Automated Medical Image Follow-Up Reading Through Body-Region Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Medical professionals face challenges in efficiently and automatically selecting relevant previous medical images for comparison with current images due to the large number of possible reference images, which are often stored remotely and require significant network resources for retrieval.
Innovation Solution
A method and system for automatically selecting reference medical images by determining a region of interest, comparing body regions, and performing registration between target and candidate medical image series using machine learning and image registration techniques, allowing for efficient and flexible selection of images appropriate for comparison.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all prior medical images for a patient are retrieved for manual assessment, then the medical professional can assess the appropriateness of previous images, but the network resources consumed increase significantly and the process becomes time-consuming
Solution Approach 1:
The patent extracts only the necessary metadata (body region, imaging modality, date) from the large volume of medical image data, rather than retrieving all images. This selective extraction allows the system to filter and present only relevant reference images for comparison, significantly reducing network bandwidth consumption while maintaining assessment accuracy.
Solution Approach 2:
The patent introduces an intermediary processing layer (the processing device) that acts between the remote storage and the medical professional's terminal. This intermediary automatically filters, selects, and pre-processes reference images based on metadata comparison, reducing the data transmission burden on network resources while ensuring only appropriate images are presented for review.
2Measurement precision
If all prior medical images for a patient are retrieved for manual assessment, then the medical professional can assess the appropriateness of previous images, but the time required for assessment increases significantly
Solution Approach 1:
The patent performs preliminary actions by automatically filtering and selecting reference images before they are presented to the medical professional. The system pre-comparates metadata (body region, imaging modality, date) to identify appropriate reference images in advance, so that when the professional reviews images, only the most relevant ones are already selected, dramatically reducing assessment time while maintaining accuracy.
Solution Approach 2:
The system performs self-service by automatically selecting and presenting reference images without requiring manual intervention from the medical professional. The processing device autonomously compares metadata, identifies relevant images, and prepares them for display, freeing the professional to focus only on actual medical assessment rather than image selection.
3Quantity of substance
If medical images are stored remotely for centralized access, then storage capacity is optimized, but retrieving large image datasets requires significant network resources
Solution Approach 1:
The patent segments medical image data into two components: large image files stored remotely for centralized storage, and smaller metadata records (body region, modality, date) that can be efficiently transmitted over networks. By processing and comparing only the metadata for selection decisions, the system enables remote storage optimization without incurring high network resource costs for retrieving complete image datasets.
Data Source
AI summary
At least some example embodiments of methods and systems for generating display data of a medical image data set include identifying, for a target medical image series of a patient at a first point in time, a reference medical image series of the patient taken at a second point in time different from the first point in time. In particular, the selection may be based on a comparison of respectively depicted body regions of the patient. Further, methods and systems may be directed to generating display data to cause a display device to display a rendering of the reference medical image series based on a registration between the target medical image series and the reference medical image series.