Related Experiment Video
Updated: Jun 1, 2026
13:01
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
Published on: June 3, 2022
Computer-Aided Grading of Lymphangioleiomyomatosis (LAM) using HRCT
Jianhua Yao1, Nilo Avila, Andrew Dwyer
1Diagnostic Radiology Department, Clinical Center, National Institute of Health, Bethesda, MD, USA.
Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition
|June 1, 2011
Summary
A new computer system accurately grades lung involvement in lymphangioleiomyomatosis (LAM) using texture analysis. This tool correlates well with expert assessments and lung function, aiding disease progression tracking.
Area of Science:
- Radiology
- Medical Imaging
- Pulmonary Medicine
Background:
- Lymphangioleiomyomatosis (LAM) is a rare, multisystem disorder characterized by smooth muscle cell proliferation, leading to lung destruction.
- Current subjective grading of LAM on high-resolution computed tomography (HRCT) is often imprecise and challenging, particularly in severe cases.
Purpose of the Study:
- To develop and evaluate a computer-aided system for objective grading of LAM involvement in the lungs.
- To assess the correlation of the computer-generated grade with subjective radiologist assessments and pulmonary function tests.
Main Methods:
- A computer-aided evaluation system was developed utilizing a committee of support vector machines for classification.
- The system analyzes lung texture patterns to quantify LAM involvement.
- The system was validated on a cohort of 36 patients.
Main Results:
- The computer-generated LAM grade showed a strong positive correlation with subjective radiologist grades (R=0.91, p<0.0001).
- The computer grade also demonstrated a significant correlation with pulmonary functional tests (R=0.85, p<0.0001).
- The system proved capable of precise assessment of disease progression over time.
Conclusions:
- Computer-aided analysis of lung texture patterns offers an objective and precise method for grading LAM involvement on HRCT.
- This system has the potential to improve diagnostic accuracy and patient management by providing reliable disease assessment and progression monitoring.
