Impact of coronary lumen reconstruction on the estimation of endothelial shear stress: in vivo comparison of three-dimensional quantitative coronary angiography and three-dimensional fusion combining optical coherent tomography

Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography

BACKGROUND

Invasive coronary angiography (ICA) is a primary imaging modality that visualizes the lumen area of coronary arteries for diagnosis and interventional guidance. In the current practice of quantitative coronary analysis (QCA), semi-automatic segmentation tools require labor-intensive and time-consuming manual correction, limiting their application in the catheterization room.

PURPOSE

This study aims to propose rank-based selective ensemble methods that improve the segmentation performance and reduce morphological errors that limit fully automated quantification of coronary artery using deep-learning segmentation of ICA.

METHODS

Two selective ensemble methods proposed in this work integrated the weighted ensemble approach with per-image quality estimation. The segmentation outcomes from five base models with different loss functions were ranked either by mask morphology or estimated dice similarity coefficient (DSC). The final output was determined by imposing different weights according to the ranks. The ranking criteria based on mask morphology were formulated from empirical insight to avoid frequent types of segmentation errors (MSEN), while the estimation of DSCs was performed by comparing the pseudo-ground truth generated from a meta-learner (ESEN). Five-fold cross-validation was performed with the internal dataset of 7426 coronary angiograms from 2924 patients, and prediction model was externally validated with 556 images of 226 patients.

RESULTS

The selective ensemble methods improved the segmentation performance with DSCs up to 93.07% and provided a better delineation of coronary lesion with local DSCs of up to 93.93%, outperforming all individual models. Proposed methods also minimized the chances of mask disconnection in the most narrowed regions to 2.10%. The robustness of the proposed methods was also evident in the external validation. Inference time for major vessel segmentation was approximately one-sixth of a second.

CONCLUSION

Proposed methods successfully reduced morphological errors in the predicted masks and were able to enhance the robustness of the automatic segmentation. The results suggest better applicability of real-time QCA-based diagnostic methods in routine clinical settings.

Computational Fractional Flow Reserve From Coronary Computed Tomography Angiography—Optical Coherence Tomography Fusion Images in Assessing Functionally Significant Coronary Stenosis

Background

Coronary computed tomography angiography (CTA) and optical coherence tomography (OCT) provide additional functional information beyond the anatomy by applying computational fluid dynamics (CFD). This study sought to evaluate a novel approach for estimating computational fractional flow reserve (FFR) from coronary CTA-OCT fusion images.

Methods

Among patients who underwent coronary CTA, 148 patients who underwent both pressure wire-based FFR measurement and OCT during angiography to evaluate intermediate stenosis in the left anterior descending artery were included from the prospective registry. Coronary CTA-OCT fusion images were created, and CFD was applied to estimate computational FFR. Based on pressure wire-based FFR as a reference, the diagnostic performance of Fusion-FFR was compared with that of CT-FFR and OCT-FFR.

Results

Fusion-FFR was strongly correlated with FFR (r = 0.836, P < 0.001). Correlation between FFR and Fusion-FFR was stronger than that between FFR and CT-FFR (r = 0.682, P < 0.001; z statistic, 5.42, P < 0.001) and between FFR and OCT-FFR (r = 0.705, P < 0.001; z statistic, 4.38, P < 0.001). Area under the receiver operating characteristics curve to assess functionally significant stenosis was higher for Fusion-FFR than for CT-FFR (0.90 vs. 0.83, P = 0.024) and OCT-FFR (0.90 vs. 0.83, P = 0.043). Fusion-FFR exhibited 84.5% accuracy, 84.6% sensitivity, 84.3% specificity, 80.9% positive predictive value, and 87.5% negative predictive value. Especially accuracy, specificity, and positive predictive value were superior for Fusion-FFR than for CT-FFR (73.0%, P = 0.007; 61.4%, P < 0.001; 64.0%, P < 0.001) and OCT-FFR (75.7%, P = 0.021; 73.5%, P = 0.020; 69.9%, P = 0.012).

Conclusion

CFD-based computational FFR from coronary CTA-OCT fusion images provided more accurate functional information than coronary CTA or OCT alone.

Clinical Trial Registration

[www.ClinicalTrials.gov], identifier [NCT03298282].

Three-dimensional phase and intensity reconstruction from coherent modulation imaging measurements

Coherent modulation imaging is a lensless imaging technique, where a complex-valued image can be recovered from a single diffraction pattern using the iterative algorithm. Although mostly applied in two dimensions, it can be tomographically combined to produce three-dimensional (3D) images. Here we present a 3D reconstruction procedure for the sample's phase and intensity from coherent modulation imaging measurements. Pre-processing methods to remove illumination probe, inherent ambiguities in phase reconstruction results, and intensity fluctuation are given. With the projections extracted by our method, standard tomographic reconstruction frameworks can be used to recover accurate quantitative 3D phase and intensity images. Numerical simulations and optical experiments validate our method.

Improving Blood Flow Visualization of Recirculation Regions at Carotid Bulb in 4D Flow MRI Using Semi-Automatic Segmentation with ITK-SNAP

Assessment of carotid bulb hemodynamics using four-dimensional (4D) flow magnetic resonance imaging (MRI) requires accurate segmentation of recirculation regions that is frequently hampered by limited resolution. This study aims to improve the accuracy of 4D flow MRI carotid bulb segmentation and subsequent recirculation regions analysis. Time-of-flight (TOF) MRI and 4D flow MRI were performed on bilateral carotid artery bifurcations in seven healthy volunteers. TOF-MRI data was segmented into 3D geometry for computational fluid dynamics (CFD) simulations. ITK-SNAP segmentation software was included in the workflow for the semi-automatic generation of 4D flow MRI angiographic data. This study compared the velocities calculated at the carotid bifurcations and the 3D blood flow visualization at the carotid bulbs obtained by 4D flow MRI and CFD. By applying ITK-SNAP segmentation software, an obvious improvement in the 4D flow MRI visualization of the recirculation regions was observed. The 4D flow MRI images of the recirculation flow characteristics of the carotid artery bulbs coincided with the CFD. A reasonable agreement was found in terms of velocity calculated at the carotid bifurcation between CFD and 4D flow MRI. However, the dispersion of velocity data points relative to the local errors of measurement in 4D flow MRI remains. Our proposed strategy showed the feasibility of improving recirculation regions segmentation and the potential for reliable blood flow visualization in 4D flow MRI. However, quantitative analysis of recirculation regions in 4D flow MRI with ITK-SNAP should be enhanced for use in clinical situations.

3D single-shot ptychography with highly tilted illuminations

A method based on highly tilted illumination and non-paraxial iterative computation is proposed to improve the image quality of single-shot 3D ptychography. A thick sample is illuminated with a cluster of laser beams that are separated by large enough angles to record each diffraction pattern distinctly in a single exposure. 3D structure of the thick sample is accurately reconstructed from recorded diffraction patterns using a modified multi-slice algorithm to process non-paraxial illumination. Sufficient number of recorded diffraction patterns with noticeably low crosstalk enhances the fidelity of reconstruction significantly over single-shot 3D ptychography methods that are based on paraxial illumination. Experimental observations guided by the results of numerical simulations show the feasibility of the proposed method.

Investigation of Wall Shear Stress in Cardiovascular Research and in Clinical Practice-From Bench to Bedside

In the 1900s, researchers established animal models experimentally to induce atherosclerosis by feeding them with a cholesterol-rich diet. It is now accepted that high circulating cholesterol is one of the main causes of atherosclerosis; however, plaque localization cannot be explained solely by hyperlipidemia. A tremendous amount of studies has demonstrated that hemodynamic forces modify endothelial athero-susceptibility phenotypes. Endothelial cells possess mechanosensors on the apical surface to detect a blood stream-induced force on the vessel wall, known as "wall shear stress (WSS)", and induce cellular and molecular responses. Investigations to elucidate the mechanisms of this process are on-going: on the one hand, hemodynamics in complex vessel systems have been described in detail, owing to the recent progress in imaging and computational techniques. On the other hand, investigations using unique in vitro chamber systems with various flow applications have enhanced the understanding of WSS-induced changes in endothelial cell function and the involvement of the glycocalyx, the apical surface layer of endothelial cells, in this process. In the clinical setting, attempts have been made to measure WSS and/or glycocalyx degradation non-invasively, for the purpose of their diagnostic utilization. An increasing body of evidence shows that WSS, as well as serum glycocalyx components, can serve as a predicting factor for atherosclerosis development and, most importantly, for the rupture of plaques in patients with high risk of coronary heart disease.

3D reconstruction of coronary artery bifurcations from coronary angiography and optical coherence tomography: feasibility, validation, and reproducibility

The three-dimensional (3D) representation of the bifurcation anatomy and disease burden is essential for better understanding of the anatomical complexity of bifurcation disease and planning of stenting strategies. We propose a novel methodology for 3D reconstruction of coronary artery bifurcations based on the integration of angiography, which provides the backbone of the bifurcation, with optical coherence tomography (OCT), which provides the vessel shape. Our methodology introduces several technical novelties to tackle the OCT frame misalignment, correct positioning of the OCT frames at the carina, lumen surface reconstruction, and merging of bifurcation lumens. The accuracy and reproducibility of the methodology were tested in n = 5 patient-specific silicone bifurcations compared to contrast-enhanced micro-computed tomography (µCT), which was used as reference. The feasibility and time-efficiency of the method were explored in n = 7 diseased patient bifurcations of varying anatomical complexity. The OCT-based reconstructed bifurcation models were found to have remarkably high agreement compared to the µCT reference models, yielding r² values between 0.91 and 0.98 for the normalized lumen areas, and mean differences of 0.005 for lumen shape and 0.004 degrees for bifurcation angles. Likewise, the reproducibility of our methodology was remarkably high. Our methodology successfully reconstructed all the patient bifurcations yielding favorable processing times (average lumen reconstruction time < 60 min). Overall, our method is an easily applicable, time-efficient, and user-friendly tool that allows accurate and reproducible 3D reconstruction of coronary bifurcations. Our technique can be used in the clinical setting to provide information about the bifurcation anatomy and plaque burden, thereby enabling planning, education, and decision making on bifurcation stenting.

Deep learning segmentation of major vessels in X-ray coronary angiography

X-ray coronary angiography is a primary imaging technique for diagnosing coronary diseases. Although quantitative coronary angiography (QCA) provides morphological information of coronary arteries with objective quantitative measures, considerable training is required to identify the target vessels and understand the tree structure of coronary arteries. Despite the use of computer-aided tools, such as the edge-detection method, manual correction is necessary for accurate segmentation of coronary vessels. In the present study, we proposed a robust method for major vessel segmentation using deep learning models with fully convolutional networks. When angiographic images of 3302 diseased major vessels from 2042 patients were tested, deep learning networks accurately identified and segmented the major vessels in X-ray coronary angiography. The average F1 score reached 0.917, and 93.7% of the images exhibited a high F1 score > 0.8. The most narrowed region at the stenosis was distinctly captured with high connectivity. Robust predictability was validated for the external dataset with different image characteristics. For major vessel segmentation, our approach demonstrated that prediction could be completed in real time with minimal image preprocessing. By applying deep learning segmentation, QCA analysis could be further automated, thereby facilitating the use of QCA-based diagnostic methods.