Search

Vessel border detection in IVUS images is essential for coronary disease diagnosis. It helps to obtain the clinical indices on the inner vessel morphology to indicate the stenosis. However, the existing methods suffer the challenge of scale-dependent interference. Early methods usually rely on the hand-crafted features, thus not robust to this interference. The existing deep learning methods are also ineffective to solve this challenge, because these methods aggregate multi-scale features in the top-down way. This aggregation may bring in interference from the non-adjacent scale. Besides, they only combine the features in all scales, and thus may weaken their complementary information. We propose the scale mutualized perception to solve this challenge by considering the adjacent scales mutually to preserve their complementary information. First, the adjacent small scales contain certain semantics to locate different vessel tissues. Then, they can also perceive the global context to assist the representation of the local context in the adjacent large scale, and vice versa. It helps to distinguish the objects with similar local features. Second, the adjacent large scales provide detailed information to refine the vessel boundaries. The experiments show the effectiveness of our method in 153 IVUS sequences, and its superiority to ten state-of-the-art methods.

Deep learning (DL) has been applied for automatic left ventricle (LV) ejection fraction (EF) measurement, but the diagnostic performance was rarely evaluated for various phenotypes of heart disease. This study aims to evaluate a new DL algorithm for automated LVEF measurement using two-dimensional echocardiography (2DE) images collected from three centers. The impact of three ultrasound machines and three phenotypes of heart diseases on the automatic LVEF measurement was evaluated. Using 36890 frames of 2DE from 340 patients, we developed a DL algorithm based on U-Net (DPS-Net) and the biplane Simpson's method was applied for LVEF calculation. Results showed a high performance in LV segmentation and LVEF measurement across phenotypes and echo systems by using DPS-Net. Good performance was obtained for LV segmentation when DPS-Net was tested on the CAMUS data set (Dice coefficient of 0.932 and 0.928 for ED and ES). Better performance of LV segmentation in study-wise evaluation was observed by comparing the DPS-Net v2 to the EchoNet-dynamic algorithm (

We aimed to compare the performance of FFRCT and FFRQCA in assessing the functional significance of coronary artery stenosis in patients suffering from coronary artery disease with stable angina. A total of 101 stable coronary heart disease (CAD) patients with 181 lesions were recruited. FFRCT and FFRQCA were compared using invasive fractional flow reserve (FFR) as a reference standard. Comparisons between FFRCT and FFRQCA were conducted based on strategies of the geometric reconstruction, boundary conditions, and geometric characteristics. The performance of FFRCT and FFRQCA in detecting hemodynamic significance was also investigated. The performance of FFRCT and FFRQCA in discriminating hemodynamically significant lesions was compared. Good correlation and agreement with invasive FFR was found using FFRCT and FFRQCA (r = 0.809, p

Intracoronary imaging is a crucial imaging technology in coronary disease diagnosis as it visualizes the internal tissue morphologies of coronary arteries. Vessel border detection in intracoronary images (VBDI) is desired because it can help the succeeding procedures of computer-aided disease diagnosis. However, existing VDBI methods suffer from the challenge of vessel-environment variability (i.e. high intra- and inter-subject diversity of vessels and their surrounding tissues appeared in images). This challenge leads to the ineffectiveness in the vessel region representation for hand-crafted features, in the receptive field extraction for deeply-represented features, as well as performance suppression derived from clinical data limitation. To solve this challenge, we propose a novel privileged modality distillation (PMD) framework for VBDI. PMD transforms the single-input-single-task (SIST) learning problem in the single-mode VBDI to a multiple-input-multiple-task (MIMT) problem by using the privileged image modality to help the learning model in the target modality. This learns the enriched high-level knowledge with similar semantics and generalizes PMD on diversity-increased low-level image features for improving the model adaptation to diverse vessel environments. Moreover, PMD refines MIMT to SIST by distilling the learned knowledge from multiple to one modality. This eliminates the reliance on privileged modality in the test phase, and thus enables the applicability to each of different intracoronary modalities. A structure-deformable neural network is proposed as an elaborately-designed implementation of PMD. It expands a conventional SIST network structure to the MIMT structure, and then recovers it to the final SIST structure. The PMD is validated on intravascular ultrasound imaging and optical coherence tomography imaging. One modality is the target, and the other one can be considered as the privileged modality owing to their semantic relatedness. The experiments show that our PMD is effective in VBDI (e.g. the Dice index is larger than 0.95), as well as superior to six state-of-the-art VBDI methods.

Summary In this study, we proposed an automatic approach to segment the three‐dimensional coronary tree from computed tomography angiography (CTA) image data. Compared to the previous studies, our ...

Abnormal autonomic nervous regulation has an important role in the development of hypertension. As to whether blood pressure (BP) or BP variability represents the proper characteristics for predisposition to hypertension in Chinese young adults remains controversial. We studied the properties of the indices extracted from beat-to-beat BP during a 13 min cold pressor test (CPT). In this study, 69 Chinese young adults including 34 offspring of hypertensive parents (OHPs; 25.6±2.5 years) and 35 offspring of normotensive parents (ONPs; 25.3±2.3 years) were analyzed. We assessed the differences between the two groups regarding mean beat-to-beat BP and variability indices. Beat-to-beat BP variability indices included time-domain indices and frequency-domain indices. Our results showed that the differences in beat-to-beat systolic BP and mean BP levels between the OHPs and the ONPs were statistically significant (P

Impaired bioavailability of endothelium-derived nitric oxide (NO) and endothelial dysfunction may play a pivotal role in the pathogenesis of in-stent restenosis (ISR) after coronary stenting. We aimed to investigate the relation between asymmetric dimethylarginine (ADMA), an endogenous NO synthase inhibitor, and the ISR lesions tissue characteristics assessed by optical coherence tomography (OCT).Forty-five patients with symptomatic ISR lesions (17 bare metal stents, 28 drug-eluting stents, medium implantation duration: 58.0 months) were evaluated by OCT for in-stent tissue characteristics and calcification. We defined neoatherosclerosis as the presence of lipid or calcified neointima in ISR lesions, and 12 (26.7%), 33 (73.3%) ISR lesions were classified as with homogenous neointima and neoatherosclerosis respectively. The patients with neoatherosclerosis have significantly higher plasma ADMA levels compared to those of patients with homogenous neointima (1.12 ± 0.21 μmol/l versus 0.83 ± 0.08 μmol/l, p 0.001). Furthermore, the plasma ADMA level of ISR lesions with intra-stent calcification (n = 24, 53.3%) was also significantly higher than those of ISR lesions without (n = 21, 46.7%; p 0.001). There was a highly significant association between plasma ADMA level and intra-stent relative calcium index (mean calcium arc × calcium length)/(360 × analyzed length) (p 0.001, r = 0.702). In multivariate analyses adjusted for age, sex, diabetes, eGFR, plasma ADMA level remained the only significant predictor for the presence of neoatherosclerosis (p = 0.008) and intra-stent calcification (p 0.001). In contrast, plasma ADMA level correlated with intra-stent relative lipid core index (mean lipid core arc × lipid core length)/(360 × analyzed length) only in subgroup without intra-stent calcification (p = 0.004, r = 0.596, multivariate-adjusted p = 0.022).Increased plasma ADMA levels were associated with the development of in-stent neoatherosclerosis and calcification.

Major limitations for conventional FFR measurement using a pressure wire (PW) include the suboptimal handling characteristics and needs for occasional disconnecting and reconnecting of the PW. To address these limitations, a piezoresistive-sensor equipped pressure microcatheter (PMC), with a profile

Primary percutaneous coronary intervention (PPCI) is always targeted on the angiographically identified culprit lesion. However, the actual culprit lesion may not compromise the lumen and can be located proximally or distally to the angiographic target lesion. As a result, the risk of incomplete lesion coverage can be high when the PPCI is guided solely by angiography. Furthermore, stent implantation must be optimized, as incomplete apposition and/or edge dissection may result in in-stent restenosis or acute thrombotic events. Thus, invasive coronary imaging using intravascular ultrasound or optical coherence tomography can be useful to guide the PPCI procedure by locating the true culprit lesion and may lead to better stent coverage of the lesion. Besides, invasive imaging also helps to resolve diagnostic uncertainty and to identify the mechanisms underlying acute events.

An automated framework for detecting lumen and media-adventitia borders in intravascular ultrasound images was developed on the basis of an adaptive region-growing method and an unsupervised clustering method. To demonstrate the capability of the framework, linear regression, Bland-Altman analysis and distance analysis were used to quantitatively investigate the correlation, agreement and spatial distance, respectively, between our detected borders and manually traced borders in 337 intravascular ultrasound images in vivo acquired from six patients. The results of these investigations revealed good correlation (r = 0.99), good agreement (>96.82% of results within the 95% confidence interval) and small average distance errors (lumen border: 0.08 mm, media-adventitia border: 0.10 mm) between the borders generated by the automated framework and the manual tracing method. The proposed framework was found to be effective in detecting lumen and media-adventitia borders in intravascular ultrasound images, indicating its potential for use in routine studies of vascular disease.

This paper describes an artificial neural network (ANN) method that employs a feature-learning algorithm to detect the lumen and MA borders in intravascular ultrasound (IVUS) images. Three types of imaging features including spatial, neighboring, and gradient features were used as the input features to the neural network, and then the different vascular layers were distinguished using two sparse autoencoders and one softmax classifier. To smooth the lumen and MA borders detected by the ANN method, we used the active contour model. The performance of our approach was compared with the manual drawing method and another existing method on 538 IVUS images from six subjects. Results showed that our approach had a high correlation (r = 0.9284 ∼ 0.9875 for all measurements) and good agreement (bias = 0.0148 ∼ 0.4209 mm) with the manual drawing method, and small detection error (lumen border: 0.0928±0.0935 mm, MA border: 0.1056±0.1088 mm). The average time to process each image was 14±4.6 seconds. The obtained results indicate that our proposed approach can be used to efficiently and accurately detect the lumen and MA borders in IVUS images.

Intravascular ultrasound (IVUS) has been well recognized as one powerful imaging technique to evaluate the stenosis inside the coronary arteries. The detection of lumen border and media-adventitia (MA) border in IVUS images is the key procedure to determine the plaque burden inside the coronary arteries, but this detection could be burdensome to the doctor because of large volume of the IVUS images. In this paper, we use the artificial neural network (ANN) method as the feature learning algorithm for the detection of the lumen and MA borders in IVUS images. Two types of imaging information including spatial, neighboring features were used as the input data to the ANN method, and then the different vascular layers were distinguished accordingly through two sparse auto-encoders and one softmax classifier. Another ANN was used to optimize the result of the first network. In the end, the active contour model was applied to smooth the lumen and MA borders detected by the ANN method. The performance of our approach was compared with the manual drawing method performed by two IVUS experts on 461 IVUS images from four subjects. Results showed that our approach had a high correlation and good agreement with the manual drawing results. The detection error of the ANN method close to the error between two groups of manual drawing result. All these results indicated that our proposed approach could efficiently and accurately handle the detection of lumen and MA borders in the IVUS images.

A novel tri-band optical coherence tomography (OCT) system based on fiber optical parametric amplifier (FOPA) has been proposed and subsequently demonstrated for endoscopic functional spectroscopic imaging of aorta and lipid plaques in mouse models.

The Combo drug-eluting stent (OrbusNeich Medical, Inc, Fort Lauderdale, FL) has an abluminal sirolimus-eluting bioabsorbable polymer and a luminal CD34+ antibody designed to capture endothelial progenitor cells to promote early re-endothelialization. This is the first prospective study to evaluate

Data of virtual histology (VH) acquired by intravascular ultrasound (IVUS) on saphenous vein graft (SVG) lesions is lacking. This study sought to report the VH IVUS findings in degenerative aortocoronary SVG lesions and correlate various types of plaque compositions (fibrous, fibro-fatty, dense calcium, and necrotic core) with different clinical and lesion characteristics. Virtual histology IVUS was performed on SVG in 38 symptomatic patients with a history of coronary artery bypass grafting, who underwent percutaneous coronary intervention on either native vessels or SVG. Measurements were made at the image slice with the smallest lumen. A total of 54 SVG lesions were analyzed; the mean graft age was 13.7 +/- 4.0 years. The mean vessel size was 5.0 +/- 1.0 mm; plaque area was 13.4 +/- 7.3 mm(2), and plaque burden was 63.0% +/- 15.0%. Fibrous tissue represented the major plaque component (62.1% +/- 17.1%). Lesions with a plaque burden ofor=70% were associated with positive remodeling, larger vessel size, higher percentage of fibro-fatty tissue, but lower percentage of dense calcium. Plaque burden was found to be positively correlated with remodeling index (r = 0.37, P = 0.01) and % fibro-fatty tissue (r = 0.49, P0.001) but negatively correlated with % dense calcium (r= -0.31, P = 0.03). The severity of SVG atherosclerosis paralleled with a proportional increase in fibro-fatty tissue. Unstable plaques in SVG were associated with positive remodeling, lipid-rich atheroma, and less calcium deposition, similar to the VH IVUS findings in native coronary arteries.

The hemodynamic alteration in the cerebral circulation caused by the geometric variations in the cerebral circulation arterial network of the circle of Wills (CoW) can lead to fatal ischemic attacks in the brain. The geometric variations due to impairment in the arterial network result in incomplete cerebral arterial structure of CoW and inadequate blood supply to the brain. Therefore, it is of great importance to understand the hemodynamics of the CoW, for efficiently and precisely evaluating the status of blood supply to the brain. In this paper, three-dimensional computational fluid dynamics of the main CoW vasculature coupled with zero-dimensional lumped parameter model boundary condition for the CoW outflow boundaries is developed for analysis of the blood flow distribution in the incomplete CoW cerebral arterial structures. The geometric models in our study cover the arterial segments from the aorta to the cerebral arteries, which can allow us to take into account the innate patient-specific resistance of the arterial trees. Numerical simulations of the governing fluid mechanics are performed to determine the CoW arterial structural hemodynamics, for illustrating the redistribution of the blood flow in CoW due to the structural variations. We have evaluated our coupling methodology in five patient-specific cases that were diagnosed with the absence of efferent vessels or impairment in the connective arteries in their CoWs. The velocity profiles calculated by our approach in the segments of the patient-specific arterial structures are found to be very close to the Doppler ultrasound measurements. The accuracy and consistency of our hemodynamic results have been improved (to [Formula: see text] %) compared to that of the pure-resistance boundary conditions (of 43.5 [Formula: see text] 28 %). Based on our grouping of the five cases according to the occurrence of unilateral occlusion in vertebral arteries, the inter-comparison has shown that (i) the flow reduction in posterior cerebral arteries is the consequence of the unilateral vertebral arterial occlusion, and (ii) the flow rate in the anterior cerebral arteries is correlated with the posterior structural variations. This study shows that our coupling approach is capable of providing comprehensive information of the hemodynamic alterations in the pathological CoW arterial structures. The information generated by our methodology can enable evaluation of both the functional and structural status of the clinically significant symptoms, for assisting the treatment decision-making.

Intravascular spectroscopic photoacoustic technology can image atherosclerotic plaque composition with high sensitivity and specificity, which is critical for identifying vulnerable plaques. Here, we designed and engineered a catheter of 0.9 mm in diameter for intravascular photoacoustic (IVPA) imaging, smaller than the critical size of 1 mm required for clinical translation. Further, a quasifocusing photoacoustic excitation scheme was developed for the catheter, producing well-detectable IVPA signals from stents and lipids with a laser energy as low as ~30 μJ/pulse. As a result, this design enabled the use of a low-energy, high-repetition rate, ns-pulsed optical parametric oscillator laser for high-speed spectroscopic IVPA imaging at both the 1.2-μm and 1.7-μm spectral bands for lipid detection. Specifically, for each wavelength, a 1-kHz IVPA A-line rate was achieved, ~100-fold faster than previously reported IVPA systems offering a similar wavelength tuning range. Using the system, spectroscopic IVPA imaging of peri-adventitial adipose tissue from a porcine aorta segment was demonstrated. The significantly improved imaging speed, together with the reduced catheter size and multiwavelength spectroscopic imaging ability, suggests that the developed high-speed IVPA technology is of great potential to be further translated for in vivo applications.

Ultrafast endoscopic optical coherence tomography is demonstrated based on inertia-free time-stretch mechanism. Images of finger skin and intravascular stent are obtained with a line-scan rate of ~11.5 MHz to showcase its capability in endoscopic bioimaging.

Fractional flow reserve (FFR) is a well-validated index for assessing the physiologic significance of a coronary stenosis in most clinical conditions encountered in today's catheterisation laboratory. The aim of this paper is to provide a short overview of the theoretical background of the coronary pressure-derived FFR index and its clinical applicability in guiding complex coronary intervention procedures.

Intravascular ultrasound (IVUS) plays a vital role in assessing the severity of atherosclerosis and has greatly enriched our knowledge on atherosclerotic plaques. However, it mainly reveals the structural information of plaques. In contrast, spectroscopic and molecular photoacoustic imaging can potentially improve plaque composition identification, inflammation detection, and ultimately the stratification of plaque vulnerability and risk. In this work, we developed an integrated intravascular ultrasound and optical-resolution photoacoustic microscopy (IVUS-PAM) system with a single catheter as small as 1 mm in diameter, comparable to that of existing clinical IVUS catheters. In addition, by using a GRIN lens to focus the excitation laser pulse, the system provides an optical-diffraction limited photoacoustic lateral resolution as fine as 19.6 micrometers, ~10-fold finer than that of conventional intravascular photoacoustic imaging and existing IVUS technology. The system employs a custom-made miniaturized single-element ultrasonic transducer with a dimension of ~0.5 mm, a centre frequency of ~40 MHz, and a fractional bandwidth of ~60%. The IVUS-PAM can simultaneously acquire co-registered IVUS images with an axial resolution of ~40 micrometers and a lateral resolution of ~200 micrometers. In the future, IVUS-PAM may open up new opportunities for improved high-resolution vulnerable plaque imaging and image-guided stent deployment.

Intravascular Ultrasound (IVUS) is one ultrasonic imaging technology to acquire vascular cross-sectional images for the visualization of the inner vessel structure. This technique has been widely used for the diagnosis and treatment of coronary artery diseases. The detection of the calcified plaque with acoustic shadowing in IVUS images plays a vital role in the quantitative analysis of atheromatous plaques. The conventional method of the calcium detection is manual drawing by the doctors. However, it is very time-consuming, and with high inter-observer and intra-observer variability between different doctors. Therefore, the computer-aided detection of the calcified plaque is highly desired. In this paper, an automated method is proposed to detect the calcified plaque with acoustic shadowing in IVUS images by the Rayleigh mixture model, the Markov random field, the graph searching method and the prior knowledge about the calcified plaque. The performance of our method was evaluated over 996 in-vivo IVUS images acquired from eight patients, and the detected calcified plaques are compared with manually detected calcified plaques by one cardiology doctor. The experimental results are quantitatively analyzed separately by three evaluation methods, the test of the sensitivity and specificity, the linear regression and the Bland-Altman analysis. The first method is used to evaluate the ability to distinguish between IVUS images with and without the calcified plaque, and the latter two methods can respectively measure the correlation and the agreement between our results and manual drawing results for locating the calcified plaque in the IVUS image. High sensitivity (94.68%) and specificity (95.82%), good correlation and agreement (>96.82% results fall within the 95% confidence interval in the Student t-test) demonstrate the effectiveness of the proposed method in the detection of the calcified plaque with acoustic shadowing in IVUS images.

Intravascular ultrasound (IVUS) is one medical imaging technology using invasive ultrasound imaging modality, and has been widely used in the assessment of the extent and severity of the atherosclerosis. Automatic and accurate detection of the shape of the calcified plaque with acoustic shadowing can assist the evaluation and treatment of the pathological changes in the cardiovascular vessels. In this paper, we have developed a method to automatically detect the range of the calcified plaque with acoustic shadowing in IVUS images by combining of the Gaussian mixture model and Markov random field. The results of this study on In-Vivo IVUS images demonstrate that the proposedmethod has great potential for automatically detecting the calcified plaque with acoustic shadowing.

Background The effect of an early short-term home-based cardiac rehabilitation (CR) program on ventricular function in acute myocardial infarction (AMI) patients is not yet clear. The purpose of this study was to evaluate the efficacy of our CR program on the improvement of myocardial function using three-dimensional speckle tracking echocardiography (3D-STE) in AMI patients. Methods Fifty-two AMI patients were randomly assigned to 2 groups after discharge: the rehabilitation group, which participated in an early, home-based CR program, and the control group, which received only usual care. All subjects in both groups underwent 3D-STE examinations of the left ventricle within 48 hours of percutaneous coronary intervention and again 4 weeks after discharge. Global longitudinal strain (GLS), global radial strain (GRS), global area strain (GAS), global circumferential strain (GCS), left ventricular ejection fraction (LVEF), and segmental strains were computed. The CR program was initially conducted with supervised inpatient training, followed by an unsupervised home-based training program during a 4-week follow-up. Results We obtained segmental strains from 832 segments, of which 319 were defined as interventional segments, 179 as ischemic segments, and the remaining segments as normal segments. At the 4-week follow-up, when controlling for baseline values, the rehabilitation group showed significant improvements in GLS, GRS, GCS, GAS, LVEF, and in all of the segmental strains of the 3 subgroups compared with the control group (P Conclusion Our study suggests that an early, home-based CR program can greatly improve the ventricular function of AMI patients in a short period of time.

Contrast coronary angiography and catheter based Intravascular Ultrasound (IVUS) are complementary imaging techniques, and have been widely used in clinical diagnosis of vascular diseases. In this paper, a novel approach of 3D reconstruction of coronary vessels based on fusion of coronary angiogram and IVUS images was proposed. First, 3D vessel centerline was reconstructed from a pair of angiograms acquired from a single plane angiography. Secondly, a preprocessing method was proposed for novel IVUS images. Thereafter the coronary lumen and media-adventitia borders were identified based on modified GVF Snake method. Finally, the axial position of each IVUS slice was determined along the 3D vessel centerline and the vessel segment of interest was reconstructed. The results showed that the current reconstruction approach could provide a better segmentation of coronary lumen and media-adventitia borders. The reconstructed 3D vessel can be used as a virtual platform for further study on the coronary arteries.

Background: While statin induces plaque regression, its effects, particularly with different doses on plaque virtual histology composition, remain unknown. Methods and Results: In this prospective, randomized, double-blinded study, 40 consecutive statin-naive patients with stable angina requiring percutaneous coronary intervention (PCI) were randomized to 2 arms (20 patients each) receiving 6 months of atorvastatin 10mg or 40mg daily. The primary end-point was (VH-IVUS) changes from baseline to 6 months, as assessed by a core laboratory. Fifty-four VH-IVUS lesions were analyzed from the 10mg group and 57 from the 40mg group. Overall, plaque volume was reduced by 4.28% (–5.10±14.93mm3, P

This paper aims to provide a short overview of the theoretical background for coronary pressure-derived fractional flow reserve (FFR) index and to focus on its clinical applicability in complex coronary intervention.