Skip to Main Content

An official website of the United States government

Analysis of Chest X-rays Based on Deep Learning for Health Risk Assessment

Principal Investigator
Name
Yu Fei Huang
Degrees
M.E.
Institution
China Medical University
Position Title
Student
Email
About this CDAS Project
Study
PLCO (Learn more about this study)
Project ID
PLCOI-1730
Initial CDAS Request Approval
Nov 5, 2024
Title
Analysis of Chest X-rays Based on Deep Learning for Health Risk Assessment
Summary
This project aims to utilize deep learning techniques to analyze chest X-rays (CXR) for health risk assessment and biological age prediction. By automatically segmenting and extracting features from key anatomical structures in chest images, the study will quantify changes in structures such as the lungs, heart, and blood vessels, thereby assessing the biological aging process of individuals. Additionally, the research will develop a multi-task learning framework that combines image features for early screening of high-risk diseases, such as chronic obstructive pulmonary disease (COPD). The goal of this project is to advance the application of medical imaging in health management and provide new scientific evidence for individual preventive health assessments.
Aims

1.Develop a Deep Learning Model for CXR Analysis: Construct and refine a model focused on analyzing anatomical structures in chest X-rays (CXR) to estimate biological age, supporting personalized health assessments in medical imaging.
2.Health Risk Assessment and Early Detection: Identify and extract key imaging features from CXR scans to assess health risks related to lung diseases, aiming to improve non-invasive, early screening methods for high-risk individuals.
3.Implement a Multi-Task Learning Framework: Develop a framework that integrates anatomical segmentation with lesion detection to enhance the accuracy and robustness of the model, supporting diverse applications in medical imaging.
4.Clinical Translation and Application: Validate the model’s efficacy in clinical settings, exploring its potential to streamline diagnostics and advance the use of artificial intelligence in health management and preventive care.

Collaborators

1.Professor Jiang Xiran, China Medical University
2.Department of Radiology, The First Affiliated Hospital of China Medical University