Medical Image Size Measurement Using Reference Object Masking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical image processing methods are prone to inaccurate measurements due to lens deformation and changes in biological tissue during medical examinations, particularly when manually measuring target objects like polyps using endoscopes.
Innovation Solution
A medical image processing method and apparatus that utilize a neural network, such as Mask RCNN, to determine the size of a target object by comparing it to a reference object with known size, using a preset mapping relationship to calculate the target size in real-time, thereby minimizing the impact of deformation and tissue changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual measurement methods are used to measure target objects in medical images, then the measurement process is simple to operate, but the measurement precision deteriorates due to lens deformation and tissue changes
Solution Approach 1:
The patent introduces a reference object with known size as an intermediary element in the measurement process. This reference object serves as a mediator between the imaging system and the target object, enabling accurate size calculation of the target object by comparing their feature sizes in the medical image, thereby compensating for lens deformation and tissue changes without requiring complex calibration procedures
Solution Approach 2:
The patent changes the measurement parameter from direct physical measurement to ratio-based calculation. By calculating the ratio between the feature size of the target object and the reference object in the image, and then applying a preset mapping relationship, the system achieves accurate measurement that is invariant to lens deformation and tissue changes
2Productivity
If real-time measurement is implemented to improve examination efficiency, then the productivity improves, but the measurement precision deteriorates due to tissue changes during the examination process
Solution Approach 1:
The patent performs preliminary action by placing a reference object with known size into the examination field before measuring the target object. This reference object remains in the field throughout the examination, providing a stable reference that compensates for tissue changes and lens deformation occurring during real-time observation, enabling continuous accurate measurement without sacrificing productivity
Solution Approach 2:
The system uses the reference object as a feedback mechanism to continuously monitor and compensate for changes in the imaging conditions. By comparing the measured feature size of the reference object against its known size, the system can detect and correct for lens deformation and tissue changes in real-time, maintaining measurement precision throughout the examination
Data Source
AI summary
A medical image processing method includes: determining a target mask of a target object in a medical image and a reference mask of a reference object in the medical image, the target mask indicating a position and a boundary of the target object, and the reference mask indicating a position and a boundary of the reference object; determining a feature size of the target object based on the target mask; determining a feature size of the reference object based on the reference mask; and determining a target size of the target object based on the feature size of the reference object, a preset mapping relationship between the feature size of the reference object and a reference size, and the feature size of the target object.