Search

Background: Three‐dimensional (3D) ventilation flow capacity‐weighted (VFCW) maps together with 3D ventilation‐weighted (VW) maps may help to better assess pulmonary function. Purpose: To investigate the use of 3D VFCW and VW maps for evaluating pulmonary ventilation function. Study Type: Prospective. Population: Two patients (one male, 85 years old; one female, 64 years old) with chronic obstructive pulmonary disease (COPD) and nine healthy subjects (all male; 23–27 years). Field Strength/Sequence: 3‐T, 3D radial UTE imaging. Assessment: 3D VFCW and VW maps were calculated from 3D UTE MRI by voxel‐wise subtraction of respiratory phase images. Their validation was tested in nine healthy volunteers using slow/deep and fast/shallow breathing conditions. Additional validation was performed by comparison with single photon emission computed tomography (SPECT) ventilation maps of one healthy participant. For comparison, gravity dependence of anterior–posterior regional ventilation was assessed by one‐dimensional plot of the mean signal intensity for each coronal slice. Structural similarity index measure was also calculated. Finally, VW maps and VFCW maps of two COPD patients were evaluated for emphysema lesions with reference to CT images. Statistical Tests: Wilcoxon sign‐rank tests for regional Ventilation and ventilation flow capacity, analysis of variance, post‐hoc t‐tests and Bonferroni correction, coefficient of variation, Kullback–Liebler divergence. A P‐value <0.05 was considered statistically significant. Results: The validation of 3D VFCW and VW maps was shown by statistically significant differences in ventilation flow capacity and ventilation between the breathing conditions. Additionally, UTE‐MRI and SPECT‐based ventilation maps showed gravitational dependence in the anteroposterior direction. When applied to patients with COPD, the use of 3D VFCW and VW maps was able to differentiate between two patients with different phenotypes. Data Conclusion: The use of 3D VFCW and VW maps can provide regional information on ventilation function and potentially contribute to assessment of COPD subtypes and disease progression. Evidence Level: 2 Technical Efficacy: Stage 1 [ABSTRACT FROM AUTHOR]

In this paper, a novel deep learning approach based on conditional FLOW is proposed for sea clutter augmentation. Sea clutter data augmentation is important for testing detection algorithms for maritime remote sensing and surveillance due to the expensive and time-consuming nature of sea clutter data acquisition. Whereas the conventional parametric methods face challenges in finding appropriate distributions and modeling time correlations of sea clutter data, the proposed deep learning approach, GCC-FLOW, can learn the data distribution from the data without explicitly defining a mathematical model. Furthermore, unlike the existing generative deep learning approaches, the proposed GCC-FLOW is able to synthesize sea clutter data of arbitrary length with the stable autoregressive structure using conditional FLOW. In addition, the proposed algorithm generates sea clutter data not only with the same characteristics of the training data, but also with the interpolated characteristics of different training data by introducing a global condition variable corresponding to the target characteristic, such as sea state. Experimental results demonstrate the effectiveness of the proposed GCC-FLOW in generating sea clutter data of arbitrary length under different sea state conditions. [ABSTRACT FROM AUTHOR]