Temporal Lung Risk Scoring for Variable-Interval Medical Imaging

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current CADx systems struggle to effectively handle unstructured temporal data for lung nodule assessment, as they are typically designed for fixed temporal data, failing to account for variable intervals and sequence lengths in clinical management scenarios, leading to potential false positives and negatives.

Innovation Solution

A CADx system utilizing a recursive neural network that processes unstructured temporal data, including variable intervals between medical image scans and clinical parameters, to provide a lung disease risk measure by encoding time stamps and updating system states, allowing for flexible temporal data analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If current CADx systems use fixed temporal data processing methods, then system design is simplified, but accuracy in handling variable interval clinical data deteriorates

Engineering Contradiction:
Improvesystem design complexityVSAvoidlung disease risk assessment accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The system transitions from static fixed-interval processing to dynamic variable-interval processing by introducing a time interval calculator that computes Δt between consecutive scans and a variable selector that adapts the processing interval based on clinical context, allowing the system to handle both routine and urgent assessments optimally

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the temporal parameter from fixed to variable by incorporating time interval calculations and allowing the processing interval to be adjusted based on the specific clinical scenario, improving accuracy for both routine follow-ups and urgent reassessments

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If CADx systems process only fixed interval scan data, then data processing is more straightforward, but reliability in variable interval clinical scenarios deteriorates

Engineering Contradiction:
Improvedata processing simplicityVSAvoidrisk assessment reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system introduces dynamic interval adjustment mechanisms including a time interval calculator and variable selector that adapts processing based on whether the scenario is routine or urgent, making the system reliable across different clinical workflows without sacrificing operational simplicity

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system achieves universality by designing a multi-functional processing pipeline that can handle both fixed and variable interval data, routine and urgent scenarios, and different clinical workflows through a single integrated architecture with adaptive interval selection

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Measurement precision

If the system uses variable temporal intervals for data processing, then accuracy in clinical scenarios improves, but system complexity increases

Engineering Contradiction:
Improverisk assessment accuracyVSAvoidsystem architecture complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the processing pipeline into distinct functional modules: time interval calculator, variable selector, and adaptive processing components, allowing each to handle specific aspects of variable interval processing independently while maintaining overall system manageability

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The variable selector acts as an intermediary component that bridges the time interval calculator and the main processing pipeline, translating variable time intervals into appropriate processing parameters without requiring complete restructuring of the underlying system architecture

Inventive Principle:
Principle #24Intermediary (Mediator)

4Ease of manufacture

If CADx systems assume fixed scan intervals, then model training is simpler, but false positives and negatives increase

Engineering Contradiction:
Improvemodel training simplicityVSAvoiddiagnosis accuracy
Core Design Contradiction:
Ease of manufactureVSReliability

Solution Approach 1:

The system changes the temporal parameter from fixed to variable during model training by incorporating time interval calculations and using these variable intervals as inputs to the risk assessment model, enabling the model to learn patterns specific to different scan intervals and reducing false positives and negatives

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4002382B1Using unstructured temporal medical data for disease prediction
Publication Date: 2026.03.18 OPTELLUM LTD
  • EP4002382B1 patent drawingFigure 1
  • EP4002382B1 patent drawingFigure 2
  • EP4002382B1 patent drawingFigure 3

AI summary

A method for providing a lung disease risk measure in a Computer Aided Diagnosis system is described. The method comprising the steps of: receiving a plurality of inputs for a subject, each input comprising at least one image showing all or part of the lungs of a patient and a time stamp for the image, where the inputs are obtained at varying intervals; analysing the inputs to assess temporal changes in the images using at least one of an input data encoder and a time stamp encoder; inputting the output of at least one of the encoders to a score calculator to calculate a risk score; outputting the risk score indicating the lung disease risk for the subject. A Computer Aided diagnosis system for implementing the method is also described.