Meeting Banner
Abstract #4646

Classification of COPD and ILD Subtypes Using 129Xe MRI/MRS with Unsupervised Cluster Analysis

Fuyao Li1, David Mummy2, Suphachart Leewiwatwong1, Anna Costelle3, Hong Qin2, and Bastiaan Driehuys1,2,3
1Biomedical Engineering, Duke University, DURHAM, NC, United States, 2Radiology, Duke University, DURHAM, NC, United States, 3Medical Physics Graduate Program, Duke University, DURHAM, NC, United States

Synopsis

Keywords: Hyperpolarized MR (Gas), Hyperpolarized MR (Gas), Machine Learning, Hyperpolarized Xenon MRI, Chronic Obstructive Pulmonary Disease, Interstitial Lung Disease

Motivation: 129Xe MRI/MRS can assess distinct aspects of pulmonary gas exchange and hemodynamics. However, there is no gold standard against which these metrics can be validated.

Goal(s): To evaluate whether unsupervised cluster analysis of 129Xe MRI/MRS metrics naturally reveal patterns known to be associated with certain disease groups.

Approach: Eight 129Xe MRI/MRS features were subjected to k-means clustering with internal validation indices used to determine optimal cluster number.

Results: The analysis identified four clusters that largely distinguished healthy, COPD, and ILD patient groups.

Impact: This study offers a pathway for designing future prospective clinical trials that could validate non-invasive 129Xe MRI/MRS metrics of gas exchange by demonstrating that certain patterns distinguish between lung disease subtypes with high accuracy.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords