CT Nodule State Change Prediction for pGGO Follow-Up Timing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current CADx devices for lung cancer diagnosis struggle to provide timely information on the potential solid transformation of pure ground-glass opacity (pGGO) nodules, which are associated with uncertainty in management pathways due to their unpredictable behavior, leading to prolonged and potentially unnecessary follow-up periods.

Innovation Solution

A CADx system with a feature state change prediction circuit that analyzes medical images, particularly CT scans, to predict the time frame for transformation from pGGO to semi-solid or solid nodules, incorporating machine learning models to determine nodule attenuation and activate specific prediction tasks based on clinical parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If CADx devices provide only malignancy risk scores, then the device complexity is low and ease of operation is high, but the loss of information occurs as urgency indication is not provided

Engineering Contradiction:
Improveurgency indicationVSAvoiddevice complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system segments the risk assessment into two distinct components: malignancy risk score and solid transformation probability. This segmentation allows the device to provide comprehensive information (including urgency indication) while maintaining clear, separate output modules that do not significantly increase operational complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system adds a new dimension to the risk assessment by introducing temporal prediction (solid transformation probability within specific time frames). This transforms the static malignancy risk score into a dynamic assessment that includes both malignancy likelihood and transformation urgency, providing comprehensive information without requiring complete system redesign.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If CADx devices provide only malignancy risk scores, then the device complexity is low, but the reliability is insufficient for clinical decision-making

Engineering Contradiction:
ImprovereliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary classification of GGO nodules based on their likely transformation behavior. By pre-categorizing nodules into time-frame groups (e.g., likely to transform within 6 months, 1-2 years, or longer), the system provides reliable guidance for clinical decision-making while using established machine learning models that do not significantly increase device complexity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary prediction layer that bridges malignancy risk assessment and clinical urgency determination. The solid transformation probability acts as a mediator that translates complex imaging features into clinically actionable urgency indicators, enhancing reliability without requiring direct complex clinical decision logic in the device.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If prolonged follow-ups are required for GGO nodules, then the reliability of diagnosis is maintained, but the loss of time occurs and productivity is reduced

Engineering Contradiction:
ImproveproductivityVSAvoiddiagnosis reliability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system dynamically adjusts follow-up recommendations based on predicted solid transformation probability. Instead of uniform prolonged follow-ups for all GGO nodules, the system adapts follow-up intervals to individual nodule characteristics, enabling earlier intervention for high-risk cases and reducing unnecessary follow-ups for low-risk cases, thereby improving both productivity and maintaining diagnosis reliability.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the key parameter from static malignancy risk to dynamic transformation probability over time. By predicting when solid transformation is likely to occur, the system optimizes follow-up timing parameters, allowing clinicians to intervene at the optimal moment rather than relying on fixed prolonged follow-up schedules, thus improving productivity while maintaining reliability.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4246527B1Method and apparatus to predict feature state change within an image
Publication Date: 2026.05.20 OPTELLUM LTD
  • EP4246527B1 patent drawingFigure 1
  • EP4246527B1 patent drawingFigure 2
  • EP4246527B1 patent drawingFigure 3

AI summary

A CADx system for analysing medical images to monitor at least one feature on the image to predict at least one of a change of the state or maintenance of the current state of a monitored feature within a time frame is described. The system comprising: an input circuit for receiving at least one medical input image; a feature state change circuit for analysing the received input image and predicting a state change comprising: a state change predictor to predict a state change of the monitored feature within the time frame; and an output circuit to output an indication of the change of state or maintenance of the current state of the monitored feature within the time frame based on the prediction of the feature state change predictor. A method of training a feature state change prediction circuit using Machine Learning is also described.