Medical Image Report Hyperlinking via NLP Feature Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current medical image reporting systems lack an automated means to link medical image reports to corresponding images, leading to manual and error-prone navigation, especially when images are sent to different facilities, and absolute links are often broken due to inaccessible image storage systems.

Innovation Solution

The system employs natural language processing (NLP) to extract image features from reports and compare them with features extracted from images, creating selectable data links between the report and images, allowing for automatic insertion of hyperlinks that enable seamless navigation between reports and images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If manual navigation to images is used, then physicians can access images, but it takes an extended period of time especially when a large number of images were taken

Engineering Contradiction:

Improvetime to navigate to imagesVSAvoidmanual navigation process

Core Design Contradiction:

Loss of timeVSEase of operation

Solution Approach 1:

The system performs preliminary action by automatically generating hyperlinks between report entries and corresponding images before the physician needs to access them. The NLP processing and hyperlink insertion occur in advance, so when the physician views the report, the navigation paths are already prepared, eliminating the time-consuming manual search process.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Hyperlinks serve as an intermediary element between the report text and the image database. Instead of direct manual navigation, the hyperlink acts as a mediator that automatically guides the physician from the report entry to the relevant image, streamlining the access process.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If physicians manually add reference numbers or identifiers for images, then links can be created, but the process is error-prone and relies on manual input

Engineering Contradiction:

Improveaccuracy of image referencesVSAvoidmanual addition of references

Core Design Contradiction:

ReliabilityVSExtent of automation

Solution Approach 1:

The system performs self-service by automatically extracting image features from both the report and images, comparing them, and generating hyperlinks without human intervention. The NLP processor and feature comparison algorithms autonomously complete the linking task, eliminating manual input errors and improving reliability.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical process of adding reference numbers is replaced with an automated computational system. NLP technology and image feature comparison algorithms substitute the manual typing and matching process, thereby eliminating human error and improving accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If embedded links are used in plain text reports, then image references can be included, but the links impede readability and formatting of the report

Engineering Contradiction:

Improveability to store images in reportVSAvoidreadability and formatting

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system segments the linking function from the report display. Hyperlinks are inserted in a controlled manner at specific locations in the report text, allowing the report to maintain its plain text readability while providing automated navigation capabilities through strategically placed, unobtrusive links.

Inventive Principle:

Principle #1Segmentation

4Adaptability or versatility

If absolute links are used for image references, then image viewers can be launched with full URL context, but the links are broken when images are sent to different facilities

Engineering Contradiction:

Improvelink functionality across facilitiesVSAvoidlink accessibility

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The hyperlink system is designed to be dynamic and adaptive. When images and reports are moved between facilities, the system can update the hyperlink references to maintain functionality. The links are not static absolute URLs but can be dynamically adjusted to point to the correct image locations in different storage systems or facilities.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS10825173B2Automatically linking a description of pathology in a medical image report to an image

Publication Date: 2020.11.03 MERATIVE US LP

AI summary

Methods and systems for automatically linking entries in a medical image report to an image of a medical image study. One method includes identifying a description of pathology in text included in the medical image report using natural language processing and applying a model to select for the medical image report at least one modality and at least one image included in the at least one medical image study generated by the at least one modality. The method also includes creating a data link between the description of pathology and the at least one image included in the at least one medical image study generated by the at least one modality, and automatically inserting the data link into the medical image report, the data link being selectable to display the at least one image included in the at least one image generated by the at least one modality.