Pulmonary ventilation imaging in asthma and cystic fibrosis using oxygen‐enhanced 3D radial ultrashort echo time MRI

Abstract

2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;47:1287-1297.

Deep convolutional neural networks with multiplane consensus labeling for lung function quantification using UTE proton MRI

“…After registration and density correction, the ventilation‐weighted PSE map was computed as PSE = ( S 100% − S 21% )/ S 21% ⋅ 100%, where S 21% and S 100% represent the signal intensity of the normoxic and hyperoxic UTE images, respectively. The low‐intensity regions from the PSE map was considered ventilation defects, which were quantified automatically as VDP by a machine learning‐based approach, adaptive K ‐means, using the binary lung mask segmented using either the reference method, or the DL approach. Lung segmentation and ventilation defect quantification were performed individually by an imaging scientist (W.Z.)…”

“…A previously developed workflow including data preprocessing, deformable registration, and retrospective lung density correction was used to generate percent signal enhancement (PSE) maps from the normoxic and hyperoxic UTE volumes acquired for each subject. 4 The normoxic and hyperoxic UTE volumes were preprocessed automatically with image denoising, intensity correction using bias field inhomogeneity estimation, 32 and intensity normalization to the intensity range [0, 1]. These UTE volumes were then cropped semiautomatically in axial, coronal, and sagittal planes in order to reduce the computational cost in image registration.…”

“…MAGNETIC RESONANCE IMAGING (MRI) of the chest can provide regional assessment of lung ventilation by inhaling oxygen (O 2 ), hyperpolarized noble gases, or fluorinated gas . Oxygen‐enhanced (OE) MRI using a 3D radial ultrashort echo time (UTE) sequence supports quantitative differentiation of diseased vs. healthy lungs using whole lung ventilation defect percent (VDP) . This method does not require specialized multinuclear hardware or expensive specialty gases, while providing full chest images of regional ventilation with isotropic spatial resolution.…”

3D ultrashort echo time MRI of the lung using stack‐of‐spirals and spherical k‐Space coverages: Evaluation in healthy volunteers and parenchymal diseases

“…Lung MRI has recently benefited from the emergence of UTE sequences to reach morphological information close to that of a CT scan. 4,6,14,24 The two main procedures consist of acquiring k-space either radially into a sphere or into a cylinder using stack-of-discs, although several variants exist. 3D-USV using a stack-of-spirals has been recently described and applied in patients with lung cancer.…”

Technical Note: Deep learning based MRAC using rapid ultrashort echo time imaging

“…In medical imaging, deep Convolutional Neural Networks (CNN) have been shown to be especially effective at various tasks such as segmenting cardiac structures, brain structures, brain tumors, and musculoskeletal tissues . Similar to CNNs are Convolutional Encoder–Decoder (CED) networks, which consist of a paired encoder and decoder, which are particularly favorable in multiple tissue segmentation studies due to their high efficiency and applicability . The encoder network performs efficient image data compression while estimating robust and spatial invariant image features.…”