0000000000003350
AUTHOR
Alain Lalande
Generative Adversarial Networks in Cardiology
A B S T R A C T Generative Adversarial Networks (GANs) are state-of-the-art neural network models used to synthesize images and other data. GANs brought a considerable improvement to the quality of synthetic data, quickly becoming the standard for data generation tasks. In this work, we summarize the applications of GANs in the field of cardiology, including generation of realistic cardiac images, electrocardiography signals, and synthetic electronic health records. The utility of GAN-generated data is discussed with respect to research, clinical care, and academia. Moreover, we present illustrative examples of our GAN-generated cardiac magnetic resonance and echocardiography images, showin…
Measurement of the local aortic stiffness by a non-invasive bioelectrical impedance technique.
International audience; Aortic stiffness measurement is well recognized as an independent predictor of cardiovascular mortality and morbidity. Recently, a simple method has been proposed for the evaluation of the local aortic stiffness (AoStiff) using a non-invasive bioelectrical impedance (BI) technique. This approach relies on a novel interpretation of the arterial stiffness where AoStiff is computed from the measurement of two new BI variables: (1) the local aortic flow resistance (AoRes) exerted by the drag forces onto the flow; (2) the local aortic wall distensibility (AoDist). Herein, we propose to detail and compare these three indices with the reference pulse wave velocity (PWV) mea…
Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges
International audience
IRM cardio-vasculaire, des séquences d'acquisition aux paramètres physiologiques
Mes travaux de recherche s'articulent principalement autour de l'extraction automatisée de paramètres anatomiques et fonctionnels en L'Imagerie par Résonance Magnétique (IRM) du cœur et de l'aorte (les renvois des références dans ce document correspondent aux numéros de la liste des publications). Plus précisément, ces travaux sur l'IRM portent sur les thématiques suivantes : - Etude de la fonction cardiaque - Etude de la désynchronisation cardiaque - Etude de la perfusion myocardique et de la viabilité - Etude de l'élasticité de l'aorte - Etude du flux sanguin et détermination de zones de stress au niveau de la paroi de l'aorte - Métrologie des sinus de Valsalva Ces différents points vont …
3D segmentation of abdominal aorta from CT-scan and MR images
International audience; We designed a generic method for segmenting the aneurismal sac of an abdominal aortic aneurysm (AAA) both from multi-slice MR and CT-scan examinations. It is a semi-automatic method requiring little human intervention and based on graph cut theory to segment the lumen interface and the aortic wall of AAAs. Our segmentation method works independently on MRI and CT-scan volumes and has been tested on a 44 patient dataset and 10 synthetic images. Segmentation and maximum diameter estimation were compared to manual tracing from 4 experts. An inter-observer study was performed in order to measure the variability range of a human observer. Based on three metrics (the maxim…
Deep Generative Model-Driven Multimodal Prostate Segmentation in Radiotherapy
Deep learning has shown unprecedented success in a variety of applications, such as computer vision and medical image analysis. However, there is still potential to improve segmentation in multimodal images by embedding prior knowledge via learning-based shape modeling and registration to learn the modality invariant anatomical structure of organs. For example, in radiotherapy automatic prostate segmentation is essential in prostate cancer diagnosis, therapy, and post-therapy assessment from T2-weighted MR or CT images. In this paper, we present a fully automatic deep generative model-driven multimodal prostate segmentation method using convolutional neural network (DGMNet). The novelty of …
Cardiac motion tracking using a deformable 2D-mesh modeling
International audience; Abstract: The work reported here deals with movement tracking in sequences of medical images in order to quantify the general movements and deformations of the heart For this purpose, we partition the first image into triangular patches in order that each object of the image corresponds to a set of triangles. Then, the nodes of the mesh are tracked across the image sequence giving a mesh which warps with the images. The method is applied to cardiac image sequences where the study of the deformation of the triangles is applied to the determination of the movement of the ventricles
Automatic classification of tissues on pelvic MRI based on relaxation times and support vector machine
International audience; Tissue segmentation and classification in MRI is a challenging task due to a lack of signal intensity standardization. MRI signal is dependent on the acquisition protocol, the coil profile, the scanner type, etc. While we can compute quantitative physical tissue properties independent of the hardware and the sequence parameters, it is still difficult to leverage these physical properties to segment and classify pelvic tissues. The proposed method integrates quantitative MRI values (T1 and T2 relaxation times and pure synthetic weighted images) and machine learning (Support Vector Machine (SVM)) to segment and classify tissues in the pelvic region, i.e.: fat, muscle, …
Automatic detection of cardiac contours on MR Images using fuzzy logic and dynamic programming
International audience; Abstract: This paper deals with the use of fuzzy logic and dynamic programming in the detection of cardiac contours in MR Images. The definition of two parameters for each pixel allows the construction of the fuzzy set of the cardiac contour points. The first parameter takes into account the grey level, and the second the presence of an edge. A corresponding fuzzy matrix is derived from the initial image. Finally, a dynamic programming with graph searching is performed on this fuzzy matrix. The method has been tested on several MR images and the results of the contouring were validated by an expert in the domain. This preliminary work clearly demonstrates the interes…
Object tracking in medical imaging using a 2D active mesh system
International audience; Abstract: This article proposes a technique for tracking moving organs in medical imaging. It can be split into two stages. We first initialize a 2D-triangular mesh on the first image of the sequence. We distinguish different objects of interest by grouping together the triangles that make them up. Afterwards, we deform this mesh on the successive images in order to track each identified object. The tracking stage uses optical flow by adding a node relaxation step to avoid mesh deteriorations. The mesh deformations analysis provides access to motion information along the sequence. This technique is applied to a cine-MRI sequences of the heart and allows the analysis …
An adapted optical flow algorithm for robust quantification of cardiac wall motion from standard cine-MR examinations
International audience; This paper presents a method for local myocardial motion estimation from a conventional steady-state free precession cine-MRI sequence using a modified phase-based optical flow (OF) technique. Initially, the technique was tested on synthetic images to evaluate its robustness with regards to Rician noise and to brightness variations. The method was then applied to cardiac images acquired on 11 healthy subjects. Myocardial velocity is measured in centimeter per second in each studied pixel and visualized as colored vectors superimposed on MRI images. The estimated phase-based OF results were compared with a reference OF method and gave similar results on synthetic imag…
Automatic determination of aortic compliance with cine-magnetic resonance imaging - An application of fuzzy logic theory
International audience; Abstract: RATIONALE AND OBJECTIVES. Aortic compliance is defined as the relative change in aortic cross-sectional area divided by the change in arterial pressure. Magnetic resonance imaging (MRI) is a useful imaging modality for the noninvasive evaluation of aortic compliance. However, manual tracing of the aortic contour is subject to important interobserver variations. To estimate the aortic compliance from cine-MRI, a method based on fuzzy logic theory was elaborated. MATERIALS AND METHODS. Seven healthy volunteers and eight patients with Marfan syndrome were examined using an ECG gated cine-MRI sequence. The aorta was imaged in the transverse plane at the level o…
Improved estimation of the left ventricular ejection fraction using a combination of independent automated segmentation results in cardiovascular magnetic resonance imaging
—This work aimed at combining different segmenta-tion approaches to produce a robust and accurate segmentation result. Three to five segmentation results of the left ventricle were combined using the STAPLE algorithm and the reliability of the resulting segmentation was evaluated in comparison with the result of each individual segmentation method. This comparison was performed using a supervised approach based on a reference method. Then, we used an unsupervised statistical evaluation, the extended Regression Without Truth (eRWT) that ranks different methods according to their accuracy in estimating a specific biomarker in a population. The segmentation accuracy was evaluated by focusing o…
Major impact of admission glycemia on myocardial perfusion assessed by magnetic resonance imaging, in patients with acute myocardial infarction
International audience
Intramural neovascularization and haemorrhages are major long‐term effects of intravascularγ‐radiation after stenting
Structural changes that might influence the structural integrity of the vessel in response to intravascular brachytherapy (IVB) and stenting were examined, focus being on the importance of neovascularization in rabbit stented arteries. Stents were implanted in the infrarenal aortas of rabbits, immediately followed by gamma IVB or a sham radiation procedure, and the arteries harvested at 6 months. Labelling for von Willebrand factor showed an increase in adventitial and medial neovascularization in irradiated versus control arteries group (5.04+/-0.89 versus 1.51+/-0.23 mm(-2), respectively; p=0.004). Moreover, intramedial haemorrhages (free hemosiderin deposition) and inflammation (macropha…
Cardiovascular magnetic resonance-derived aortic compliance, distensibility and pulse wave velocity at rest and during a supine bicycle exercise in young adults: A pilot study.
Background Purpose: Risk of aortic rupture is evaluated based on the vessel diameter; this parameter is probably insufficient. In vivo evaluation of biomechanical property of the aortic tissue might be of interest to discriminate between normal and altered aortic tissue (A Lalande et al, JMRI 2008). The purpose of this study was to describe a technique to measure regional aortic compliance (AC), aortic distensibility (AD) and aortic stiffness with 1.5 T MRI in young individuals under resting conditions and during supine bicycle exercise.
GridNet with Automatic Shape Prior Registration for Automatic MRI Cardiac Segmentation
In this paper, we propose a fully automatic MRI cardiac segmentation method based on a novel deep convolutional neural network (CNN) designed for the 2017 ACDC MICCAI challenge. The novelty of our network comes with its embedded shape prior and its loss function tailored to the cardiac anatomy. Our model includes a cardiac center-of-mass regression module which allows for an automatic shape prior registration. Also, since our method processes raw MR images without any manual preprocessing and/or image cropping, our CNN learns both high-level features (useful to distinguish the heart from other organs with a similar shape) and low-level features (useful to get accurate segmentation results).…
Semantic and topological classification of images in magnetically guided capsule endoscopy
International audience; Magnetically-guided capsule endoscopy (MGCE) is a nascent technology with the goal to allow the steering of a capsule endoscope inside a water filled stomach through an external magnetic field. We developed a classification cascade for MGCE images with groups images in semantic and topological categories. Results can be used in a post-procedure review or as a starting point for algorithms classifying pathologies. The first semantic classification step discards over-/under-exposed images as well as images with a large amount of debris. The second topological classification step groups images with respect to their position in the upper gastrointestinal tract (mouth, es…
Automatic Myocardial Infarction Evaluation from Delayed-Enhancement Cardiac MRI using Deep Convolutional Networks
In this paper, we propose a new deep learning framework for an automatic myocardial infarction evaluation from clinical information and delayed enhancement-MRI (DE-MRI). The proposed framework addresses two tasks. The first task is automatic detection of myocardial contours, the infarcted area, the no-reflow area, and the left ventricular cavity from a short-axis DE-MRI series. It employs two segmentation neural networks. The first network is used to segment the anatomical structures such as the myocardium and left ventricular cavity. The second network is used to segment the pathological areas such as myocardial infarction, myocardial no-reflow, and normal myocardial region. The segmented …
3D landmark detection for augmented reality based otologic procedures
International audience; Ear consists of the smallest bones in the human body and does not contain significant amount of distinct landmark points that may be used to register a preoperative CT-scan with the surgical video in an augmented reality framework. Learning based algorithms may be used to help the surgeons to identify landmark points. This paper presents a convolutional neural network approach to landmark detection in preoperative ear CT images and then discusses an augmented reality system that can be used to visualize the cochlear axis on an otologic surgical video.
Quantifying stenosis in renal arteriograms: a fuzzy syntactic analysis.
AbstractThe introduction of fuzzy logic improves a system for the automatic quantification of renal artery lesions seen in digital subtraction angiograms. A two-step approach has been followed. An earlier system based on non-fuzzy syntactic analysis provided a clear symbolic description of the stenotic lesions. Although this system worked correctly, it did not take into account the variability and uncertainty inherent to image processing and to knowledge on the reference diameter. This system has been improved by the introduction of fuzzy logic in the representation of the reference diameter. It provides a description of the stenosis in terms of fuzzy quantities. To illustrate the benefits …
Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?
Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac magnetic resonance images (multi-slice 2-D cine MRI) is a common clinical task to establish diagnosis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the “Automatic Cardiac Diagnosis Challenge” dataset (ACDC), the largest publicly available and fully annotated dataset for the purpose of cardiac MRI (CMR) assessment. The dataset contains data from 150 multi-equipments CMRI recordings with reference measurements and classification from two medical experts. The overarching objective of this paper is to measure how f…
FCA-Net: Adversarial Learning for Skin Lesion Segmentation Based on Multi-Scale Features and Factorized Channel Attention
International audience; Skin lesion segmentation in dermoscopic images is still a challenge due to the low contrast and fuzzy boundaries of lesions. Moreover, lesions have high similarity with the healthy regions in terms of appearance. In this paper, we propose an accurate skin lesion segmentation model based on a modified conditional generative adversarial network (cGAN). We introduce a new block in the encoder of cGAN called factorized channel attention (FCA), which exploits both channel attention mechanism and residual 1-D kernel factorized convolution. The channel attention mechanism increases the discriminability between the lesion and non-lesion features by taking feature channel int…
Automatic evaluation of the peri-infarct area of myocardial infarction from delayed enhancement MRI
International audience; Delay Enhancement - Magnetic Resonance Imaging (DE-MRI) can be considered as the gold standard for the assessment of myocardial viability after myocardial infarction (MI). Around the infarcted areas that appear with hyper-enhanced signal, there is a peri-infarct border zone that may be an important arrhythmogenic substrate. The extent of this area is an independent predictor of post-MI mortality (1). However, it is difficult to separate peri-infarct border zones from infarct core or normal areas, because of their intermediate signal intensity. We propose a new automatic approach to detect this area, based on a modified Gaussian Mixture Model (GMM) and spatial-weighte…
A fuzzy automaton to detect and quantify artery lesions from arteriograms.
International audience
Learning With Context Feedback Loop for Robust Medical Image Segmentation
Deep learning has successfully been leveraged for medical image segmentation. It employs convolutional neural networks (CNN) to learn distinctive image features from a defined pixel-wise objective function. However, this approach can lead to less output pixel interdependence producing incomplete and unrealistic segmentation results. In this paper, we present a fully automatic deep learning method for robust medical image segmentation by formulating the segmentation problem as a recurrent framework using two systems. The first one is a forward system of an encoder-decoder CNN that predicts the segmentation result from the input image. The predicted probabilistic output of the forward system …
Multi-modal image fusion for small animal studies in in-line PET /3T MRI
Congrès sous l’égide de la Société Française de Génie Biologique et Médical (SFGBM).; National audience; In the framework of small animal multi-modal imaging, the current progression of the IMAPPI project is illustrated by the design of an in-line PET/MRI prototype, coupled to a dedicated multi-resolution registration method allowing the robust fusion of data coming from both modalities. The first results show a good alignment of the data from tumor imaging at the level of the abdomen.
Tracking of blood vessels motion from 4D-flow MRI data
This paper presents a novel approach to track objects from 4D Flow MRI data. A salient feature of the proposed method is that it fully exploits the geometrical and dynamical nature of the information provided by this imaging modality. The underlying idea consists in formulating the tracking problem as a data assimilation problem, in which both position and velocity observations are extracted from the 4D Flow MRI data series. Optimal estate estimation is then performed in a sequential fashion via Kalman filtering. The capabilities of the method are extensively assessed in a numerical study involving synthetic and clinical data.
Relationship between fragmented QRS and no-reflow, infarct size, and peri-infarct zone assessed using cardiac magnetic resonance in patients with myocardial infarction.
International audience; BACKGROUND: The relation between fragmented QRS complex (fQRS) and cardiac magnetic resonance parameters is poorly documented in ischemic cardiopathy. METHODS: Among 209 consecutive patients, those with fQRS were compared with those without fQRS. Cardiac magnetic resonance studies with late gadolinium-enhanced sequences were done during the week after acute myocardial infarction. RESULTS: fQRS was present in 113 (54%) patients, and associated with a significantly lower left ventricular ejection fraction, increased left ventricular volumes, a larger infarct size (IS), and a larger peri-infarct zone. Microvascular obstruction was more frequent in patients with fQRS (62…
Comparaison de la mesure des déformations de fantômes de l’aorte à partir d’image obtenues par IRM et stéréovision
International audience; The study of the wall strain distribution could be helpful to improve the decision criterion for surgery of aortic aneurysm. Recently, numerical simulations can complete the data obtained from imaging measurement in order to develop reliable models. However, the used medical imaging tools are not experimentally validated, in metrological point of view. The aim of this study focused on accuracy and reliability of measurement obtained from kinetic MR sequences. The measures of deformations from MRI were compare to those obtained from stereovision system. Cylindrical phantom of silicone material similar to arterial behavior simulated a symmetric aneurysm was designed. A…
Stereo calibration of non-overlapping field of view heterogeneous cameras for calibrating surgicalmicroscope with external tracking camera
International audience
Use of Super Paramagnetic Iron Oxide Nanoparticles as Drug Carriers in Brain and Ear: State of the Art and Challenges
International audience; Drug delivery and distribution in the central nervous system (CNS) and the inner ear represent a challenge for the medical and scientific world, especially because of the blood–brain and the blood–perilymph barriers. Solutions are being studied to circumvent or to facilitate drug diffusion across these structures. Using superparamagnetic iron oxide nanoparticles (SPIONs), which can be coated to change their properties and ensure biocompatibility, represents a promising tool as a drug carrier. They can act as nanocarriers and can be driven with precision by magnetic forces. The aim of this study was to systematically review the use of SPIONs in the CNS and the inner e…
Utility of Cardiac Magnetic Resonance to assess association between admission hyperglycemia and myocardial damage in patients with reperfused ST-segment elevation myocardial infarction
Abstract Aims to investigate the association between admission hyperglycemia and myocardial damage in patients with ST-segment elevation myocardial infarction (STEMI) using Cardiac Magnetic Resonance (CMR). Methods We analyzed 113 patients with STEMI treated with successful primary percutaneous coronary intervention. Admission hyperglycemia was defined as a glucose level ≥ 7.8 mmol/l. Contrast-enhanced CMR was performed between 3 and 7 days after reperfusion to evaluate left ventricular function and perfusion data after injection of gadolinium-DTPA. First-pass images (FP), providing assessment of microvascular obstruction and Late Gadolinium Enhanced images (DE), reflecting the extent of in…
Dynamic 4D Blood Flow Representation in the Aorta and Analysis from Cine-MRI in Patients
International audience; Abstract: Natural evolution of aortic disease is characterized by a diameter increase that can result in aortic dissection or rupture. Currently the evaluation of risk of rupture or dissection is based on the size of the aorta. However, this parameter is not always relevant and it appears necessary to define new parameters. In this perspective, 3D velocity imaging acquired with ECG gated velocity-encoded cine-MRI allows the aortic blood flow study. As the acquired images are not directly usable, the present study proposes a 4D-representation Of aortic blood flow in order to optimize the visualization of the particularities of non-laminar flow within the aorta. Image …
Compliance and Pulse Wave Velocity Assessed by MRI Detect Early Aortic Impairment in Young Patients With Mutation of the Smooth Muscle Myosin Heavy Chain
Purpose To evaluate aortic elasticity with MRI on young asymptomatic individuals with mutation of the smooth muscle myosin heavy chain in whom aortic enlargement is not present. Materials and Methods Aortic compliance, aortic distensibility, and pulse wave velocity (PWV) were semiautomatically measured from MRI in 8 asymptomatic subjects having a mutation of the MYH11 gene (M+) and 21 nonmutated relatives (M−) of similar age, sex, and blood pressure characteristics. Results Despite a similar aortic diameter in both groups, the aortic compliance and distensibility were significantly lower in M+ subjects compared with M− (0.84 ± 0.33 versus 2.03 ± 0.54 mm2/mmHg, 1.18 ± 0.62 10−3 versus 5.11 ±…
Exercise stress CMR reveals reduced aortic distensibility and impaired right-ventricular adaptation to exercise in patients with repaired tetralogy of Fallot
International audience; The aim of our study was to evaluate the feasibility of exercise cardiac magnetic resonance (CMR) in patients with repaired tetralogy of Fallot (RTOF) and to assess right and left ventricular adaptation and aortic wall response to exercise in comparison with volunteers.Methods11 RTOF and 11 volunteers underwent prospective CMR at rest and during exercise. A supine bicycle ergometer was employed to reach twice the resting heart rate during continuous exercise, blood pressure and heart rate were recorded. Bi-ventricular parameters and aortic stiffness were assessed using accelerated cine sequences and flow-encoding CMR. A t-test was used to compare values between group…
Automatic Myocardial Infarction Evaluation from Delayed-Enhancement Cardiac MRI Using Deep Convolutional Networks
In this paper, we propose a new deep learning framework for an automatic myocardial infarction evaluation from clinical information and delayed enhancement-MRI (DE-MRI). The proposed framework addresses two tasks. The first task is automatic detection of myocardial contours, the infarcted area, the no-reflow area, and the left ventricular cavity from a short-axis DE-MRI series. It employs two segmentation neural networks. The first network is used to segment the anatomical structures such as the myocardium and left ventricular cavity. The second network is used to segment the pathological areas such as myocardial infarction, myocardial no-reflow, and normal myocardial region. The segmented …
Definition of a mutual reference shape based on information theory and active contours
In this paper, we propose to consider the estimation of a reference shape from a set of different segmentation results using both active contours and information theory. The reference shape is then defined as the minimum of a criterion that benefits from both the mutual information and the joint entropy of the input segmentations. This energy criterion is here justified using similarities between information theory quantities and area measures, and presented in a continuous variational framework. This framework brings out some interesting evaluation measures such as the specificity and sensitivity. In order to solve this shape optimization problem, shape derivatives are computed for each te…
Influence of age and sex on aortic distensibility assessed by MRI in healthy subjects
International audience; Abstract: Magnetic resonance imaging (MRI) is particularly well adapted to the evaluation of aortic distensibility. The calculation of this parameter, based on the change in vessel cross-sectional area per unit change in blood pressure, requires precise delineation of the aortic wall on a series of cine-MR images. Firstly, the study consisted in validating a new automatic method to assess aortic elasticity. Secondly, aortic distensibility was studied for the ascending and descending thoracic aortas in 26 healthy subjects. Two homogeneous groups were available to evaluate the influence of sex and age (with an age limit value of 35 years). The automatic postprocessing …
Realignment of myocardial first-pass MR perfusion images using an automatic detection of the heart-lung interface
International audience; Abstract: Magnetic resonance first-pass imaging of a bolus of contrast agent is well adapted to distinguish normal and hypoperfused areas of the myocardium. In most cases, the signal intensity-time curves in user defined regions of interest (ROI) are studied. As image acquisition is ECG-gated, the images are acquired at the same moment in the cardiac cycle, and the basic shape of the heart is similar from one view to the next. However, superficial respiratory motion can displace the heart in the short-axis plane. The aim of this study is to correct for the respiratory motion of the heart by performing an automatic realignment of the myocardial ROI based on a method t…
Comparison of different segmentation approaches without using gold standard. Application to the estimation of the left ventricle ejection fraction from cardiac cine MRI sequences.
International audience; A statistical method is proposed to compare several estimates of a relevant clinical parameter when no gold standard is available. The method is illustrated by considering the left ventricle ejection fraction derived from cardiac magnetic resonance images and computed using seven approaches with different degrees of automation. The proposed method did not use any a priori regarding with the reliability of each method and its degree of automation. The results showed that the most accurate estimates of the ejection fraction were obtained using manual segmentations, followed by the semiautomatic methods, while the methods with the least user input yielded the least accu…
Integrated PET/MRI in preclinical studies State of the art
International audience; The exquisite tissue contrast of magnetic resonance imaging (MRI), the absence of ionising radiation and the opportunity to obtain new molecular and functional data have strengthened the enthusiasm for coupling MRI rather than computed tomography (CT) to positron emission tomography (PET). When reviewing the current literature one might be surprised by the almost unlimited diversity of what is placed under the name of PET/MRI in the articles. The magnetic field is varying from 0.3 Tesla (T) to 9.4 T, the size of the bore varies also from the wide bore of clinical scanners to volumes limited to a few tens of mL. Many preclinical studies are performed using separate PE…
First steps toward the generation of PET/MR attenuation map in the case of prostate cancer
Congrès sous l’égide de la Société Française de Génie Biologique et Médical (SFGBM).; National audience; A new methodology providing the first step towards the generation of attenuation maps for PET/MR systems based solely on MR information is presented in this paper. From T1-and T2-weighted MR data set and anatomical-based knowledge, our method segments and classifies the attenuation-differing regions of the patient's pelvis using a robust implementation of the weighted fuzzy C-means algorithm. Providing no signal, particular process is performed for the bones. We have demonstrated the feasibility of this approach by correctly segmenting and classifying six attenuation-differing regions on…
A 3D deep learning approach based on Shape Prior for automatic segmentation of myocardial diseases
Accurate three-dimensional (3D) cardiac segmentation from late gadolinium enhancement (LGE)-MRI plays a critical role in designing a structure of reference for diagnosing many cardiac pathologies such as ischemia, myocarditis and myocardial infarction. This segmentation is however still a non-trivial task, due to the motion artifacts during acquisition, and heterogeneous intensity distributions. In this study, we develop a fully 3D automated model based on deep neural networks (DNN) for LGE-MRI myocardial pathologies (scar and No-reflow tissues) segmentation in a new expert annotated dataset. Considering that damaged tissue constitutes a small area of the whole LGE-MRI, we concentrated on m…
Should aortic stiffness be evaluated in thoracic aortic aneurysm/dissection relatives to prevent risks?
International audience
MR imaging of the heart in patients after myocardial infarction: effect of increasing intersection gap on measurements of left ventricular volume, ejection fraction, and wall thickness.
International audience; Abstract: PURPOSE: To determine the extent to which the number of planes imaged at magnetic resonance (MR) imaging could be reduced without modifying the volume and thickness of the left ventricle. MATERIALS AND METHODS: Sixty-one patients were examined after a myocardial infarction. The whole left ventricle was imaged by using 5-mm contiguous breath-hold cine MR short-axis sections with no gap (SA(ng)) (two-dimensional fast low-angle shot sequence, 9/4.8 [repetition time msec/echo time msec]). The effect of omitting in two (short-axis sections with 5-mm gap [SA(5mm)]) or two sections in three(short-axis sections with 10-mm gap [SA(10mm)]) was studied. RESULTS: In th…
Segmentation et métrologie des sinus de Valsalva à partir de ciné-IRM
Automatic segmentation of Valsalva sinuses from cine-MRI
Evaluation automatique du remodelage ventriculaire gauche à partir d'imagerie multimodale en pré-clinique et clinique.
Automatic evaluation of the left ventricular remodelling from MRI in pre-clinical and clinical practice.
Graph cut-based method for segmenting the left ventricle from MRI or echocardiographic images
International audience; In this paper, we present a fast and interactive graph cut method for 3D segmentation of the endocardial wall of the left ventricle (LV) adapted to work on two of the most widely used modalities: magnetic resonance imaging (MRI) and echocardiography. Our method accounts for the fundamentally different nature of both modalities: 3D echocardiographic images have a low contrast, a poor signal-to-noise ratio and frequent signal drop, while MR images are more detailed but also cluttered and contain highly anisotropic voxels. The main characteristic of our method is to work in a 3D Bezier coordinate system instead of the original Euclidean space. This comes with several ad…
Left ventricular ejection fraction calculation from automatically selected and processed diastolic and systolic frames in short-axis cine-MRI
International audience; Abstract: The calculation of the left ventricular ejection fraction (LVEF) is dependent upon the accurate measurement of diastolic and systolic left ventricular volumes. Although breath-hold cine magnetic resonance imaging (MRI) allows coverage of the whole cardiac cycle with an excellent time resolution, many authors rely on the visual selection of diastolic and the systolic short-axis slices in order to reduce the postprocessing time. An automatic method was developed to detect the endocardial contour on each image, allowing an automatic selection of the systolic frame. The calculated ejection fraction was compared with radionuclide ventriculography (RNV). Sixty-fi…
Automatic fuzzy classification of the washout curves from magnetic resonance first-pass perfusion imaging after myocardial infarction.
International audience; Abstract: Objectives: We sought to investigate the diagnostic ability of cardiac magnetic resonance imaging (MRI) perfusion in acute reper-fused myocardial infarction. The study used fuzzy logic to automatically classify signal intensity-time curves from myocardial segments into 3 categories: normal, hypointense, and Hyperintense. Materials and Methods: Thirty-eight patients with myocardial infarction underwent short-axis cine-MRI and contrast-enhanced MRI to provide data on wall thickening and the transmural extent of infarction. Of these, 17 had a second cardiac MRI to ascertain the functional recovery in each segment. Results: The fuzzy logic based classification …
Extraction et analyse automatiques des sinus de Valsalva à partir de séquences IRM
MRI appears to be particularly attractive for the study of the Sinuses of Valsalva (SV), however there is no global consensus on their suitable measurements. In this paper, we propose a new method to automatically evaluate the SV from cine-MRI in a cross-sectional orientation. It consists in the extraction of the shape, the detection of relevant points (commissures, cusps and the centre of the SV), the measure of associated distances and in a classification of the SV as bicuspid or tricuspid. Our method was tested on 23 patient examinations and radii calculations were compared with manual processing. The classification of the valve as tricuspid or bicuspid was correct for all the cases. Mor…
Comparison of the strain field of abdominal aortic aneurysm measured by magnetic resonance imaging and stereovision: a feasibility study for prediction of the risk of rupture of aortic abdominal aneurysm
International audience; The prediction of the risk of rupture of abdominal aortic aneurysm (AAA) is a complex problem. Currently the criteria to predict rupture of abdominal aortic aneurysms are aneurysm diameter and growth rates. It is generally believed that study of the wall strain distribution could be helpful to find a better decision criterion for surgery of aortic aneurysms before their rupture. The wall strain distribution depends on many biological and biomechanical factors such as elastic properties of the aorta, turbulent blood flow, anatomy of the aorta, presence of thrombus or not and so on. Recently, numerical simulations to estimate rupture-potential have received many attent…
Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning
Accurate and reproducible measurements of the aortic diameters are crucial for the diagnosis of cardiovascular diseases and for therapeutic decision making. Currently, these measurements are manually performed by healthcare professionals, being time consuming, highly variable, and suffering from lack of reproducibility. In this work we propose a supervised deep-learning method for the direct estimation of aortic diameters. The approach is devised and tested over 100 magnetic resonance angiography scans without contrast agent. All data was expert-annotated at six aortic locations typically used in clinical practice. Our approach makes use of a 3D+2D convolutional neural network (CNN) that ta…
Automatic classification of tissues using T1 and T2 relaxation times from prostate MRI: a step toward generation of PET/MR attenuation map
This paper presents a new methodology providing the first step towards generating attenuation maps for PET/MR systems based solely on MR information. The new method segments and classifies the attenuation-differing regions of the patient's pelvis based on acquired T 1 - and T 2 -weighted MR data sets and anatomical-based knowledge by computing the tissue specific T 1 and T 2 relaxation times, using a robust implementation of the weighted fuzzy C-means algorithm and applying a novel process to detect bones. We have demonstrated the feasibility of this approach by correctly segmenting and classifying six differing regions of structural and anatomical importance: fat, muscle, prostate, air, ba…
Automatic fuzzy contouring and parameter extraction of the left ventricle from multi-slice MR Images.
International audience
Segmentation-Free Estimation of Aortic Diameters from MRI Using Deep Learning
Accurate and reproducible measurements of the aortic diameters are crucial for the diagnosis of cardiovascular diseases and for therapeutic decision making. Currently, these measurements are manually performed by healthcare professionals, being time consuming, highly variable, and suffering from lack of reproducibility. In this work we propose a supervised deep-learning method for the direct estimation of aortic diameters. The approach is devised and tested over 100 magnetic resonance angiography scans without contrast agent. All data was expert-annotated at six aortic locations typically used in clinical practice. Our approach makes use of a 3D+2D convolutional neural network (CNN) that ta…
Validation of the Strain Assessment of a Phantom of Abdominal Aortic Aneurysm: Comparison of Results Obtained From Magnetic Resonance Imaging and Stereovision Measurements
Predicting aortic aneurysm ruptures is a complex problem that has been investigated by many research teams over several decades. Work on this issue is notably complex and involves both the mechanical behavior of the artery and the blood flow. Magnetic resonance imaging (MRI) can provide measurements concerning the shape of an organ and the blood that flows through it. Measuring local distortion of the artery wall is the first essential factor to evaluate in a ruptured artery. This paper aims to demonstrate the feasibility of this measure using MRI on a phantom of an abdominal aortic aneurysm (AAA) with realistic shape. The aortic geometry is obtained from a series of cine-MR images and reco…
Aortic Function's Adaptation in Response to Exercise-Induced Stress Assessing by 1.5T MRI : A Pilot Study in Healthy Volunteers
AIM:Evaluation of the aortic "elastic reserve" might be a relevant marker to assess the risk of aortic event. Our aim was to compare regional aortic elasticity at rest and during supine bicycle exercise at 1.5 T MRI in healthy individuals. METHODS:Fifteen volunteers (8 men), with a mean age of 29 (23-41) years, completed the entire protocol. Images were acquired immediately following maximal exercise. Retrospective cine sequences were acquired to assess compliance, distensibility, maximum rates of systolic distension and diastolic recoil at four different locations: ascending aorta, proximal descending aorta, distal descending aorta and aorta above the coeliac trunk level. Segmental aortic …
Multi-variate analysis predicts clinical outcome 30 days after middle cerebral artery infarction
BACKGROUND AND PURPOSE: To evaluate the functional prognostic value of proton magnetic resonance spectroscopy performed within the 5 days of an infarction of the middle cerebral artery territory, compared with previously demonstrated prognostic factors. METHODS: Proton magnetic resonance spectroscopy was performed on 77 consecutive non-comatosed patients during the acute stage of middle cerebral artery infarction. The functional status was determined for each patient via the Orgogozo score. Proton magnetic resonance spectroscopic data were acquired in the infarction and in contra-lateral normal tissue and the results were expressed as metabolite ratios. Correlations were evaluated between t…
A reference free approach for the comparative evaluation of eight segmentation methods for the estimation of the left ventricular ejection fraction in cardiac MRI.
International audience; Objective evaluation and comparison of segmentation algorithms for medical imaging is still a challenging issue. The most frequently used evaluation method consists in comparing the segmentation with a manual delineation. Since obtaining such manual segmentation can be tedious, we proposed a method based on the "extended Regression Without Truth" approach (eRWT)(1). This approach is applied to the comparative evaluation of 8 segmentation algorithms with different degrees of automation from the estimated left ventricular ejection fraction (LVEF).
Myocardial Infarction Quantification from Late Gadolinium Enhancement MRI Using Top-Hat Transforms and Neural Networks
Significance: Late gadolinium enhanced magnetic resonance imaging (LGE-MRI) is the gold standard technique for myocardial viability assessment. Although the technique accurately reflects the damaged tissue, there is no clinical standard for quantifying myocardial infarction (MI), demanding most algorithms to be expert dependent. Objectives and Methods: In this work a new automatic method for MI quantification from LGE-MRI is proposed. Our novel segmentation approach is devised for accurately detecting not only hyper-enhanced lesions, but also microvascular-obstructed areas. Moreover, it includes a myocardial disease detection step which extends the algorithm for working under healthy scans.…
[Role of visual analysis of first-pass contrast-enhanced MRI in reperfused myocardial infarction].
The aim of this work is to evaluate the relationship between improvement of regional myocardial function and visual analysis of contrast-enhanced (CE) MRI in patients after acute myocardial infarction. MRI was performed on 19 patients 1 and 11 weeks after a reperfused acute myocardial infarction. Perfusion data (first-pass images [FPI] and delayed CE images) were acquired after an intravenous bolus of gadolinium-DTPA and visually analyzed using a 17 segment model. Each segment was then classified in 3 groups, according to the presence or absence of FPI and CE patterns at baseline study: group 0: normal-appearing segments; group 1: segments with delayed hyper-enhancement but no early hypo-en…
A 3D Network Based Shape Prior for Automatic Myocardial Disease Segmentation in Delayed-Enhancement MRI
Abstract Objectives: In this work, a new deep learning model for relevant myocardial infarction segmentation from Late Gadolinium Enhancement (LGE)-MRI is proposed. Moreover, our novel segmentation method aims to detect microvascular-obstructed regions accurately. Material and methods: We first segment the anatomical structures, i.e., the left ventricular cavity and the myocardium, to achieve a preliminary segmentation. Then, a shape prior based framework that fuses the 3D U-Net architecture with 3D Autoencoder segmentation framework to constrain the segmentation process of pathological tissues is applied. Results: The proposed network reached outstanding myocardial segmentation compared wi…
NCprocessing: a software to determine non-compacted and compacted masses from MRI
International audience
Indications de l'IRM cardiaque.
International audience
Semiautomatic detection of myocardial contours in order to investigate normal values of the left ventricular trabeculated mass using MRI
Purpose To propose, assess, and validate a semiautomatic method allowing rapid and reproducible measurement of trabeculated and compacted left ventricular (LV) masses from cardiac magnetic resonance imaging (MRI). Materials and Methods We developed a method to automatically detect noncompacted, endocardial, and epicardial contours. Papillary muscles were segmented using semiautomatic thresholding and were included in the compacted mass. Blood was removed from trabeculae using the same threshold tool. Trabeculated, compacted masses and ratio of noncompacted to compacted (NC:C) masses were computed. Preclinical validation was performed on four transgenic mice with hypertrabeculation of the LV…
Mutations in myosin heavy chain 11 cause a syndrome associating thoracic aortic aneurysm/aortic dissection and patent ductus arteriosus
We have recently described two kindreds presenting thoracic aortic aneurysm and/or aortic dissection ( TAAD) and patent ductus arteriosus (PDA)(1,2) and mapped the disease locus to 16p12.2-p13.13 (ref. 3). We now demonstrate that the disease is caused by mutations in the MYH11 gene affecting the C-terminal coiled-coil region of the smooth muscle myosin heavy chain, a specific contractile protein of smooth muscle cells (SMC). All individuals bearing the heterozygous mutations, even if asymptomatic, showed marked aortic stiffness. Examination of pathological aortas showed large areas of medial degeneration with very low SMC content. Abnormal immunological recognition of SM-MHC and the colocal…
Evaluation of cardiac structure segmentation in cine magnetic resonance imaging
International audience
Segmentation Integrating Watershed and Shape Priors Applied to Cardiac Delayed Enhancement MR Images
International audience; Background: In recent years, there has been a rapid rise in the use of shape priors applied to segmentation process of medical images. Previous approaches on left ventricle segmentation from Delayed-Enhancement Magnetic Resonance Imaging (DE-MRI) have focused on the extraction of myocardium or just diseased region in short axis orientation. However these studies did not take into account the segmentation of non-diseased myocardium from DE-MRI. The segmentation of non-diseased myocardium from DE-MRI, has some useful applications. For instance it can simplify the PET-MR registration process.Methods: This paper presents a novel semi-automatic segmentation method of non-…
ProstateAnalyzer: web-based medical application for the management of prostate cancer using multiparametric MR imaging
Objectives: In this paper, we present ProstateAnalyzer, a new web-based medical tool for prostate cancer diagnosis. ProstateAnalyzer allows the visualization and analysis of magnetic resonance images (MRI) in a single framework. Methods: ProstateAnalyzer recovers the data from a PACS server and displays all the associated MRI images in the same framework, usually consisting of 3D T2-weighted imaging for anatomy, dynamic contrast-enhanced MRI for perfusion, diffusion-weighted imaging in the form of an apparent diffusion coefficient (ADC) map and MR Spectroscopy. ProstateAnalyzer allows annotating regions of interest in a sequence and propagates them to the others. Results: From a representat…
Familial thoracic aortic aneurysm/dissection with patent ductus arteriosus: genetic arguments for a particular pathophysiological entity.
International audience; Thoracic aortic aneurysm and aortic dissection (TAA and AD) are an important cause of sudden death. Familial cases could account for 20% of all cases. A genetic heterogeneity with two identified genes (FBN1 and COL3A1) and three loci (3p24-25 or MFS2/TAAD2, 5q13-q14 and 11q23.2-24) has been shown previously. Study of a single family composed of 179 members with an abnormally high occurrence of TAA/AD disease. A total of 40 subjects from three generations were investigated. In addition to five cases of stroke and three cases of sudden death, there were four cases of AD and four cases of TAA in adults. In all, 11 cases of patent ductus arteriosus (PDA) were observed, t…
Comparison of two techniques (in vivo and ex-vivo) for evaluating the elastic properties of the ascending aorta: Prospective cohort study.
Introduction Aneurysms of the ascending aorta (AA) correspond to a dilatation of the ascending aorta that progressively evolves over several years. The main complication of aneurysms of the ascending aorta is type A aortic dissection, which is associated with very high rates of morbidity and mortality. Prophylactic ascending aorta replacement guidelines are currently based on maximal AA diameter. However, this criterion is imperfect. Stretching tests on the aorta carried out ex-vivo make it possible to determine the elastic properties of healthy and aneurysmal aortic fragments (tension test, resistance before rupture). For several years now, cardiac magnetic resonance imaging (MRI) has pro…
Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts?
Deep learning methods are the de facto solutions to a multitude of medical image analysis tasks. Cardiac MRI segmentation is one such application, which, like many others, requires a large number of annotated data so that a trained network can generalize well. Unfortunately, the process of having a large number of manually curated images by medical experts is both slow and utterly expensive. In this paper, we set out to explore whether expert knowledge is a strict requirement for the creation of annotated data sets on which machine learning can successfully be trained. To do so, we gauged the performance of three segmentation models, namely U-Net, Attention U-Net, and ENet, trained with dif…
Biomechanical study on ascending aortic aneurysms associated with quadricuspid aortic valve
The quadricuspid aortic valve (QAV) is a rare anatomical situation and the biomechanical properties are not well known when it is associated with ascending aortic aneurysms (AsAA). The objective is to find out what is the biomechanical properties in such situation and to compare it with the existing data. In a sixty-three-years-old female (BMI 26,4) with hypertension disease, QAV, AsAA of 52 mm, an aortic valve and ascending aorta replacement were performed. The aortic wall sample was collected within 30 mins after replacement, partitioned related to medial, posterior, lateral, and anterior quadrants. The sample was cut in square size (15 mm × 15 mm, n = 13) with marking the circumferential…
Inferring postimplant dose distribution of salvage permanent prostate implant (PPI) after primary PPI on CT images
International audience; PURPOSE:To evaluate the dose distribution of additional radioactive seeds implanted during salvage permanent prostate implant (sPPI) after a primary permanent prostate implant (pPPI).METHODS AND MATERIALS:Patients with localized prostate cancer were primarily implanted with iodine-125 seeds and had a dosimetric assessment based on day 30 postimplant CT (CT1). After an average of 6 years, these patients underwent sPPI followed by the same CT-based evaluation of dosimetry (CT2). Radioactive seeds on each CT were detected. The detected primary seeds on CT1 and CT2 were registered and then removed from CT2 referred as a modified CT2 (mCT2). Dosimetry evaluations (D90 and…
Augmented Reality of the Middle Ear Combining Otoendoscopy and Temporal Bone Computed Tomography
International audience; HYPOTHESIS:Augmented reality (AR) may enhance otologic procedures by providing sub-millimetric accuracy and allowing the unification of information in a single screen.BACKGROUND:Several issues related to otologic procedures can be addressed through an AR system by providing sub-millimetric precision, supplying a global view of the middle ear cleft, and advantageously unifying the information in a single screen. The AR system is obtained by combining otoendoscopy with temporal bone computer tomography (CT).METHODS:Four human temporal bone specimens were explored by high-resolution CT-scan and dynamic otoendoscopy with video recordings. The initialization of the system…
Magnetic resonance image segmentation and heart motion tracking with an active mesh based system
International audience; Abstract: The work presented here relates to a method fir motion tracking in sequences of medical images. The purpose is to. quantify the general motions and the local deformations of a beating heart during a cardiac cycle. In order to achieve this goal, we first tessellate the,first image of the sequence into triangular patches. A Delaunay triangulation is applied to find the optimal set of triangles describing this image, giving a mesh covering the organs. One imposes the contours of the organs to correspond to edges of triangles so that each part of the heart (left ventricle, right ventricle, myocardium) can he described as a different set of triai izles, each set…
Real-Time Augmented Reality for Ear Surgery
International audience; Transtympanic procedures aim at accessing the middle ear structures through a puncture in the tympanic membrane. They require visualization of middle ear structures behind the eardrum. Up to now, this is provided by an oto endoscope. This work focused on implementing a real-time augmented reality based system for robotic-assisted transtympanic surgery. A preoperative computed tomography scan is combined with the surgical video of the tympanic membrane in order to visualize the ossciles and labyrinthine windows which are concealed behind the opaque tympanic membrane. The study was conducted on 5 artificial and 4 cadaveric temporal bones. Initially, a homography framew…
On the Use of XML in Medical Imaging Web-Based Applications
The rapid growth of digital technology in medical fields over recent years has increased the need for applications able to manage patient medical records, imaging data, and chart information. Web-based applications are implemented with the purpose to link digital databases, storage and transmission protocols, management of large volumes of data and security concepts, allowing the possibility to read, analyze, and even diagnose remotely from the medical center where the information was acquired. The objective of this paper is to analyze the use of the Extensible Markup Language (XML) language in web-based applications that aid in diagnosis or treatment of patients, considering how this proto…
Cerebral metabolism after transient ischemic attack. A 1H MR spectroscopy study
International audience; Abstract: Metabolic changes induced by cerebral infarction or by stenosis and occlusion of the internal carotid artery have been previously described in 1H Magnetic Resonance Spectroscopy (1H MRS). These changes are essentially characterized by decreased N-acetyl-aspartate (NAA) and increased lactate concentration. Little is known about the metabolic changes observed in the three days following a transient ischemic attack (TIA) in the absence of stenosis or occlusion of the internal carotid artery, and without visible infarction on Magnetic Resonance imaging (MRI). We studied five patients with a TIA lasting between 30 min and 3 h, affecting the sensory and motor fun…
Left-Ventricle Segmentation of SPECT Images of Rats
Single-photon emission computed tomography (SPECT) imaging of the heart is helpful to quantify the left-ventricular ejection fraction and study myocardial perfusion scans. However, these evaluations require a 3-D segmentation of the left-ventricular wall on each phase of the cardiac cycle. This paper presents a fast and interactive graph cut method for 3-D segmentation of the left ventricle (LV) of rats in SPECT images. The method is carried out in three steps. First, 3-D sampling of the LV cavity is made in a spherical-cylindrical coordinate system. Then, a graph-cut-based energy minimization procedure provides delineation of the myocardium centerline surface. From there, it is possible to…
A deep learning approach for the segmentation of myocardial diseases
Cardiac left ventricular (LV) segmentation is a paramount essential step for both diagnosis and treatment of cardiac pathologies such as ischemia, myocardial infarction, arrhythmia and myocarditis. However, this segmentation is challenging due to high variability across patients and the potential lack of contrast between structures. In this work, we propose and evaluate a (2.5D) SegU-Net model based on the fusion of two deep learning segmentation techniques (U-Net and Seg-Net) for automated LGE-MRI (Late gadolinium enhanced magnetic resonance imaging) myocardial disease (infarct core and no-reflow region) quantification in a new multifield expert annotated dataset. Given that the scar tissu…
Hypertrophic cardiomyopathy and fibrosis: correlation between late gadolinium enhancement on CMR and speckle tracking imaging using Ultrasound
Background Hypertrophic cardiomyopathy (HCM) is the most frequent genetic cardiovascular disorder and represents one of the most common cause of heart related sudden death in young adults. Myocardial fibrosis seems to be an independant predictor of adverse events including sudden death, ventricular arrhythmias and heart failure. While late gadolinium enhancement (LGE) on Cardiac Magnetic Resonance (CMR) is actually the gold-standard to detect fibrosis, new techniques are being evaluated such as 2D strain echocardiography.
Automatic Detection of Left Ventricular Contours from Cardiac Cine Magnetic Resonance Imaging Using Fuzzy Logic
Gated cardiac cine magnetic resonance imaging provides accurate dynamic data of the left ventricular function. However, the manual extraction of important physiologic parameters such as myocardium wall thickness and left ventricular volumes is invariably time consuming and subjective. To reduce the variability and time constraints inherent in observer contour tracing, the authors developed an automatic left ventricle contour-detection method.The purpose was to apply fuzzy logic-based automatic contour detection to identification of endocardial and epicardial borders in short-axis magnetic resonance images. The automatic contouring was compared with manual tracing using the calculated ejecti…
Convolutional Neural Network With Shape Prior Applied to Cardiac MRI Segmentation.
In this paper, we present a novel convolutional neural network architecture to segment images from a series of short-axis cardiac magnetic resonance slices (CMRI). The proposed model is an extension of the U-net that embeds a cardiac shape prior and involves a loss function tailored to the cardiac anatomy. Since the shape prior is computed offline only once, the execution of our model is not limited by its calculation. Our system takes as input raw magnetic resonance images, requires no manual preprocessing or image cropping and is trained to segment the endocardium and epicardium of the left ventricle, the endocardium of the right ventricle, as well as the center of the left ventricle. Wit…
Efficient 3D Deep Learning for Myocardial Diseases Segmentation
Automated myocardial segmentation from late gadolinium enhancement magnetic resonance images (LGE-MRI) is a critical step in the diagnosis of cardiac pathologies such as ischemia and myocardial infarction. This paper proposes a deep learning framework for improved myocardial diseases segmentation. In the first step, we build an encoder-decoder segmentation network that generates myocardium and cavity segmentations from the whole volume, followed by a 3D U-Net based on Shape prior to identifying myocardial infarction and myocardium ventricular obstruction (MVO) segmentations from the encoder-decoder prediction. The proposed network achieves good segmentation performance, as computed by avera…
Local ex-vivo evaluation of the biomechanical properties of the ascending aortic aneurysms
Introduction Currently, surgical recommendations for aneurysm of the ascending aorta (AsAA) are based on the maximum diameter of the ascending aorta, but this factor is not reliable. Understanding the biomechanical properties of the aorta could lead to improve the prediction of the development of an AsAA. The aim of this study is to obtain the local patient specific elastic modulus distribution of the AsAA from a biaxial tensile test. Methods Pathologic ascending aortic tissue samples (n = 10) were obtained from patients undergoing elective surgical repair of AsAA ( Table 1 ). All the aortic wall samples were partitioned related to medial, posterior, lateral, and anterior quadrants. Each As…
Contribution of Augmented Reality to Minimally Invasive Computer-Assisted Cranial Base Surgery.
Cranial base procedures involve manipulation of small, delicate and complex structures in the fields of otology, rhinology, neurosurgery and maxillofacial surgery. Critical nerves and blood vessels are in close proximity of these structures. Augmented reality is an emerging technology that can revolutionize the cranial base procedures by providing supplementary anatomical and navigational information unified on a single display. However, the awareness and acceptance of possibilities of augmented reality systems in cranial base domain is fairly low. This article aims at evaluating the usefulness of augmented reality systems in cranial base surgeries and highlights the challenges that current…