Joint Image Prediction Model for Early Symptom Progression Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies fail to accurately predict the onset and progression of joint-related symptoms, which can significantly reduce the quality of life of subjects, necessitating early detection and intervention.

Innovation Solution

A prediction device utilizing a neural network-based model to analyze medical images of joints, predicting future symptoms and intervention effects, incorporating machine learning to generate reliable prediction information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a prediction model is developed to predict joint-related symptoms, then the ability to detect and intervene early is improved, but the complexity of the system increases

Engineering Contradiction:

Improveprediction accuracyVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The prediction model is divided into multiple independent prediction units, each responsible for predicting specific joint-related symptoms (e.g., osteoarthritis, osteoporosis, joint inflammation). Each unit processes medical images independently and outputs specialized prediction results, allowing the system to handle complex prediction tasks through modular components rather than a monolithic complex system

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

A support vector machine (SVM) classifier is introduced as an intermediary component that integrates predictions from multiple prediction units. The SVM receives prediction results from various units and synthesizes them into comprehensive prediction information, acting as a mediator that coordinates the complexity of multiple specialized units while presenting a unified output

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If machine learning is used to analyze medical images, then prediction reliability is improved, but the difficulty of detecting and measuring increases

Engineering Contradiction:

Improveprediction reliabilityVSAvoidmodel training difficulty

Core Design Contradiction:

ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The system performs preliminary actions by pre-processing medical images to extract relevant features and characteristics before feeding them into the prediction models. Image segmentation, feature extraction, and data preparation are conducted in advance, reducing the complexity of real-time prediction and making the overall system more manageable and easier to implement

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system transforms medical images into standardized numerical parameters and features that can be processed by machine learning algorithms. By converting visual data into quantifiable parameters (e.g., joint space width, bone density, cartilage thickness), the system simplifies the detection and measurement processes while maintaining prediction reliability

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12469129B2Prediction device, prediction system, control method, and control program

Publication Date: 2025.11.11 KYOCERA CORP

AI summary

A prediction device includes a first prediction unit that outputs first prediction information regarding a joint at a second point in time after a predetermined period of time from a first point in time, from a medical image showing the joint of a subject at the first point in time. The first prediction unit includes a first prediction model capable of estimating the first prediction information from the medical image.