Medical Imaging Calibration Using Patch-Based Artifact Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Medical imaging systems, such as MRI devices, suffer from artifacts due to system errors and external interferences, leading to poor image quality that can affect diagnostic accuracy.
Innovation Solution
A calibration method that divides imaging data into patches, identifies abnormal points using trained classification models, and calibrates the data based on these patches, employing different strategies for different patch positions to improve accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional artifact correction methods are used, then imaging quality can be improved, but scanning time increases and productivity decreases
Solution Approach 1:
The patent applies preliminary action by performing artifact detection and classification before the actual scanning process. The system detects abnormal points in K-space data and classifies them into different types (e.g., RF interference, system faults) prior to scanning, enabling the calibration system to prepare correction strategies in advance and avoid the need for time-consuming rescaning operations.
Solution Approach 2:
The patent implements feedback mechanisms where the calibration system continuously monitors imaging data, detects artifacts, and adjusts calibration parameters in real-time. The system uses feedback from detected abnormal points to automatically modify calibration models and correction strategies, allowing for iterative improvement without requiring additional scanning time.
2Measurement precision
If comprehensive calibration is performed on all imaging data, then calibration accuracy improves, but data processing time increases
Solution Approach 1:
The patent applies segmentation by dividing the imaging data into smaller manageable units (patches or blocks) and processing them individually. The system segments K-space data into multiple regions, detects artifacts in each segment separately, and applies targeted calibration only to segments containing abnormal points, rather than processing the entire dataset uniformly.
Solution Approach 2:
The patent implements local quality by applying different calibration strategies to different regions of the imaging data based on their specific characteristics. The system identifies the location and type of artifacts in specific regions and applies localized correction methods appropriate to each region, rather than applying a uniform calibration approach throughout the entire dataset.
3Measurement precision
If artifact detection sensitivity is increased, then detection accuracy improves, but false positive rate increases
Solution Approach 1:
The patent applies parameter changes by dynamically adjusting detection thresholds and classification criteria based on the specific characteristics of the imaging data and detected artifacts. The system modifies detection parameters adaptively to match the underlying patterns of different artifact types, enabling high accuracy while minimizing false positives through intelligent parameter adjustment rather than fixed rigid thresholds.
Solution Approach 2:
The patent uses an intermediary classification model as a mediator between raw detection signals and final artifact identification. The classification model processes initial detection results and filters out false positives by analyzing the contextual characteristics of detected abnormal points, acting as an intermediate layer that refines detection accuracy while reducing false positive rates.
Data Source
AI summary
The present disclosure discloses a calibration method and system for medical imaging. The calibration method comprising: obtaining imaging data; dividing the imaging data into a plurality of patches; and calibrating the imaging data based on one or more target patches of the plurality of patches, wherein the one or more target patches is a part of the plurality of patches.