminating labor-intensive manual operations
2Productivity
If automated analysis methods are implemented, then productivity is improved, but measurement precision may deteriorate
Solution Approach 1:
The system incorporates feedback mechanisms where the AI model's outputs are continuously refined based on performance metrics and validation results, ensuring that automated analysis maintains high diagnostic accuracy while improving efficiency
Solution Approach 2:
The patent performs preliminary actions by training the AI model extensively on labeled datasets before deployment, pre-establishing accurate patterns and relationships that enable the system to maintain high diagnostic precision during automated operation
3Measurement precision
If complex machine learning models are used, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the complex analysis task into distinct modular components including image preprocessing, feature extraction, segmentation, and validation stages, each handled by specialized model components that can be independently optimized and maintained
Data Source
AI summary
Digital images are used for time-based mapping of metabolic activity within a selected anatomy of a subject, particularly within a brain of the subject. Machine learning algorithms receive magnetic resonance image (MRI) data and four-dimensional dynamic positron emission tomography (dPET) data of the brain. A tracer may be applied prior to the anatomical scanning, and the MRI data is co-registered with the dPET data. A convolutional neural network (CNN) outputs localized data frames and a probability distribution for respective localized data frames. The probability distribution corresponds to a section of the subject's anatomy, such as internal carotid arteries, being visible in each of the respective localized data frames. The chosen section of the anatomy is segmented from the visible frames and a model-corrected input function (MCIF) for blood flow is calculated to compute a Ki map that illustrates influx of the tracer into the preferred anatomical portion.