Quantification of ¹²⁹Xe MRI Ventilation-defect-percent Using Binary-threshold, Gaussian Linear-Binning and K-means...

Hyperpolarized ¹²⁹Xe magnetic resonance imaging (MRI) provides a way to quantify ventilation heterogeneity as ventilation defect percent (VDP), calculated as the volume of unventilated lung volume normalized to the thoracic cavity volume. Currently used methods for quantifying VDP include (1) binary signal-intensity thresholds (Binary-threshold, BT), (2) Gaussian transformation of signal-intensity histogram with standard deviation thresholds or Gaussian-linear-binning (GLB), and (3) iterative centroid-based clustering of the signal-intensity histogram (k-means). These methods have not been directly compared in patients with asthma and chronic obstructive pulmonary disease (COPD), in whom ventilation defects are hallmark findings. Our objective was to quantify and compare VDP using these four different methods.

Data from 175 participants (n=42 healthy, n=43 COPD, n=90 asthma) were retrospectively evaluated using a CNN co-registration and segmentation pipeline and GLB, GLB_slice, (slice-wise evaluation of GLB) BT and k-means VDP quantification methods. Linear-regression and Bland-Altman plots were used to quantify inter-method correlations and agreement.

VDP was significantly different using GLB (Asthma: 6±9%, COPD: 7±7%, p<.001) and BT (Asthma: 6±7%, COPD: 10±8%, p<.001) methods compared to GLB_slice (Asthma: 12±13%, COPD: 16±15%, p<.001) and k-means (Asthma: 12±12%, COPD: 25±17%, p<.001). VDP calculated using GLB (R²=.64, p<.001), GLB_slice (R²=.84, p<.001) and BT (R²=.84, p<.001) was significantly correlated with k-means VDP. Bland-Altman plots revealed wide 95% confidence intervals of agreement for k-means with GLB/GLB_slice (COPD -6%/-1%: 42%/23%; asthma -5%/-10%:16%/10%) and BT (COPD -4%:36%; asthma -6%:19%).

VDP differences in patients with asthma and COPD calculated using four methods are important to consider for multi-center studies.