Deep Learning Synthetic Strain: Quantitative Assessment of Regional Myocardial Wall Motion at MRI.

Purpose: To assess the feasibility of a newly developed algorithm, called deep learning synthetic strain (DLSS), to infer myocardial velocity from cine steady-state free precession (SSFP) images and detect wall motion abnormalities in patients with ischemic heart disease. Materials and Methods: In this retrospective study, DLSS was developed by using a data set of 223 cardiac MRI examinations including cine SSFP images and four-dimensional flow velocity data (November 2017 to May 2021). To establish normal ranges, segmental strain was measured in 40 individuals (mean age, 41 years ± 17 [SD]; 30 men) without cardiac disease. Then, DLSS performance in the detection of wall motion abnormalities was assessed in a separate group of patients with coronary artery disease, and these findings were compared with consensus results of four independent cardiothoracic radiologists (ground truth). Algorithm performance was evaluated by using receiver operating characteristic curve analysis. Results: Median peak segmental radial strain in individuals with normal cardiac MRI findings was 38% (IQR: 30%-48%). Among patients with ischemic heart disease (846 segments in 53 patients; mean age, 61 years ± 12; 41 men), the Cohen κ among four cardiothoracic readers for detecting wall motion abnormalities was 0.60-0.78. DLSS achieved an area under the receiver operating characteristic curve of 0.90. Using a fixed 30% threshold for abnormal peak radial strain, the algorithm achieved a sensitivity, specificity, and accuracy of 86%, 85%, and 86%, respectively. Conclusion: The deep learning algorithm had comparable performance with subspecialty radiologists in inferring myocardial velocity from cine SSFP images and identifying myocardial wall motion abnormalities at rest in patients with ischemic heart disease.Keywords: Neural Networks, Cardiac, MR Imaging, Ischemia/Infarction Supplemental material is available for this article. © RSNA, 2023.

Heterogeneous expression of alternatively spliced lncRNA mediates vascular smooth cell plasticity.

9p21.3 locus polymorphisms have the strongest correlation with coronary artery disease, but as a noncoding locus, disease connection is enigmatic. The lncRNA ANRIL found in 9p21.3 may regulate vascular smooth muscle cell (VSMC) phenotype to contribute to disease risk. We observed significant heterogeneity in induced pluripotent stem cell-derived VSMCs from patients homozygous for risk versus isogenic knockout or nonrisk haplotypes. Subpopulations of risk haplotype cells exhibited variable morphology, proliferation, contraction, and adhesion. When sorted by adhesion, risk VSMCs parsed into synthetic and contractile subpopulations, i.e., weakly adherent and strongly adherent, respectively. Of note, >90% of differentially expressed genes coregulated by haplotype and adhesion and were associated with Rho GTPases, i.e., contractility. Weakly adherent subpopulations expressed more short isoforms of ANRIL, and when overexpressed in knockout cells, ANRIL suppressed adhesion, contractility, and αSMA expression. These data suggest that variable lncRNA penetrance may drive mixed functional outcomes that confound pathology.

Deep Learning Automated Background Phase Error Correction for Abdominopelvic 4D Flow MRI.

Background Four-dimensional (4D) flow MRI has the potential to provide hemodynamic insights for a variety of abdominopelvic vascular diseases, but its clinical utility is currently impaired by background phase error, which can be challenging to correct. Purpose To assess the feasibility of using deep learning to automatically perform image-based background phase error correction in 4D flow MRI and to compare its effectiveness relative to manual image-based correction. Materials and Methods A convenience sample of 139 abdominopelvic 4D flow MRI acquisitions performed between January 2016 and July 2020 was retrospectively collected. Manual phase error correction was performed using dedicated imaging software and served as the reference standard. After reserving 40 examinations for testing, the remaining examinations were randomly divided into training (86% [85 of 99]) and validation (14% [14 of 99]) data sets to train a multichannel three-dimensional U-Net convolutional neural network. Flow measurements were obtained for the infrarenal aorta, common iliac arteries, common iliac veins, and inferior vena cava. Statistical analyses included Pearson correlation, Bland-Altman analysis, and F tests with Bonferroni correction. Results A total of 139 patients (mean age, 47 years ± 14 [standard deviation]; 108 women) were included. Inflow-outflow correlation improved after manual correction (ρ = 0.94, P < .001) compared with that before correction (ρ = 0.50, P < .001). Automated correction showed similar results (ρ = 0.91, P < .001) and demonstrated very strong correlation with manual correction (ρ = 0.98, P < .001). Both correction methods reduced inflow-outflow variance, improving mean difference from -0.14 L/min (95% limits of agreement: -1.61, 1.32) (uncorrected) to 0.05 L/min (95% limits of agreement: -0.32, 0.42) (manually corrected) and 0.05 L/min (95% limits of agreement: -0.38, 0.49) (automatically corrected). There was no significant difference in inflow-outflow variance between manual and automated correction methods (P = .10). Conclusion Deep learning automated phase error correction reduced inflow-outflow bias and variance of volumetric flow measurements in four-dimensional flow MRI, achieving results comparable with manual image-based phase error correction. © RSNA, 2021 See also the editorial by Roldán-Alzate and Grist in this issue.

Radiologist-supervised Transfer Learning: Improving Radiographic Localization of Pneumonia and Prognostication of Patients With COVID-19.

PURPOSE: To assess the potential of a transfer learning strategy leveraging radiologist supervision to enhance convolutional neural network-based (CNN) localization of pneumonia on radiographs and to further assess the prognostic value of CNN severity quantification on patients evaluated for COVID-19 pneumonia, for whom severity on the presenting radiograph is a known predictor of mortality and intubation. MATERIALS AND METHODS: We obtained an initial CNN previously trained to localize pneumonia along with 25,684 radiographs used for its training. We additionally curated 1466 radiographs from patients who had a computed tomography (CT) performed on the same day. Regional likelihoods of pneumonia were then annotated by cardiothoracic radiologists, referencing these CTs. Combining data, a preexisting CNN was fine-tuned using transfer learning. Whole-image and regional performance of the updated CNN was assessed using receiver-operating characteristic area under the curve and Dice. Finally, the value of CNN measurements was assessed with survival analysis on 203 patients with COVID-19 and compared against modified radiographic assessment of lung edema (mRALE) score. RESULTS: Pneumonia detection area under the curve improved on both internal (0.756 to 0.841) and external (0.864 to 0.876) validation data. Dice overlap also improved, particularly in the lung bases (R: 0.121 to 0.433, L: 0.111 to 0.486). There was strong correlation between radiologist mRALE score and CNN fractional area of involvement (ρ=0.85). Survival analysis showed similar, strong prognostic ability of the CNN and mRALE for mortality, likelihood of intubation, and duration of hospitalization among patients with COVID-19. CONCLUSIONS: Radiologist-supervised transfer learning can enhance the ability of CNNs to localize and quantify the severity of disease. Closed-loop systems incorporating radiologists may be beneficial for continued improvement of artificial intelligence algorithms.

High shear stress enhances endothelial permeability in the presence of the risk haplotype at 9p21.3.

Single nucleotide polymorphisms (SNPs) are exceedingly common in non-coding loci, and while they are significantly associated with a myriad of diseases, their specific impact on cellular dysfunction remains unclear. Here, we show that when exposed to external stressors, the presence of risk SNPs in the 9p21.3 coronary artery disease (CAD) risk locus increases endothelial monolayer and microvessel dysfunction. Endothelial cells (ECs) derived from induced pluripotent stem cells of patients carrying the risk haplotype (R/R WT) differentiated similarly to their non-risk and isogenic knockout (R/R KO) counterparts. Monolayers exhibited greater permeability and reactive oxygen species signaling when the risk haplotype was present. Addition of the inflammatory cytokine TNFα further enhanced EC monolayer permeability but independent of risk haplotype; TNFα also did not substantially alter haplotype transcriptomes. Conversely, when wall shear stress was applied to ECs in a microfluidic vessel, R/R WT vessels were more permeable at lower shear stresses than R/R KO vessels. Transcriptomes of sheared cells clustered more by risk haplotype than by patient or clone, resulting in significant differential regulation of EC adhesion and extracellular matrix genes vs static conditions. A subset of previously identified CAD risk genes invert expression patterns in the presence of high shear concomitant with altered cell adhesion genes, vessel permeability, and endothelial erosion in the presence of the risk haplotype, suggesting that shear stress could be a regulator of non-coding loci with a key impact on CAD.

Clinical Performance and Role of Expert Supervision of Deep Learning for Cardiac Ventricular Volumetry: A Validation Study.

PURPOSE: To evaluate the performance of a deep learning (DL) algorithm for clinical measurement of right and left ventricular volume and function across cardiac MR images obtained for a range of clinical indications and pathologies. MATERIALS AND METHODS: A retrospective, Health Insurance Portability and Accountability Act-compliant study was conducted using the first 200 noncongenital clinical cardiac MRI examinations from June 2015 to June 2017 for which volumetry was available. Images were analyzed using commercially available software for automated DL-based and manual contouring of biventricular volumes. Fully automated measurements were compared using Pearson correlations, relative volume errors, and Bland-Altman analyses. Manual, automated, and expert revised contours for 50 MR images were examined by comparing regional Dice coefficients at the base, midventricle, and apex to further analyze the contour quality. RESULTS: Fully automated and manual left ventricular volumes were strongly correlated for end-systolic volume (ESV: Pearson r = 0.99, P < .001), end-diastolic volume (EDV: r = 0.97, P < .001), and ejection fraction (EF: r = 0.94, P < .001). Right ventricular measurements were also correlated for ESV (r = 0.93, P < .001), EDV (r = 0.92, P < .001), and EF (r = 0.73, P < .001). Visual inspection of segmentation quality showed most errors (73%) occurred at the cardiac base. Mean Dice coefficients between manual, automated, and expert revised contours ranged from 0.92 to 0.95, with greatest variance at the base and apex. CONCLUSION: Fully automated ventricular segmentation by the tested algorithm provides contours and ventricular volumes that could be used to aid expert segmentation, but can benefit from expert supervision, particularly to resolve errors at the basal and apical slices. Supplemental material is available for this article. © RSNA, 2020.

Deep Learning Single-Frame and Multiframe Super-Resolution for Cardiac MRI.

Background Cardiac MRI is limited by long acquisition times, yet faster acquisition of smaller-matrix images reduces spatial detail. Deep learning (DL) might enable both faster acquisition and higher spatial detail via super-resolution. Purpose To explore the feasibility of using DL to enhance spatial detail from small-matrix MRI acquisitions and evaluate its performance against that of conventional image upscaling methods. Materials and Methods Short-axis cine cardiac MRI examinations performed between January 2012 and December 2018 at one institution were retrospectively collected for algorithm development and testing. Convolutional neural networks (CNNs), a form of DL, were trained to perform super resolution in image space by using synthetically generated low-resolution data. There were 70%, 20%, and 10% of examinations allocated to training, validation, and test sets, respectively. CNNs were compared against bicubic interpolation and Fourier-based zero padding by calculating the structural similarity index (SSIM) between high-resolution ground truth and each upscaling method. Means and standard deviations of the SSIM were reported, and statistical significance was determined by using the Wilcoxon signed-rank test. For evaluation of clinical performance, left ventricular volumes were measured, and statistical significance was determined by using the paired Student t test. Results For CNN training and retrospective analysis, 400 MRI scans from 367 patients (mean age, 48 years ± 18; 214 men) were included. All CNNs outperformed zero padding and bicubic interpolation at upsampling factors from two to 64 (P < .001). CNNs outperformed zero padding on more than 99.2% of slices (9828 of 9907). In addition, 10 patients (mean age, 51 years ± 22; seven men) were prospectively recruited for super-resolution MRI. Super-resolved low-resolution images yielded left ventricular volumes comparable to those from full-resolution images (P > .05), and super-resolved full-resolution images appeared to further enhance anatomic detail. Conclusion Deep learning outperformed conventional upscaling methods and recovered high-frequency spatial information. Although training was performed only on short-axis cardiac MRI examinations, the proposed strategy appeared to improve quality in other imaging planes. © RSNA, 2020 Online supplemental material is available for this article.

Hemodynamic-mediated endocardial signaling controls in vivo myocardial reprogramming.

Lower vertebrate and neonatal mammalian hearts exhibit the remarkable capacity to regenerate through the reprogramming of pre-existing cardiomyocytes. However, how cardiac injury initiates signaling pathways controlling this regenerative reprogramming remains to be defined. Here, we utilize in vivo biophysical and genetic fate mapping zebrafish studies to reveal that altered hemodynamic forces due to cardiac injury activate a sequential endocardial-myocardial signaling cascade to direct cardiomyocyte reprogramming and heart regeneration. Specifically, these altered forces are sensed by the endocardium through the mechanosensitive channel Trpv4 to control Klf2a transcription factor expression. Consequently, Klf2a then activates endocardial Notch signaling which results in the non-cell autonomous initiation of myocardial Erbb2 and BMP signaling to promote cardiomyocyte reprogramming and heart regeneration. Overall, these findings not only reveal how the heart senses and adaptively responds to environmental changes due to cardiac injury, but also provide insight into how flow-mediated mechanisms may regulate cardiomyocyte reprogramming and heart regeneration.

Volumetric segmentation-free method for rapid visualization of vascular wall shear stress using 4D flow MRI.

PURPOSE: To develop a rapid segmentation-free method to visualize and compute wall shear stress (WSS) throughout the aorta using 4D Flow MRI data. WSS is the drag force-per-area the vessel endothelium exerts on luminal blood; abnormal levels of WSS are associated with cardiovascular pathologies. Previous methods for computing WSS are bottlenecked by labor-intensive manual segmentation of vessel boundaries. A rapid automated segmentation-free method for computing WSS is presented. THEORY AND METHODS: Shear stress is the dot-product of the viscous stress tensor and the inward normal vector. The inward normal vectors are approximated as the gradient of fluid speed at every voxel. Subsequently, a 4D map of shear stress is computed as the partial derivatives of velocity with respect to the inward normal vectors. We highlight the shear stress near the wall by fusing visualization with edge-emphasized anatomical data. RESULTS: As a proof-of-concept, four cases with aortic pathologies are presented. Visualization allows for rapid localization of pathologic WSS. Subsequent analysis of these pathological regions enables quantification of WSS. Average WSS during peak systole measures approximately 50-60 cPa in nonpathological regions of the aorta and is elevated in regions of stenosis, coarctation, and dissection. WSS is reduced in regions of aneurysm. CONCLUSION: A volumetric technique for calculation and visualization of WSS from 4D Flow MRI data is presented. Traditional labor-intensive methods for WSS rely on explicit manual segmentation of vessel boundaries before visualization. This automated volumetric strategy for visualization and quantification of WSS may facilitate its clinical translation.

Increasing Thermal Stability of Gelatin by UV-Induced Cross-Linking with Glucose.

The effects of ultraviolet (254 nm) radiation on a hydrated gelatin-glucose matrix were investigated for the development of a physiologically thermostable substrate for potential use in cell scaffold production. Experiments conducted with a differential scanning calorimeter indicate that ultraviolet irradiation of gelatin-glucose hydrogels dramatically increases thermal stability such that no melting is observed at temperatures of at least 90°C. The addition of glucose significantly increases the yield of cross-linked product, suggesting that glucose has a role in cross-link formation. Comparisons of lyophilized samples using scanning electron microscopy show that irradiated materials have visibly different densities.

The analysis of macroalgae biomass found around Hawaii for bioethanol production.

Macroalgae commonly found in the ocean around Hawaii were collected from near shore locations and their potential as biomass feedstock for fermentative ethanol was investigated. A green alga, Ulva reticulata, was selected for further analysis. This species forms large complex structures that grow quickly and has high dry biomass percentage (20%), soluble carbohydrates (18%); and high total carbohydrates along with low quantities of lignin (13%). During acid saccharification, it was determined that 49% of the total mass was observed as sugars in the hydrolysate; however, fermentation was problematic. Enzymatic saccharification using cellulase from Trichoderma reesei was attempted which recovered a measured maximum of 20% glucose based on the initial dry mass. Fermentation successfully converted all the glucose to ethanol. The measured ethanol yield corresponded to approximately 90 L per tonne of dried macroalgae.