AI Lung Volume Estimation From 2D X-Ray and Clinical Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional lung volume measurement methods using spirometers are inaccurate for patients with stiff lungs due to disorders like pulmonary fibrosis, and CT scans are costly and time-consuming for lung volume estimation.
Innovation Solution
A lung volume estimation method using a two-dimensional medical image and clinical information through an artificial intelligence model to determine lung volume.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a spirometer is used to measure lung volume, then the measurement process is simple, but the accuracy deteriorates for patients with stiff lungs due to pulmonary fibrosis
Solution Approach 1:
The patent replaces the mechanical spirometer with an AI-based system that processes 2D medical images. The AI model analyzes chest X-ray images and combines them with clinical information to estimate lung volume, eliminating the need for mechanical breathing exercises and directly addressing the accuracy issue for patients with stiff lungs.
Solution Approach 2:
The patent introduces an intermediary AI model that acts as a mediator between the 2D medical image and the lung volume measurement. This intermediary processes the image data and clinical information to produce accurate lung volume estimates, bridging the gap between simple imaging and precise measurement.
2Measurement precision
If a CT scan is performed to obtain lung volume, then the measurement accuracy is improved, but the cost and time consumption increase
Solution Approach 1:
The patent uses a 2D chest X-ray image as a copy or representation of the lung structure, instead of requiring a full 3D CT scan. The AI model processes this 2D copy along with clinical information to extract lung volume data, achieving accurate measurements without the time and cost burden of CT scanning.
Solution Approach 2:
The patent transitions from 3D CT imaging to 2D X-ray imaging, reducing the dimensionality of the data required. By processing 2D images through AI, the system achieves sufficient accuracy for lung volume measurement while significantly reducing scan time and cost.
3Measurement precision
If a CT scan is performed to obtain lung volume, then the measurement accuracy is improved, but the cost increases
Solution Approach 1:
The patent uses a 2D chest X-ray image as a cost-effective copy of the lung structure, replacing expensive 3D CT scans. The AI model processes this lower-cost 2D image to produce accurate lung volume estimates, significantly reducing the financial burden while maintaining measurement precision.
4Measurement precision
If lung region separation is performed on 3D medical images, then the lung volume can be obtained, but the process complexity increases
Solution Approach 1:
The patent replaces complex 3D image segmentation algorithms with a simpler AI-based processing system. The AI model directly processes 2D X-ray images and clinical information to estimate lung volume, eliminating the need for complex region separation processes while maintaining accurate measurements.
Data Source
AI summary
Provided are a lung volume estimation method and an apparatus therefor. The lung volume estimation apparatus inputs two-dimensional medical image and clinical information of a patient into an artificial intelligence model to determine the patient's lung volume. The artificial intelligence model may include a first neural network that generates an encoded image for the two-dimensional medical image and a second neural network that determines a lung volume from data obtained by concatenating an output value of the first neural network with the clinical information.