arXiv subjects

Reza Razavi

Publications and source records attributed to Reza Razavi.

33 records · Page 2Linked to original sources

arXiv2021

An automated near-real time computational method for induction and treatment of scar-related ventricular tachycardias

Catheter ablation is currently the only curative treatment for scar-related ventricular tachycardias (VTs). However, not only are ablation procedures long, with relatively high risk, but success rates are punitively low, with frequent VT recurrence. Personalized in-silico approaches have the opportunity to address these limitations. However, state-of-the-art reaction diffusion (R-D) simulations of VT induction and subsequent circuits used for in-silico ablation target identification require long execution times, along with vast computational resources, which are incompatible with the clinical workflow. Here, we present the Virtual Induction and Treatment of Arrhythmias (VITA), a novel, rapid and fully automated computational approach that uses reaction-Eikonal methodology to induce VT and identify subsequent ablation targets. The rationale for VITA is based on finding isosurfaces associated with an activation wavefront that splits in the ventricles due to the presence of an isolated isthmus of conduction within the scar; once identified, each isthmus may be assessed for their vulnerability to sustain a reentrant circuit, and the corresponding exit site automatically identified for potential ablation targeting. VITA was tested on a virtual cohort of 7 post-infarcted porcine hearts and the results compared to R-D simulations. Using only a standard desktop machine, VITA could detect all scar-related VTs, simulating activation time maps and ECGs (for clinical comparison) as well as computing ablation targets in 48 minutes. The comparable VTs probed by the R-D simulations took 68.5 hours on 256 cores of high-performance computing infrastructure. The set of lesions computed by VITA was shown to render the ventricular model VT-free. VITA could be used in near real-time as a complementary modality aiding in clinical decision-making in the treatment of post-infarction VTs.

physics.med-ph↗

arXiv2021

Can non-specialists provide high quality gold standard labels in challenging modalities?

Probably yes. -- Supervised Deep Learning dominates performance scores for many computer vision tasks and defines the state-of-the-art. However, medical image analysis lags behind natural image applications. One of the many reasons is the lack of well annotated medical image data available to researchers. One of the first things researchers are told is that we require significant expertise to reliably and accurately interpret and label such data. We see significant inter- and intra-observer variability between expert annotations of medical images. Still, it is a widely held assumption that novice annotators are unable to provide useful annotations for use by clinical Deep Learning models. In this work we challenge this assumption and examine the implications of using a minimally trained novice labelling workforce to acquire annotations for a complex medical image dataset. We study the time and cost implications of using novice annotators, the raw performance of novice annotators compared to gold-standard expert annotators, and the downstream effects on a trained Deep Learning segmentation model's performance for detecting a specific congenital heart disease (hypoplastic left heart syndrome) in fetal ultrasound imaging.

cs.CV↗

arXiv2021

B-line Detection in Lung Ultrasound Videos: Cartesian vs Polar Representation

Lung ultrasound (LUS) imaging is becoming popular in the intensive care units (ICU) for assessing lung abnormalities such as the appearance of B-line artefacts as a result of severe dengue. These artefacts appear in the LUS images and disappear quickly, making their manual detection very challenging. They also extend radially following the propagation of the sound waves. As a result, we hypothesize that a polar representation may be more adequate for automatic image analysis of these images. This paper presents an attention-based Convolutional+LSTM model to automatically detect B-lines in LUS videos, comparing performance when image data is taken in Cartesian and polar representations. Results indicate that the proposed framework with polar representation achieves competitive performance compared to the Cartesian representation for B-line classification and that attention mechanism can provide better localization.

eess.IV↗

arXiv2021

Detecting Hypo-plastic Left Heart Syndrome in Fetal Ultrasound via Disease-specific Atlas Maps

Fetal ultrasound screening during pregnancy plays a vital role in the early detection of fetal malformations which have potential long-term health impacts. The level of skill required to diagnose such malformations from live ultrasound during examination is high and resources for screening are often limited. We present an interpretable, atlas-learning segmentation method for automatic diagnosis of Hypo-plastic Left Heart Syndrome (HLHS) from a single `4 Chamber Heart' view image. We propose to extend the recently introduced Image-and-Spatial Transformer Networks (Atlas-ISTN) into a framework that enables sensitising atlas generation to disease. In this framework we can jointly learn image segmentation, registration, atlas construction and disease prediction while providing a maximum level of clinical interpretability compared to direct image classification methods. As a result our segmentation allows diagnoses competitive with expert-derived manual diagnosis and yields an AUC-ROC of 0.978 (1043 cases for training, 260 for validation and 325 for testing).

eess.IV↗

arXiv2021

Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation

The subject of "fairness" in artificial intelligence (AI) refers to assessing AI algorithms for potential bias based on demographic characteristics such as race and gender, and the development of algorithms to address this bias. Most applications to date have been in computer vision, although some work in healthcare has started to emerge. The use of deep learning (DL) in cardiac MR segmentation has led to impressive results in recent years, and such techniques are starting to be translated into clinical practice. However, no work has yet investigated the fairness of such models. In this work, we perform such an analysis for racial/gender groups, focusing on the problem of training data imbalance, using a nnU-Net model trained and evaluated on cine short axis cardiac MR data from the UK Biobank dataset, consisting of 5,903 subjects from 6 different racial groups. We find statistically significant differences in Dice performance between different racial groups. To reduce the racial bias, we investigated three strategies: (1) stratified batch sampling, in which batch sampling is stratified to ensure balance between racial groups; (2) fair meta-learning for segmentation, in which a DL classifier is trained to classify race and jointly optimized with the segmentation model; and (3) protected group models, in which a different segmentation model is trained for each racial group. We also compared the results to the scenario where we have a perfectly balanced database. To assess fairness we used the standard deviation (SD) and skewed error ratio (SER) of the average Dice values. Our results demonstrate that the racial bias results from the use of imbalanced training data, and that all proposed bias mitigation strategies improved fairness, with the best SD and SER resulting from the use of protected group models.

cs.CV↗

arXiv2021

An 8 channel parallel transmit system with current sensor feedback for MRI-guided interventional applications

Background: Parallel transmit (pTx) has introduced many benefits to MRI with regard to decreased specific absorption rates and improved transmit field homogeneity, of particular importance in applications at higher magnetic field strengths. PTx has also been proposed as a solution to mitigating dangerous RF induced heating of elongated conductive devices such as those used in cardiac interventions. In this work we present a system that can augment a conventional scanner with pTx, in particular for use in interventional MRI for guidewire safety. Methods: The pTx system was designed to work in-line with a 1.5T MRI while the RF synthesis and imaging control was maintained on the host MR scanner. The add on pTx system relies on the RF transmit signal, unblanking pulse, and a protocol driven trigger from the scanner. The RF transmit was split into multiple fully modulated transmit signals to drive an array of custom transceiver coils. The performance of the 8-channel implementation was tested with regards to active and real-time control of RF induced currents on a standard guidewire, heating mitigation tests, and anatomical imaging in a sheep torso. Results: The pTx system was intended to update RF shims in real-time and it was demonstrated that the safe RF shim could be determined while the guidewire is moved. The anatomical imaging demonstrated that heart anatomy and neighbouring structures can be fully imaged with the pTx system inline. Conclusion: We have presented the design and performance of a real-time feedback control pTx system capable of adding such capabilities to a conventional MRI with the focus guidewire imaging in cardiac interventional MRI applications.

physics.med-ph↗

arXiv2021

Automatic Detection of B-lines in Lung Ultrasound Videos From Severe Dengue Patients

Lung ultrasound (LUS) imaging is used to assess lung abnormalities, including the presence of B-line artefacts due to fluid leakage into the lungs caused by a variety of diseases. However, manual detection of these artefacts is challenging. In this paper, we propose a novel methodology to automatically detect and localize B-lines in LUS videos using deep neural networks trained with weak labels. To this end, we combine a convolutional neural network (CNN) with a long short-term memory (LSTM) network and a temporal attention mechanism. Four different models are compared using data from 60 patients. Results show that our best model can determine whether one-second clips contain B-lines or not with an F1 score of 0.81, and extracts a representative frame with B-lines with an accuracy of 87.5%.

eess.IV↗

arXiv2020

Quality-aware semi-supervised learning for CMR segmentation

One of the challenges in developing deep learning algorithms for medical image segmentation is the scarcity of annotated training data. To overcome this limitation, data augmentation and semi-supervised learning (SSL) methods have been developed. However, these methods have limited effectiveness as they either exploit the existing data set only (data augmentation) or risk negative impact by adding poor training examples (SSL). Segmentations are rarely the final product of medical image analysis - they are typically used in downstream tasks to infer higher-order patterns to evaluate diseases. Clinicians take into account a wealth of prior knowledge on biophysics and physiology when evaluating image analysis results. We have used these clinical assessments in previous works to create robust quality-control (QC) classifiers for automated cardiac magnetic resonance (CMR) analysis. In this paper, we propose a novel scheme that uses QC of the downstream task to identify high quality outputs of CMR segmentation networks, that are subsequently utilised for further network training. In essence, this provides quality-aware augmentation of training data in a variant of SSL for segmentation networks (semiQCSeg). We evaluate our approach in two CMR segmentation tasks (aortic and short axis cardiac volume segmentation) using UK Biobank data and two commonly used network architectures (U-net and a Fully Convolutional Network) and compare against supervised and SSL strategies. We show that semiQCSeg improves training of the segmentation networks. It decreases the need for labelled data, while outperforming the other methods in terms of Dice and clinical metrics. SemiQCSeg can be an efficient approach for training segmentation networks for medical image data when labelled datasets are scarce.

eess.IV↗

arXiv2020

Automated Detection of Congenital Heart Disease in Fetal Ultrasound Screening

Prenatal screening with ultrasound can lower neonatal mortality significantly for selected cardiac abnormalities. However, the need for human expertise, coupled with the high volume of screening cases, limits the practically achievable detection rates. In this paper we discuss the potential for deep learning techniques to aid in the detection of congenital heart disease (CHD) in fetal ultrasound. We propose a pipeline for automated data curation and classification. During both training and inference, we exploit an auxiliary view classification task to bias features toward relevant cardiac structures. This bias helps to improve in F1-scores from 0.72 and 0.77 to 0.87 and 0.85 for healthy and CHD classes respectively.

eess.IV↗

arXiv2020

Automated quantification of myocardial tissue characteristics from native T1 mapping using neural networks with Bayesian inference for uncertainty-based quality-control

Tissue characterisation with CMR parametric mapping has the potential to detect and quantify both focal and diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T1 mapping in particular has shown promise as a useful biomarker to support diagnostic, therapeutic and prognostic decision-making in ischaemic and non-ischaemic cardiomyopathies. Convolutional neural networks with Bayesian inference are a category of artificial neural networks which model the uncertainty of the network output. This study presents an automated framework for tissue characterisation from native ShMOLLI T1 mapping at 1.5T using a Probabilistic Hierarchical Segmentation (PHiSeg) network. In addition, we use the uncertainty information provided by the PHiSeg network in a novel automated quality control (QC) step to identify uncertain T1 values. The PHiSeg network and QC were validated against manual analysis on a cohort of the UK Biobank containing healthy subjects and chronic cardiomyopathy patients. We used the proposed method to obtain reference T1 ranges for the left ventricular myocardium in healthy subjects as well as common clinical cardiac conditions. T1 values computed from automatic and manual segmentations were highly correlated (r=0.97). Bland-Altman analysis showed good agreement between the automated and manual measurements. The average Dice metric was 0.84 for the left ventricular myocardium. The sensitivity of detection of erroneous outputs was 91%. Finally, T1 values were automatically derived from 14,683 CMR exams from the UK Biobank. The proposed pipeline allows for automatic analysis of myocardial native T1 mapping and includes a QC process to detect potentially erroneous results. T1 reference values were presented for healthy subjects and common clinical cardiac conditions from the largest cohort to date using T1-mapping images.

eess.IV↗

arXiv2019

Assessing the Impact of Blood Pressure on Cardiac Function Using Interpretable Biomarkers and Variational Autoencoders

Maintaining good cardiac function for as long as possible is a major concern for healthcare systems worldwide and there is much interest in learning more about the impact of different risk factors on cardiac health. The aim of this study is to analyze the impact of systolic blood pressure (SBP) on cardiac function while preserving the interpretability of the model using known clinical biomarkers in a large cohort of the UK Biobank population. We propose a novel framework that combines deep learning based estimation of interpretable clinical biomarkers from cardiac cine MR data with a variational autoencoder (VAE). The VAE architecture integrates a regression loss in the latent space, which enables the progression of cardiac health with SBP to be learnt. Results on 3,600 subjects from the UK Biobank show that the proposed model allows us to gain important insight into the deterioration of cardiac function with increasing SBP, identify key interpretable factors involved in this process, and lastly exploit the model to understand patterns of positive and adverse adaptation of cardiac function.

cs.LG↗

arXiv2019

Robotic-assisted Ultrasound for Fetal Imaging: Evolution from Single-arm to Dual-arm System

The development of robotic-assisted extracorporeal ultrasound systems has a long history and a number of projects have been proposed since the 1990s focusing on different technical aspects. These aim to resolve the deficiencies of on-site manual manipulation of hand-held ultrasound probes. This paper presents the recent ongoing developments of a series of bespoke robotic systems, including both single-arm and dual-arm versions, for a project known as intelligent Fetal Imaging and Diagnosis (iFIND). After a brief review of the development history of the extracorporeal ultrasound robotic system used for fetal and abdominal examinations, the specific aim of the iFIND robots, the design evolution, the implementation details of each version, and the initial clinical feedback of the iFIND robot series are presented. Based on the preliminary testing of these newly-proposed robots on 42 volunteers, the successful and re-liable working of the mechatronic systems were validated. Analysis of a participant questionnaire indicates a comfortable scanning experience for the volunteers and a good acceptance rate to being scanned by the robots.

cs.RO↗

arXiv2019

A partition of unity approach to fluid mechanics and fluid-structure interaction

For problems involving large deformations of thin structures, simulating fluid-structure interaction (FSI) remains challenging largely due to the need to balance computational feasibility, efficiency, and solution accuracy. Overlapping domain techniques have been introduced as a way to combine the fluid-solid mesh conformity, seen in moving-mesh methods, without the need for mesh smoothing or re-meshing, which is a core characteristic of fixed mesh approaches. In this work, we introduce a novel overlapping domain method based on a partition of unity approach. Unified function spaces are defined as a weighted sum of fields given on two overlapping meshes. The method is shown to achieve optimal convergence rates and to be stable for steady-state Stokes, Navier-Stokes, and ALE Navier-Stokes problems. Finally, we present results for FSI in the case of a 2D mock aortic valve simulation. These initial results point to the potential applicability of the method to a wide range of FSI applications, enabling boundary layer refinement and large deformations without the need for re-meshing or user-defined stabilization.

cs.CE↗

arXiv2018

Fetal whole-heart 4D imaging using motion-corrected multi-planar real-time MRI

Purpose: To develop a MRI acquisition and reconstruction framework for volumetric cine visualisation of the fetal heart and great vessels in the presence of maternal and fetal motion. Methods: Four-dimensional depiction was achieved using a highly-accelerated multi-planar real-time balanced steady state free precession acquisition combined with retrospective image-domain techniques for motion correction, cardiac synchronisation and outlier rejection. The framework was evaluated and optimised using a numerical phantom, and evaluated in a study of 20 mid- to late-gestational age human fetal subjects. Reconstructed cine volumes were evaluated by experienced cardiologists and compared with matched ultrasound. A preliminary assessment of flow-sensitive reconstruction using the velocity information encoded in the phase of dynamic images is included. Results: Reconstructed cine volumes could be visualised in any 2D plane without the need for highly-specific scan plane prescription prior to acquisition or for maternal breath hold to minimise motion. Reconstruction was fully automated aside from user-specified masks of the fetal heart and chest. The framework proved robust when applied to fetal data and simulations confirmed that spatial and temporal features could be reliably recovered. Expert evaluation suggested the reconstructed volumes can be used for comprehensive assessment of the fetal heart, either as an adjunct to ultrasound or in combination with other MRI techniques. Conclusion: The proposed methods show promise as a framework for motion-compensated 4D assessment of the fetal heart and great vessels.

physics.med-ph↗

arXiv2018

Mind the gap: quantification of incomplete ablation patterns after pulmonary vein isolation using minimum path search

Pulmonary vein isolation (PVI) is a common procedure for the treatment of atrial fibrillation (AF). A successful isolation produces a continuous lesion (scar) completely encircling the veins that stops activation waves from propagating to the atrial body. Unfortunately, the encircling lesion is often incomplete, becoming a combination of scar and gaps of healthy tissue. These gaps are potential causes of AF recurrence, which requires a redo of the isolation procedure. Late-gadolinium enhanced cardiac magnetic resonance (LGE-CMR) is a non-invasive method that may also be used to detect gaps, but it is currently a time-consuming process, prone to high inter-observer variability. In this paper, we present a method to semi-automatically identify and quantify ablation gaps. Gap quantification is performed through minimum path search in a graph where every node is a scar patch and the edges are the geodesic distances between patches. We propose the Relative Gap Measure (RGM) to estimate the percentage of gap around a vein, which is defined as the ratio of the overall gap length and the total length of the path that encircles the vein. Additionally, an advanced version of the RGM has been developed to integrate gap quantification estimates from different scar segmentation techniques into a single figure-of-merit. Population-based statistical and regional analysis of gap distribution was performed using a standardised parcellation of the left atrium. We have evaluated our method on synthetic and clinical data from 50 AF patients who underwent PVI with radiofrequency ablation. The population-based analysis concluded that the left superior PV is more prone to lesion gaps while the left inferior PV tends to have less gaps (p<0.05 in both cases), in the processed data. This type of information can be very useful for the optimization and objective assessment of PVI interventions.

cs.CE↗