Paranasal Sinus CT Opacification Scoring With CNN Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for assessing paranasal sinus opacification in CT scans are time-consuming, subjective, and impractical for routine clinical use, lacking objective quantification and correlation with clinical metrics.

Innovation Solution

A convolutional neural network (CNN) is trained to perform automated volumetric segmentation and scoring of paranasal sinus opacification, using CT scans to generate objective and precise opacification scores, correlating with clinical parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual image segmentation is used for volumetric analysis of paranasal sinus cavities, then measurement precision is improved, but loss of time increases and productivity decreases

Engineering Contradiction:

Improvevolumetric measurement precisionVSAvoidanalysis time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical segmentation with an automated computer-based system that uses machine learning algorithms to perform volumetric analysis of paranasal sinus cavities. This substitution eliminates the need for manual tracing and measurement while maintaining high precision through algorithmic boundary detection and volume calculation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service automated segmentation where the computer algorithm independently identifies sinus cavity boundaries, segments the cavities, and calculates volumes without requiring manual intervention. The machine learning model automatically adapts to different anatomical variations and pathologies, performing the entire analysis pipeline autonomously.

Inventive Principle:

Principle #25Self-service

2Productivity

If automated volumetric analysis is implemented, then productivity is improved and loss of time is reduced, but device complexity increases

Engineering Contradiction:

Improveanalysis throughputVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary segmentation and volume calculation automatically during the imaging process, preparing the volumetric data in advance before clinical review. This preliminary automated analysis is integrated into the workflow, eliminating the need for separate manual measurement steps and enabling rapid assessment.

Inventive Principle:

Principle #10Preliminary action

3Ease of operation

If visual scoring is used for sinus opacification assessment, then ease of operation is maintained, but measurement precision and objectivity deteriorate

Engineering Contradiction:

Improvescoring simplicityVSAvoidopacification quantification accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system transforms the subjective visual scoring parameter into an objective volumetric measurement parameter. Instead of relying on radiologist visual assessment of opacification extent, the system automatically calculates the precise volume of opacified regions using image processing algorithms, providing quantitative data that is both accurate and objective.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260051076A1Systems and methods of volumetrically assessing structures of skeletal cavities

Publication Date: 2026.02.19 NAT JEWISH HEALTH

AI summary

Systems and methods of detecting a presence of opacification or pneumatization in skeletal structures of patients are disclosed. The systems and methods include receiving images, processing the images using a convolutional neural network, and generating, with the convolutional neural network, an opacification score for the image. Systems and methods include training the convolutional neural network to delineate skeletal structure pixels within a computed tomography scan image and to generate an intensity value for each skeletal structure pixel within a computed tomography scan image to determine an opacification score for the computed tomography scan image.