AI Body Tissue Segmentation for Accurate Medical Image Composition Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing body composition analysis methods, such as bioimpedance measurement, suffer from inaccuracies due to subject motion and muscular tension, and fail to accurately measure skin, internal organs, and bone composition.
Innovation Solution
A method and apparatus using a medical image to analyze body composition by training a first AI model to segment body tissues like skin, bone, internal organ, blood vessel, and fat, and recognizing body composition information based on region, volume, or weight.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If bioimpedance measurement is used to analyze body composition, then the measurement process is simple and quick, but the accuracy varies due to subject motion and muscular tension
Solution Approach 1:
The patent replaces the electrical measurement system (bioimpedance) with an optical imaging system (medical image processing). Instead of using electrical current to measure body composition, the system uses medical images (X-ray, CT, MRI, or ultrasonic images) to visually capture and analyze body tissue distribution, thereby eliminating errors caused by subject motion and muscular tension during electrical measurement.
2Device complexity
If bioimpedance measurement is used, then the equipment is simple, but it cannot accurately measure skin area or composition of internal organs and bones
Solution Approach 1:
The patent employs a multi-functional medical image processing system that can simultaneously measure various body compositions including skin area, subcutaneous fat, muscle mass, bone density, and internal organ composition. The system processes medical images to extract multiple types of body composition information in one measurement session, making the equipment versatile for comprehensive body analysis.
3Measurement precision
If medical image-based AI model is used to segment body tissues, then measurement accuracy is improved, but device complexity increases
Solution Approach 1:
The patent introduces an intermediary AI model that acts as a bridge between the medical image input and the body composition analysis output. The AI model is trained to automatically segment and identify different body tissues (skin, subcutaneous fat, muscle, bone, internal organs) from medical images, converting complex image data into quantifiable body composition measurements without requiring manual analysis.
4Loss of information
If multiple body tissue regions are segmented using AI model, then comprehensive body composition analysis is achieved, but processing time and computational resources increase
Solution Approach 1:
The patent applies preliminary action by pre-training the AI model with extensive training data before actual measurement. The model learns to efficiently segment and identify different body tissues during the training phase, so that during actual measurement, it can quickly process medical images and provide comprehensive body composition analysis without requiring excessive processing time or computational resources.
Data Source
AI summary
Provided are a method and an apparatus for analyzing a body composition by using a medical image. The apparatus for analyzing the body composition trains a first artificial intelligence model by using training data labelling a body tissue region, such as muscle or fat, in a medical image for training, and then, segments a body tissue from an examination medical image by using the first artificial intelligence model and outputs body composition information based on a region, a volume, or a weight of the body tissue of the examination medical image. The disclosure is a technique developed through the Seoul Business Agency's 2020 support project for artificial intelligence (AI) technology industrialization (CY20053), “AI Verification and Industrialization of Computed Tomography (CT) Image-based Opportunistic Screening of Metabolic Syndrome, Osteoporosis, and Muscle Reduction.”