BP-Net: Boundary and perfusion feature guided dual-modality ultrasound video analysis network for fibrous cap integrity assessment

Ultrasonography is one of the main imaging methods for monitoring and diagnosing atherosclerosis due to its non-invasiveness and low-cost. Automatic differentiation of carotid plaque fibrous cap integrity by using multi-modal ultrasound videos has significant diagnostic and prognostic value for cardiovascular and cerebrovascular disease patients. However, the task faces several challenges, including high variation in plaque location and shape, the absence of analysis mechanism focusing on fibrous cap, the lack of effective mechanism to capture the relevance among multi-modal data for feature fusion and selection, etc. To overcome these challenges, we propose a new target boundary and perfusion feature guided video analysis network (BP-Net) based on conventional B-mode ultrasound and contrast-enhanced ultrasound videos for assessing the integrity of fibrous cap. Based on our previously proposed plaque auto-tracking network, in our BP-Net, we further introduce the plaque edge attention module and reverse mechanism to focus the dual video analysis on the fiber cap of plaques. Moreover, to fully explore the rich information on the fibrous cap and inside/outside of the plaque, we propose a feature fusion module for B-mode and contrast video to filter out the most valuable features for fibrous cap integrity assessment. Finally, multi-head convolution attention is proposed and embedded into transformer-based network, which captures semantic features and global context information to obtain accurate evaluation of fibrous caps integrity. The experimental results demonstrate that the proposed method has high accuracy and generalizability with an accuracy of 92.35% and an AUC of 0.935, which outperforms than the state-of-the-art deep learning based methods. A series of comprehensive ablation studies suggest the effectiveness of each proposed component and show great potential in clinical application.

Coronary artery properties in atherosclerosis: A deep learning predictive model

In this work an Artificial Neural Network (ANN) was developed to help in the diagnosis of plaque vulnerability by predicting the Young modulus of the core (E _core ) and the plaque (E _plaque ) of atherosclerotic coronary arteries. A representative in silico database was constructed to train the ANN using Finite Element simulations covering the ranges of mechanical properties present in the bibliography. A statistical analysis to pre-process the data and determine the most influential variables was performed to select the inputs of the ANN. The ANN was based on Multilayer Perceptron architecture and trained using the developed database, resulting in a Mean Squared Error (MSE) in the loss function under 10^-7, enabling accurate predictions on the test dataset for E _core and E _plaque . Finally, the ANN was applied to estimate the mechanical properties of 10,000 realistic plaques, resulting in relative errors lower than 3%.

Medical Image-Based Computational Fluid Dynamics and Fluid-Structure Interaction Analysis in Vascular Diseases

Hemodynamic factors, induced by pulsatile blood flow, play a crucial role in vascular health and diseases, such as the initiation and progression of atherosclerosis. Computational fluid dynamics, finite element analysis, and fluid-structure interaction simulations have been widely used to quantify detailed hemodynamic forces based on vascular images commonly obtained from computed tomography angiography, magnetic resonance imaging, ultrasound, and optical coherence tomography. In this review, we focus on methods for obtaining accurate hemodynamic factors that regulate the structure and function of vascular endothelial and smooth muscle cells. We describe the multiple steps and recent advances in a typical patient-specific simulation pipeline, including medical imaging, image processing, spatial discretization to generate computational mesh, setting up boundary conditions and solver parameters, visualization and extraction of hemodynamic factors, and statistical analysis. These steps have not been standardized and thus have unavoidable uncertainties that should be thoroughly evaluated. We also discuss the recent development of combining patient-specific models with machine-learning methods to obtain hemodynamic factors faster and cheaper than conventional methods. These critical advances widen the use of biomechanical simulation tools in the research and potential personalized care of vascular diseases.

Extraction of Coronary Atherosclerotic Plaques From Computed Tomography Imaging: A Review of Recent Methods

Background: Atherosclerotic plaques are the major cause of coronary artery disease (CAD). Currently, computed tomography (CT) is the most commonly applied imaging technique in the diagnosis of CAD. However, the accurate extraction of coronary plaque geometry from CT images is still challenging.

Summary of Review: In this review, we focused on the methods in recent studies on the CT-based coronary plaque extraction. According to the dimension of plaque extraction method, the studies were categorized into two-dimensional (2D) and three-dimensional (3D) ones. In each category, the studies were analyzed in terms of data, methods, and evaluation. We summarized the merits and limitations of current methods, as well as the future directions for efficient and accurate extraction of coronary plaques using CT imaging.

Conclusion: The methodological innovations are important for more accurate CT-based assessment of coronary plaques in clinical applications. The large-scale studies, de-blooming algorithms, more standardized datasets, and more detailed classification of non-calcified plaques could improve the accuracy of coronary plaque extraction from CT images. More multidimensional geometric parameters can be derived from the 3D geometry of coronary plaques. Additionally, machine learning and automatic 3D reconstruction could improve the efficiency of coronary plaque extraction in future studies.

Real-time biomechanics using the finite element method and machine learning: Review and perspective

PURPOSE

The finite element method (FEM) is the preferred method to simulate phenomena in anatomical structures. However, purely FEM-based mechanical simulations require considerable time, limiting their use in clinical applications that require real-time responses, such as haptics simulators. Machine learning (ML) approaches have been proposed to help with the reduction of the required time. The present paper reviews cases where ML could help to generate faster simulations, without considerably affecting the performance results.

METHODS

This review details the ML approaches used, considering the anatomical structures involved, the data collection strategies, the selected ML algorithms, with corresponding features, the metrics used for validation, and the resulting time gains.

RESULTS

A total of 41 references were found. ML algorithms are mainly trained with FEM-based simulations in 32 publications. The preferred ML approach is neural networks, including deep learning in 35 publications. Tissue deformation is simulated in 18 applications, but other features are also considered. The average distance error and mean squared error are the most frequently used performance metrics, in 14 and 17 publications, respectively. The time gains were considerable, going from hours or minutes for purely FEM-based simulations to milliseconds, when using ML.

CONCLUSIONS

ML algorithms can be used to accelerate FEM-based biomechanical simulations of anatomical structures, possibly reaching real-time responses. Fast and real-time simulations of anatomical structures, generated with ML algorithms, can help to reduce the time required by FEM-based simulations and accelerate their adoption in the clinical practice.

A Data-Driven Learning Method for Constitutive Modeling: Application to Vascular Hyperelastic Soft Tissues

We address the problem of machine learning of constitutive laws when large experimental deviations are present. This is particularly important in soft living tissue modeling, for instance, where large patient-dependent data is found. We focus on two aspects that complicate the problem, namely, the presence of an important dispersion in the experimental results and the need for a rigorous compliance to thermodynamic settings. To address these difficulties, we propose to use, respectively, Topological Data Analysis techniques and a regression over the so-called General Equation for the Nonequilibrium Reversible-Irreversible Coupling (GENERIC) formalism (M. Grmela and H. Ch. Oettinger, Dynamics and thermodynamics of complex fluids. I. Development of a general formalism. Phys. Rev. E 56, 6620, 1997). This allows us, on one hand, to unveil the true “shape” of the data and, on the other, to guarantee the fulfillment of basic principles such as the conservation of energy and the production of entropy as a consequence of viscous dissipation. Examples are provided over pseudo-experimental and experimental data that demonstrate the feasibility of the proposed approach.

Using artificial neural networks to predict impingement and dislocation in total hip arthroplasty

Dislocation after total hip arthroplasty (THA) remains a major issue and an important post-surgical complication. Impingement and subsequent dislocation are influenced by the design (head size) and position (anteversion and abduction angles) of the acetabulum and different movements of the patient, with external extension and internal flexion the most critical movements. The aim of this study is to develop a computational tool based on a three-dimensional (3D) parametric finite element (FE) model and an artificial neural network (ANN) to assist clinicians in identifying the optimal prosthesis design and position of the acetabular cup to reduce the probability of impingement and dislocation. A 3D parametric model of a THA was used. The model parameters were the femoral head size and the acetabulum abduction and anteversion angles. Simulations run with this parametric model were used to train an ANN, which predicts the range of movement (ROM) before impingement and dislocation. This study recreates different configurations and obtains absolute errors lower than 5.5° between the ROM obtained from the FE simulations and the ANN predictions. The ROM is also predicted for patients who had already suffered dislocation after THA, and the computational predictions confirm the patient's dislocations. Summarising, the combination of a 3D parametric FE model of a THA and an ANN is a useful computational tool to predict the ROM allowed for different designs of prosthesis heads.

On the use of machine learning techniques for the mechanical characterization of soft biological tissues

Motivated by the search for new strategies for fitting a material model, a new approach is explored in the present work. The use of numerical and complex algorithms based on machine learning techniques such as support vector machines for regression, bagged decision trees, and artificial neural networks is proposed for solving the parameter identification of constitutive laws for soft biological tissues. First, the mathematical tools were trained with analytical uniaxial data (circumferential and longitudinal directions) as inputs, and their corresponding material parameters of the Gasser, Ogden, and Holzapfel strain energy function as outputs. The train and test errors show great efficiency during the training process in finding correlations between inputs and outputs; besides, the correlation coefficients were very close to 1. Second, the tool was validated with unseen observations of analytical circumferential and longitudinal uniaxial data. The results show an excellent agreement between the prediction of the material parameters of the strain energy function and the analytical curves. Finally, data from real circumferential and longitudinal uniaxial tests on different cardiovascular tissues were fitted; thus, the material model of these tissues was predicted. We found that the method was able to consistently identify model parameters, and we believe that the use of these numerical tools could lead to an improvement in the characterization of soft biological tissues.

Machine learning techniques for the optimization of joint replacements: Application to a short-stem hip implant

Today, different implant designs exist in the market; however, there is not a clear understanding of which are the best implant design parameters to achieve mechanical optimal conditions. Therefore, the aim of this project was to investigate if the geometry of a commercial short stem hip prosthesis can be further optimized to reduce stress shielding effects and achieve better short-stemmed implant performance. To reach this aim, the potential of machine learning techniques combined with parametric Finite Element analysis was used. The selected implant geometrical parameters were: total stem length (L), thickness in the lateral (R1) and medial (R2) and the distance between the implant neck and the central stem surface (D). The results show that the total stem length was not the only parameter playing a role in stress shielding. An optimized implant should aim for a decreased stem length and a reduced length of the surface in contact with the bone. The two radiuses that characterize the stem width at the distal cross-section in contact with the bone were less influential in the reduction of stress shielding compared with the other two parameters; but they also play a role where thinner stems present better results.

Contrast-Enhanced Quantitative Intravascular Elastography: The Impact of Microvasculature on Model-Based Elastography

Model-based intravascular ultrasound elastography visualizes the stress distribution within vascular tissue-information that clinicians could use to predict the propensity of atherosclerotic plaque rupture. However, there are concerns that clusters of microvessels may reduce the accuracy of the estimated stress distribution. Consequently, we have developed a contrast-enhanced intravascular ultrasound system to investigate how plaque microvasculature affects the performance of model-based elastography. In simulations, diameters of 200, 400 and 800 μm were used, where the latter diameter represented a cluster of microvessels. In phantoms, we used a microvessel with a diameter of 750 μm. Peak stress errors of 3% and 38% were incurred in the fibrous cap when stress recovery was performed with and without a priori information about microvessel geometry. The results indicate that incorporating geometric information about plaque microvasculature obtained with contrast-enhanced ultrasound imaging improves the accuracy of estimates of the stress distribution within the fibrous cap precisely.

An automatic method for arterial pulse waveform recognition using KNN and SVM classifiers

The measurement and analysis of the arterial pulse waveform (APW) are the means for cardiovascular risk assessment. Optical sensors represent an attractive instrumental solution to APW assessment due to their truly non-contact nature that makes the measurement of the skin surface displacement possible, especially at the carotid artery site. In this work, an automatic method to extract and classify the acquired data of APW signals and noise segments was proposed. Two classifiers were implemented: k-nearest neighbours and support vector machine (SVM), and a comparative study was made, considering widely used performance metrics. This work represents a wide study in feature creation for APW. A pool of 37 features was extracted and split in different subsets: amplitude features, time domain statistics, wavelet features, cross-correlation features and frequency domain statistics. The support vector machine recursive feature elimination was implemented for feature selection in order to identify the most relevant feature. The best result (0.952 accuracy) in discrimination between signals and noise was obtained for the SVM classifier with an optimal feature subset .

Neural networks applied to discriminate botanical origin of honeys

The aim of this work is develop a tool based on neural networks to predict the botanical origin of honeys using physical and chemical parameters. The managed database consists of 49 honey samples of 2 different classes: monofloral (almond, holm oak, sweet chestnut, eucalyptus, orange, rosemary, lavender, strawberry trees, thyme, heather, sunflower) and multifloral. The moisture content, electrical conductivity, water activity, ashes content, pH, free acidity, colorimetric coordinates in CIELAB space (L(∗), a(∗), b(∗)) and total phenols content of the honey samples were evaluated. Those properties were considered as input variables of the predictive model. The neural network is optimised through several tests with different numbers of neurons in the hidden layer and also with different input variables. The reduced error rates (5%) allow us to conclude that the botanical origin of honey can be reliably and quickly known from the colorimetric information and the electrical conductivity of honey.

Computational fluid dynamics in coronary artery disease

Computational fluid dynamics (CFD) is a widely used method in mechanical engineering to solve complex problems by analysing fluid flow, heat transfer, and associated phenomena by using computer simulations. In recent years, CFD has been increasingly used in biomedical research of coronary artery disease because of its high performance hardware and software. CFD techniques have been applied to study cardiovascular haemodynamics through simulation tools to predict the behaviour of circulatory blood flow in the human body. CFD simulation based on 3D luminal reconstructions can be used to analyse the local flow fields and flow profiling due to changes of coronary artery geometry, thus, identifying risk factors for development and progression of coronary artery disease. This review aims to provide an overview of the CFD applications in coronary artery disease, including biomechanics of atherosclerotic plaques, plaque progression and rupture; regional haemodynamics relative to plaque location and composition. A critical appraisal is given to a more recently developed application, fractional flow reserve based on CFD computation with regard to its diagnostic accuracy in the detection of haemodynamically significant coronary artery disease.

Does microcalcification increase the risk of rupture?

Rupture of atherosclerotic plaque, which is related to maximal stress conditions in the plaque among others, is a major cause of mortality. More careful examination of stress distributions in atherosclerotic plaques reports that it could be due to local stress behaviors at critical sites caused by cap thinning, inflammation, macroscopic heterogeneity, and recently, the presence of microcalcifications. However, the role of microcalcifications is not yet fully understood, and most finite element models of blood vessels with atheroma plaque ignore the heterogeneity of the plaque constituents at the microscale. The goal of this work is to investigate the effect of microcalcifications on the stress field of an atheroma plaque vessel section. This is achieved by performing a parametric finite element study, assuming a plane strain hypothesis, of a coronary artery section with eccentric atheroma plaque and one microcalcification incorporated. The geometrical parameters used to define and design the idealized coronary plaque anatomy and the microcalcification were the fibrous cap thickness and the microcalcification ratio, angle and eccentricity. We could conclude that microcalcifications should be considered in the modeling of this kind of problems since they cause a significant alteration of the vulnerable risk by increasing the maximum maximal principal stress up to 32%, although this increase of stress is not uniform (12% on average). The obtained results show that the fibrous cap thickness, the microcalcification ratio and the microcalcification eccentricity, in combination with the microcalcification angle, appear to be the key morphological parameters that play a determinant role in the maximal principal stress and accordingly in the rupture risk of the plaque.