Keywords: Hyperpolarized MR (Gas), Hyperpolarized MR (Gas), Asthma, Machine learning, Texture analysis
Motivation: 129Xe MRI ventilation texture features provide a way to generate quantitative spatial information about ventilation heterogeneity beyond ventilation defect percent, which is important in some asthma patients with patchy (and not obviously segmental or subsegmental) ventilation abnormalities.
Goal(s): Machine-learning and 129Xe MRI ventilation texture-analysis were used to generate ventilation-imaging based models for predicting ICS/LAMA/LABA response.
Approach: Machine-learning models trained on clinical measurements were compared with those trained on ventilation texture features.
Results: MRI texture-based models outperformed clinical models for predicting 6-week response. The neighbourhood gray-tone difference matrix strength was the top-ranking texture feature, which significantly correlated with clinical measurements.
Impact: 129Xe MRI ventilation texture features provided unique information about ventilation abnormalities and ventilation patchiness; when texture features were embedded in predictive models, these features outperformed clinical models explaining response to ICS/LAMA/LABA in moderate asthma.
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.
Keywords