Search

Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Deep learning techniques aimed at detecting coronary artery stenoses may facilitate the diagnosis. However, previous studies have failed to achieve superior accuracy and performance for real-time labeling. Our study is aimed at confirming the feasibility of real-time coronary artery stenosis detection using deep learning methods. To reach this goal we trained and tested eight promising detectors based on different neural network architectures (MobileNet, ResNet-50, ResNet-101, Inception ResNet, NASNet) using clinical angiography data of 100 patients.Three neural networks have demonstrated superior results. The network based on Faster-RCNN Inception ResNet V2 is the most accurate and it achieved the mean Average Precision of 0.954 and the prediction rate of 3 fps on the validation subset. The relatively lightweight SSD MobileNet V2 network proved itself as the fastest one with an mAP of 0.830 and a mean prediction rate of 38 fps. The model based on RFCN ResNet-101 V2 has demonstrated an optimal accuracy-to-speed ratio. Its mAP makes up 0.94, while the prediction speed is 10 fps.The resultant performance-accuracy balance of the modern neural networks has confirmed the feasibility of real-time coronary artery stenosis detection supporting the decision-making process of the Heart Team interpreting coronary angiography findings.

Anchor losses are one of the dominant sources of dissipation in micro-structures and their influence is even increased in the presence of axial loads. MEMS in which they are likely to play a major role include bistable elements which are nowadays commonly employed in shock sensors and energy harvesters. In this contribution we compute anchor losses both with a semi-analytical approach based on the theory of beams and a fully 3D finite element method including PML for wave dissipation. The two techniques provide coherent predictions and confirm the expectations of strong anchor losses. A fully analytical model is also proposed in the range of limited compressive forces and represents a valid tool for the design of new devices.

Blind image quality assessment (BIQA) is a method to predict the quality of a natural image without the presence of a reference image. Current BIQA models typically learn their prediction separately for different image distortions, ignoring the relationship between the learning tasks. As a result, a BIQA model may has great prediction performance for natural images affected by one particular type of distortion but is less effective when tested on others. In this paper, we propose to address this limitation by training our BIQA model simultaneously under different distortion conditions using multi-task learning (MTL) technique. Given a set of training images, our Multi-Task Learning based Image Quality assessment (MTL-IQ) model first extracts spatial domain BIQA features. The features are then used as an input to a trace-norm regularisation based MTL framework to learn prediction models for different distortion classes simultaneously. For a test image of a known distortion, MTL-IQ selects a specific trained model to predict the image’s quality score. For a test image of an unknown distortion, MTL-IQ first estimates the amount of each distortion present in the image using a support vector classifier. The probability estimates are then used to weigh the image prediction scores from different trained models. The weighted scores are then pooled to obtain the final image quality score. Experimental results on standard image quality assessment (IQA) databases show that MTL-IQ is highly correlated with human perceptual measures of image quality. It also obtained higher prediction performance in both overall and individual distortion cases compared to current BIQA models.

Background and Purpose— According to the International Study of Unruptured Intracranial Aneurysms (ISUIA), anterior circulation (AC) aneurysms of Methods— Information about 932 patients newly diagnosed with intracranial aneurysms between November 1, 2006, and March 31, 2012, including aneurysm status at diagnosis, its location, size, and risk factors, was collected during the multicenter @neurIST project. For each location or location and size subgroup, the odds ratio (OR) of aneurysms being ruptured at diagnosis was calculated. Results— The OR for aneurysms to be discovered ruptured was significantly higher for AcoA (OR, 3.5 [95% confidence interval, 2.6–4.5]) and posterior circulation (OR, 2.6 [95% confidence interval, 2.1–3.3]) than for AC excluding AcoA (OR, 0.5 [95% confidence interval, 0.4–0.6]). Although a threshold of 7 mm has been suggested by ISUIA as a threshold for aggressive treatment, AcoA aneurysms Conclusions— We found that AC aneurysms are not a homogenous group. Aneurysms between 4 and 7 mm located in AcoA or distal anterior cerebral artery present similar rupture odds to posterior circulation aneurysms. Intervention should be recommended for this high-risk lesion group.

Does the future of bioengineering lie in models or experiments? The long-standing debate on how and how much experimental and theoretical research in our field should cooperate can shape the future. This debate means often a choice, early in the bioengineer’s career. A bioengineer may prefer to address scientific questions based on experimental tests, or on computational and theoretical analyses. This fundamental choice can drive the future bioengineer’s mindset. Unsurprisingly, laboratories and researchers often assemble in separate, competitive teams. Indeed, the way bioengineers tackle a question is shaped by the characteristic techniques – experimental, theoretical, and computational – they are trained for. Here, without neglecting the obvious advantages of specializing exclusively in experimental, or theoretical and computational studies, I advocate a way of doing synergistic research that combine different approaches. Moreover, I believe that bioengineering desperately needs synergy and cooperation to pave the way for significant discoveries. We need efforts to train a new generation of biomedical engineers: individuals who take advantage of these synergies, who design projects accordingly, and who make these approaches work cooperatively., Seventh Framework Programme (European Commission) (Marie Sklodowska-Curie International Outgoing Fellowship Grant PIOF-GA-2013-625500)

The analysis of Micro-Electro-Mechanical structures is addressed focusing on the evaluation of damping forces exerted by the surrounding gas on moving parts. A mixed formulation based on both velocity and traction integral equations is employed and accelerated via a Fast Multipole Method. Several examples are addressed in order to test the convergence properties of the proposed formulation

The numerical simulation of fatigue crack propagation in 3D linear elastic bodies is addressed. The symmetric Galerkin BEM is employed, thus drastically reducing the remeshing work compared to what is needed by domain formulations. The propagation algorithm adopted has been implemented into a fully automated numerical code and utilized to analyze two examples concerning surface breaking cracks.

Personalized simulations can help assess and predict the clinical status of patients and are a key tenet of the Virtual Physiological Human (VPH) framework. This paper shows how the turnkey access of GIMIAS, an open source software platform built on open source toolkits (VTK, MITK,ITK), thanks to his inclusion in VPH-Share, an infrastructure European project with open-source components, was key to progressing the deployment effectiveness for MySpine, a VPH European project, among his geographically dispersed community

This paper presents a framework for the fusion of multiple point distribution models (PDMs) with unknown point correspondences. With this work, models built from distinct patient groups and imaging modalities can be merged, with the aim to obtain a PDM that encodes a wider range of anatomical variability. To achieve this, two technical challenges are addressed in this work. Firstly, the model fusion must be carried out directly on the corresponding means and eigenvectors as the original data is not always available and cannot be freely exchanged across centers for various legal and practical reasons. Secondly, the PDMs need to be normalized before fusion as the point correspondence is unknown. The proposed framework is validated by integrating statistical models of the left and right ventricles of the heart constructed from different imaging modalities (MRI and CT) and with different landmark representations of the data. The results show that the integration is statistically and anatomically meaningful and that the quality of the resulting model is significantly improved.

In this document it is described the implementation of the flux driven automatic centerline extraction algorithm proposed by Bouix et al. in 2004. This is based on a skeletonisation algorithm initially proposed by Siddiqi et al. in 2002, using properties of an average outward flux measure to distinguish skeletal points from non-skeletal ones. This information is combined with a topology preserving thinning procedure to obtain the final result. This implementation combines this skeletonisation algorithm with other techniques as described in the paper of Bouix et al. to produce an ITK filter that generates as output the skeleton, as a binary object represented in an image, of the input surface, represented as a distance transform image. In this work is described this medial curve extraction procedure following the ITK philosophy.

Intracranial stents are medical devices that are becoming increasingly popular in the treatment of intracranial aneurysms. A methodology that predicts the released stent configuration prior to intervention has the potential to support the physician in the selection of the optimal approach for a specific patient. This paper proposes a fast virtual stenting technique based on constrained simplex deformable models that is able to virtually release stents in arbitrarily shaped vessel and aneurysm models. The technique effectively embeds the geometrical properties of the stent (cell design, strut size and shape and angles between struts) and achieves favorable execution times of the order of one minute.

An algorithm for minimally interactive coronary artery tracking is presented. Tracking ability and accuracy results are demonstrated on 16 images CTA images. First, a region of interest is automatically selected and a denoising filter applied. Then, for each voxel the probability of belonging to a coronary vessel is estimated from a feature space and a vesselness measure is used to obtain a cost function. The vessel starting point is obtained automatically, while the end point is provided by the user. Finally, the centerline is obtained as the minimal cost path between both points.

Haemodynamics, and in particular wall shear stress, is thought to play a critical role in the progression and rupture of intracranial aneurysms. A novel method is presented that combines image-based wall motion estimation obtained through non-rigid registration with computational fluid dynamics (CFD) simulations in order to provide realistic intra-aneurysmal flow patterns and understand the effects of deforming walls on the haemodynamic patterns. In contrast to previous approaches, which assume rigid walls or ad hoc elastic parameters to perform the CFD simulations, wall compliance has been included in this study through the imposition of measured wall motions. This circumvents the difficulties in estimating personalized elasticity properties. Although variations in the aneurysmal haemodynamics were observed when incorporating the wall motion, the overall characteristics of the wall shear stress distribution do not seem to change considerably. Further experiments with more cases will be required to establish the clinical significance of the observed variations.

As for almost every form of knowledge, the volume of data describing human disease processes, including our understanding, diagnosis, and management of them, is growing exponentially. The data is also increasingly heterogeneous in form as text, images, and other symbolic formats. The data is also extremely diverse in context. For instance, it ranges from global guidelines based on the broadest epidemiological studies, through knowledge gained from disease-specific scientific studies, both in vitro and in vivo, to individual patient-specific data. In addition, the data also scales from the molecular to the cellular sizes, and from tissue or organ to patient representations. The recent breakthroughs in the description of the human genome and in our understanding of its connection to disease processes have also contributed more data through functional genomics studies. This phenomenal volume of fragmented information and its growth rate represent an unprecedented data-management challenge. In particular, it is often impossible for an individual— whether a clinician responsible for patient management, or a physicist or engineer developing new imaging or interventional devices—to understand and assimilate this knowledge. The result is that it has become increasingly evident that new methods are required to manage, integrate and search data so that it becomes accessible to the end user. The @neurIST project was designed to address this issue.1

The @neurIST project will develop a vertical and integrative approach to knowledge discovery, personalized risk assessment, patient guideline generation and treatment design. The project will have a big impact on the way that cerebral aneurysms are understood and handled and will provide a reusable and scalable approach to other diseases.

In this work we present a Grid-based optimization approach performed on a set of parameters that affects both the geometric and grey-level appearance properties of a three-dimensional model-based algorithm for cardiac MRI segmentation. The search for optimal values was assessed by a Monte Carlo procedure using computational Grid technology. A series of segmentation runs were conducted on an evaluation database comprising 30 studies at two phases of the cardiac cycle (60 datasets), using three shape models constructed by different methods. For each of these model-patient combinations, six parameters were optimized in two steps: those which affect the grey-level properties of the algorithm first and those relating to the geometrical properties, secondly. Two post-processing tasks (one for each stage) collected and processed (in total) more than 70000 retrieved result files. Qualitative and quantitative validation of the fitting results indicates that the segmentation performance was greatly improved with the tuning. Based on the experienced benefits with the use of our middleware, and foreseeing the advent of large-scale tests and applications in cardiovascular imaging, we strongly believe that the use of Grid computing technology in medical image analysis constitutes a real necessity.

An important assessment in patients with ischemic heart disease is whether myocardial contractility may improve after treatment. The prediction of myocardial contractility improvement is generally performed under physical or pharmalogical stress conditions. In this paper, we present a technique to build a statistical model of healthy myocardial contraction using independent component analysis. The model is used to detect regions with abnormal contraction in patients both during rest and stress.

Tagged Magnetic Resonance Imaging (MRI) is currently the reference MR modality for myocardial motion and strain analysis. NMI-based non rigid registration has proven to be an accurate method to retrieve cardiac deformation fields. The use of alphaMI permits higher dimensional features to be implemented in myocardial deformation estimation through image registration. This paper demonstrates that this is feasible with a set of Haar wavelet features of high dimension. While we do not demonstrate performance improvement for this set of features, there is no significant degradation as compared to implementing the registration method with the traditional NMI metric. We use Entropic Spanning Graphs (ESGs) to estimate the alphaMI of the wavelet feature vectors WFVs since this is not possible with histograms. To the best of our knowledge, this is the first time that ESGs are used for non rigid registration.

A novel anisotropic diffusion filter is proposed in this work with application to cardiac ultrasonic images. It includes probabilistic models which describe the probability density function (PDF) of tissues and adapts the diffusion tensor to the image iteratively. For this purpose, a preliminary study is performed in order to select the probability models that best fit the stastitical behavior of each tissue class in cardiac ultrasonic images. Then, the parameters of the diffusion tensor are defined taking into account the statistical properties of the image at each voxel. When the structure tensor of the probability of belonging to each tissue is included in the diffusion tensor definition, a better boundaries estimates can be obtained instead of calculating directly the boundaries from the image. This is the main contribution of this work. Additionally, the proposed method follows the statistical properties of the image in each iteration. This is considered as a second contribution since state-of-the-art methods suppose that noise or statistical properties of the image do not change during the filter process.