Medical Imaging Device Use Information Acquisition via Text Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The diverse information formats of different medical imaging systems make it labor-intensive and inefficient to acquire use information for each medical imaging device.
Innovation Solution
A method involving the acquisition of an image sequence from medical imaging devices, performing text recognition on specific regions of the images, and generating use information based on the recognized text.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If text recognition is performed on the entire image for each medical imaging device, then complete information can be extracted, but the workload and computational resources increase significantly
Solution Approach 1:
The patent divides the image into multiple regions of interest (ROIs) that contain specific textual information such as device parameters, operational status, and metadata. By segmenting the image and focusing text recognition only on these predefined regions rather than the entire image, the system reduces computational workload while maintaining information extraction completeness.
Solution Approach 2:
The patent applies text recognition technology selectively to specific local regions where textual information is expected to appear, such as device identifiers, operational parameters, and status indicators. This localized approach concentrates computational resources on areas most likely to contain useful information, improving processing efficiency without sacrificing data completeness.
2Adaptability or versatility
If text recognition is performed on all images from diverse medical imaging systems, then comprehensive use information can be acquired, but the complexity and time required increase
Solution Approach 1:
The patent establishes a universal text recognition framework that can process images from multiple different medical imaging systems (ultrasound, CT, MRI, PET) by identifying and extracting text from standardized regions of interest. This universal approach enables the system to handle diverse formats and manufacturers without requiring system-specific processing, reducing overall acquisition time while maintaining multi-system compatibility.
3Measurement precision
If manual determination of use information is performed for each device, then accuracy can be maintained, but the workload becomes very large
Solution Approach 1:
The patent enables the system to automatically extract use information from device images through automated text recognition and processing. The system self-services by automatically identifying, extracting, and interpreting textual data from medical imaging device images, eliminating the need for manual determination while maintaining accuracy through automated validation processes.
Data Source
AI summary
Provided in embodiments of the present application are a method for acquiring use information of a medical imaging device, an apparatus, and a system. The method for acquiring use information of a medical imaging device includes: acquiring an image sequence, wherein the image sequence is generated by the medical imaging device and includes a plurality of images in a time dimension; performing text recognition on a specific region of the images and generating text information; and generating use information of the medical imaging device according to the text information.