Cardiac MRI of patients with implanted electrical cardiac devices

Chest X-ray Foreign Objects Detection Using Artificial Intelligence

Diagnostic imaging has become an integral part of the healthcare system. In recent years, scientists around the world have been working on artificial intelligence-based tools that help in achieving better and faster diagnoses. Their accuracy is crucial for successful treatment, especially for imaging diagnostics. This study used a deep convolutional neural network to detect four categories of objects on digital chest X-ray images. The data were obtained from the publicly available National Institutes of Health (NIH) Chest X-ray (CXR) Dataset. In total, 112,120 CXRs from 30,805 patients were manually checked for foreign objects: vascular port, shoulder endoprosthesis, necklace, and implantable cardioverter-defibrillator (ICD). Then, they were annotated with the use of a computer program, and the necessary image preprocessing was performed, such as resizing, normalization, and cropping. The object detection model was trained using the You Only Look Once v8 architecture and the Ultralytics framework. The results showed not only that the obtained average precision of foreign object detection on the CXR was 0.815 but also that the model can be useful in detecting foreign objects on the CXR images. Models of this type may be used as a tool for specialists, in particular, with the growing popularity of radiology comes an increasing workload. We are optimistic that it could accelerate and facilitate the work to provide a faster diagnosis.

Magnetic resonance in patients with cardiovascular devices. SEC-GT CRMTC/SEC-Heart Rhythm Association/SERAM/SEICAT consensus document

Magnetic resonance has become a first-line imaging modality in various clinical scenarios. The number of patients with different cardiovascular devices, including cardiac implantable electronic devices, has increased exponentially. Although there have been reports of risks associated with exposure to magnetic resonance in these patients, the clinical evidence now supports the safety of performing these studies under specific conditions and following recommendations to minimize possible risks. This document was written by the Working Group on Cardiac Magnetic Resonance Imaging and Cardiac Computed Tomography of the Spanish Society of Cardiology (SEC-GT CRMTC), the Heart Rhythm Association of the Spanish Society of Cardiology (SEC-Heart Rhythm Association), the Spanish Society of Medical Radiology (SERAM), and the Spanish Society of Cardiothoracic Imaging (SEICAT). The document reviews the clinical evidence available in this field and establishes a series of recommendations so that patients with cardiovascular devices can safely access this diagnostic tool.

Magnetic resonance in patients with cardiovascular devices. SEC-GT CRMTC/SEC-Heart Rhythm Association/SERAM/SEICAT consensus document

Magnetic resonance has become a first-line imaging modality in various clinical scenarios. The number of patients with different cardiovascular devices, including cardiac implantable electronic devices, has increased exponentially. Although there have been reports of risks associated with exposure to magnetic resonance in these patients, the clinical evidence now supports the safety of performing these studies under specific conditions and following recommendations to minimize possible risks. This document was written by the Working Group on Cardiac Magnetic Resonance Imaging and Cardiac Computed Tomography of the Spanish Society of Cardiology (SEC-GT CRMTC), the Heart Rhythm Association of the Spanish Society of Cardiology (SEC-Heart Rhythm Association), the Spanish Society of Medical Radiology (SERAM), and the Spanish Society of Cardiothoracic Imaging (SEICAT). The document reviews the clinical evidence available in this field and establishes a series of recommendations so that patients with cardiovascular devices can safely access this diagnostic tool.

Estimation of Cardiac Short Axis Slice Levels with a Cascaded Deep Convolutional and Recurrent Neural Network Model

Automatic identification of short axis slice levels in cardiac magnetic resonance imaging (MRI) is important in efficient and precise diagnosis of cardiac disease based on the geometry of the left ventricle. We developed a combined model of convolutional neural network (CNN) and recurrent neural network (RNN) that takes a series of short axis slices as input and predicts a series of slice levels as output. Each slice image was labeled as one of the following five classes: out-of-apical, apical, mid, basal, and out-of-basal levels. A variety of multi-class classification models were evaluated. When compared with the CNN-alone models, the cascaded CNN-RNN models resulted in higher mean F1-score and accuracy. In our implementation and testing of four different baseline networks with different combinations of RNN modules, MobileNet as the feature extractor cascaded with a two-layer long short-term memory (LSTM) network produced the highest scores in four of the seven evaluation metrics, i.e., five F1-scores, area under the curve (AUC), and accuracy. Our study indicates that the cascaded CNN-RNN models are superior to the CNN-alone models for the classification of short axis slice levels in cardiac cine MR images.

Magnetic Resonance Imaging Safety in Patients with Cardiac Implantable Electronic Devices

High strength magnetic and electric fields used in magnetic resonance imaging (MRI) render images with unmatched soft tissue contrast. These imaging attributes have made MRI an increasingly preferred diagnostic tool in many medical conditions. Initially there was substantial concern regarding the safety of performing these imaging studies in patients with cardiac implantable electronic devices (CIEDs), which have the potential to be affected by the intense electric and magnetic fields of the MRI. More recently, there has been increasing evidence that MRI can be performed safely in patients with devices that have not been specifically labelled by regulatory agencies for use in an MRI environment (MRI nonconditional devices), which has allowed the Centers for Medicare and Medicaid Services (CMS) to start providing reimbursement for MRIs of patients with MRI nonconditional devices. For CMS to reimburse scans, a rigorous protocol must be followed, which recognizes that there are still potential adverse effects that can be mitigated by appropriate procedures. In this review we will survey the initial experiences and efforts to understand the magnitude of risk for device malfunction and harm, as well as current efforts to minimize the potential risks of MRI effects on devices and leads (heating, device movement, lead dislodgement, and device malfunction, the latter including inhibition of pacing and generation of arrhythmias).

Introduction of Cardiac Magnetic Resonance Imaging in Kosovo: First Fifty Consecutive Patients Registry Report

BACKGROUND: Cardiac magnetic resonance (CMR) as advanced diagnostic tool for the heart has been introduced in our institution since September 2019. AIM: We report on the first fifty consecutive patients using this imaging modality. METHODS AND MATERIALS: Strict protocol for CMR procedure, imaging quality assessment, contraindications, and informed consent were established. Patients selected for CMR were enrolled in a prospective registry. Visualizing the heart chambers, heart muscle and heart valves, resulted in acquiring complex imaging of the heart structure and function. When applicable, patients received gadolinium contrast agent for Late Gadolinium Enhancement (LGE). Adenosine was used for stress induced myocardial perfusion study. In this study, we report on the initial CMR procedures in the first 15 months. RESULTS: The age of the patients ranges from 17 to 82 and the number of male and female patients was well balanced. No absolute contraindications were met in any patient. Relative contraindications were noted but did not prevent from performing the scan. Different cardiac pathologies were encountered in the examined patients. Most common was the ischemic heart disease – 19 (38%). We had 15 (30%) out of 46 (92%) CMR procedures with LGE showing fibrotic scaring. Quality image assessment was scaled from poor to excellent. Most of the assessments were graded very good and good (46% and 48%), no poor, and very poor noted. CONCLUSION: CMR has been successfully introduced in Kosovo as excellent imaging tool for diagnosing and characterizing a nearly exhaustive spectrum of heart diseases.

Magnetic resonance imaging in children with implants

As access to MRI in pediatrics increases, the radiologist needs to become acquainted with the basic principles of MRI safety. As part of the image acquisition, the static magnetic field, gradient system, and the radiofrequency transmit-receive coil interact with medical and non-medical implants and can result in serious injury. The main stage of risk triage is based on the determination of whether the implant is MRI-safe, conditional, unsafe or unknown. Guiding principles include the strict adherence to manufacturer specifications for MRI-conditional implants and the assumption that an unknown implant is MR-unsafe. In this article we review considerations for common medical implants encountered in pediatrics including ventriculoperitoneal shunts, orthopedic hardware, orthodontic hardware, pacemakers, vascular stents, vagal nerve stimulators and cochlear implants. Finally, we review a set of high-yield considerations, including the non-communicative patient (sedated or non-verbal), susceptibility artifacts from unclear source, and the approach to an unknown implant.

Image similarity-based cardiac rhythm device identification from X-rays using feature point matching

AIMS

Identifying the manufacturer and the type of cardiac implantable electronic devices (CIEDs) is important in emergent clinical settings. Recent studies have illustrated that artificial neural network models can successfully recognize CIEDs from chest X-ray images. However, all existing methods require a vast amount of medical data to train the classification model. Here, we have proposed a novel method to retrieve an identical CIED image from an image database by employing the feature point matching algorithm.

METHODS AND RESULTS

A total of 653 unique X-ray images from 456 patients who visited our pacemaker clinic between April 2012 and August 2020 were collected. The device images were manually square-shaped, and was thereafter resized to 224 × 224 pixels. A scale-invariant feature transform (SIFT) algorithm was used to extract the keypoints from the query image and reference images. Paired feature points were selected via brute-force matching, and the average Euclidean distance was calculated. The image with the shortest average distance was defined as the most similar image. The classification performance was indicated by accuracy, precision, recall, and F1-score for detecting the manufacturers and model groups, respectively. The average accuracy, precision, recall, and F-1 score for the manufacturer classification were 97.0%, 0.97, 0.96, and 0.96, respectively. For the model classification task, the average accuracy, precision, recall, and F-1 score were 93.2%, 0.94, 0.92, and 0.93, respectively, all of which were higher than those of the previously reported machine learning models.

CONCLUSION

Feature point matching is useful for identifying CIEDs from X-ray images.

Application of physics-based flow models in cardiovascular medicine: Current practices and challenges

Personalized physics-based flow models are becoming increasingly important in cardiovascular medicine. They are a powerful complement to traditional methods of clinical decision-making and offer a wealth of physiological information beyond conventional anatomic viewing using medical imaging data. These models have been used to identify key hemodynamic biomarkers, such as pressure gradient and wall shear stress, which are associated with determining the functional severity of cardiovascular diseases. Importantly, simulation-driven diagnostics can help researchers understand the complex interplay between geometric and fluid dynamic parameters, which can ultimately improve patient outcomes and treatment planning. The possibility to compute and predict diagnostic variables and hemodynamics biomarkers can therefore play a pivotal role in reducing adverse treatment outcomes and accelerate development of novel strategies for cardiovascular disease management.

Making MRI available for patients with cardiac implantable electronic devices: growing need and barriers to change

Abstract

More than half of us will need a magnetic resonance imaging (MRI) scan in our lifetimes. MRI is an unmatched diagnostic test for an expanding range of indications including neurological and musculoskeletal disorders, cancer diagnosis, and treatment planning. Unfortunately, patients with cardiac pacemakers or defibrillators have historically been prevented from having MRI because of safety concerns. This results in delayed diagnoses, more invasive investigations, and increased cost. Major developments have addressed this—newer devices are designed to be safe in MRI machines under specific conditions, and older legacy devices can be scanned provided strict protocols are followed. This service however remains difficult to deliver sustainably worldwide: MRI provision remains grossly inadequate because patients are less likely to be referred, and face difficulties accessing services even when referred. Barriers still exist but are no longer technical. These include logistical hurdles (poor cardiology and radiology interaction at physician and technician levels), financial incentives (re-imbursement is either absent or fails to acknowledge the complexity), and education (physicians self-censor MRI requests). This article therefore highlights the recent changes in the clinical, logistical, and regulatory landscape. The aim of the article is to enable and encourage healthcare providers and local champions to build MRI services urgently for cardiac device patients, so that they may benefit from the same access to MRI as everyone else.

Key Points

• There is now considerable evidence that MRI can be provided safely to patients with cardiac implantable electronic devices (CIEDs). However, the volume of MRI scans delivered to patients with CIEDs is fifty times lower than that of the estimated need, and patients are approximately fifty times less likely to be referred.

• Because scans for this patient group are frequently for cancer diagnosis and treatment planning, MRI services need to develop rapidly, but the barriers are no longer technical.

• New services face logistical, educational, and financial hurdles which can be addressed effectively to establish a sustainable service at scale.

[Pacemaker and MRI in clinical practice]

The number of cardiac pacemaker wearers is continuously increasing in Germany as well as worldwide. The probability of indications for a magnetic resonance imaging (MRI) examination during the lifetime is approximately 50-75% for every person. An MRI examination is nowadays possible for pacemaker wearers under certain conditions. Due to the technical developments during the last 10 years certain MRI-conditional pacemakers are available. The recommendations of the German and American medical specialist societies currently allow an MRI examination in patients with conventional pacemakers beyond the approval conditions (off-label use) under prespecified conditions, based on the study data. This article summarizes the information on conditions of use and reprogramming strategies as well as on the study situation for the clinical routine.

Radiation-free CMR diagnostic heart catheterization in children

BACKGROUND

Children with heart disease may require repeated X-Ray cardiac catheterization procedures, are more radiosensitive, and more likely to survive to experience oncologic risks of medical radiation. Cardiovascular magnetic resonance (CMR) is radiation-free and offers information about structure, function, and perfusion but not hemodynamics. We intend to perform complete radiation-free diagnostic right heart catheterization entirely using CMR fluoroscopy guidance in an unselected cohort of pediatric patients; we report the feasibility and safety.

METHODS

We performed 50 CMR fluoroscopy guided comprehensive transfemoral right heart catheterizations in 39 pediatric (12.7 ± 4.7 years) subjects referred for clinically indicated cardiac catheterization. CMR guided catheterizations were assessed by completion (success/failure), procedure time, and safety events (catheterization, anesthesia). Pre and post CMR body temperature was recorded. Concurrent invasive hemodynamic and diagnostic CMR data were collected.

RESULTS

During a twenty-two month period (3/2015 - 12/2016), enrolled subjects had the following clinical indications: post-heart transplant 33%, shunt 28%, pulmonary hypertension 18%, cardiomyopathy 15%, valvular heart disease 3%, and other 3%. Radiation-free CMR guided right heart catheterization attempts were all successful using passive catheters. In two subjects with septal defects, right and left heart catheterization were performed. There were no complications. One subject had six such procedures. Most subjects (51%) had undergone multiple (5.5 ± 5) previous X-Ray cardiac catheterizations. Retained thoracic surgical or transcatheter implants (36%) did not preclude successful CMR fluoroscopy heart catheterization. During the procedure, two subjects were receiving vasopressor infusions at baseline because of poor cardiac function, and in ten procedures, multiple hemodynamic conditions were tested.

CONCLUSIONS

Comprehensive CMR fluoroscopy guided right heart catheterization was feasible and safe in this small cohort of pediatric subjects. This includes subjects with previous metallic implants, those requiring continuous vasopressor medication infusions, and those requiring pharmacologic provocation. Children requiring multiple, serial X-Ray cardiac catheterizations may benefit most from radiation sparing. This is a step toward wholly CMR guided diagnostic (right and left heart) cardiac catheterization and future CMR guided cardiac intervention.

TRIAL REGISTRATION

ClinicalTrials.gov NCT02739087 registered February 17, 2016.

MRI of patients with implanted cardiac devices

Cardiac implanted electronic devices (CIEDs) have historically been regarded as a contraindication for performing magnetic resonance imaging (MRI), limiting the availability of this exam for large numbers of patients who may have otherwise benefited from the unique diagnostic capabilities of MRI. Interactions between CIEDs and the magnetic field associated with MRI systems have been documented, and include potential effects on CIED function, lead heating, and force/torque on the generator. Several device manufacturers have developed "MR-Conditional" CIEDs with specific hardware and software design changes to optimize the device for the MR environment. However, a substantial body of evidence has been accumulating that suggests that MRI may be safely performed in patients with either conditional or nonconditional CIEDs. Institutional policies and procedures, including preexam screening and assessment by skilled electrophysiology personnel and intraexam monitoring, allow MRI to be safely performed in CIED patients, as evidenced by at least two, large multicenter prospective studies and multiple smaller, single-institution studies. Cross-departmental collaboration and a robust safety infrastructure at sites that perform MRI should allow for the safe imaging of CIED patients who have a clinical indication for the study, regardless of the conditionality status of the device.

LEVEL OF EVIDENCE

5 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2018;47:595-603.

Magnetic resonance examination of patients with implanted pacemakers: An evaluation of magnetic field gradients slew rate

Performing safe magnetic resonance imaging of patients with "MR conditional" pacemakers needs to meet some specific restrictions. One of these is related to the slew rate (SR) parameter, defined as the speed of magnetic field gradients rising up to their required strengths. Unfortunately, SR values cannot be easily checked at the tomograph console. The present work provides an accurate evaluation of the maximum SR for a set of widely used clinical MR sequences. The experimental approach is based on indirect measurement of time-varying spatial magnetic field gradients. All MR sequences evaluated match safety SR prescriptions. Moreover, an appropriate choice of sequence scan parameters defines some optimized scan protocols tailored for the tomograph considered in the present study. Bioelectromagnetics. 38:307-314, 2017. © 2017 Wiley Periodicals, Inc.

A Practical Guide to MR Imaging Safety: What Radiologists Need to Know

Magnetic resonance (MR) imaging can provide critical diagnostic and anatomic information while avoiding the use of ionizing radiation, but it has a unique set of safety risks associated with its reliance on large static and changing magnetic fields, high-powered radiofrequency coil systems, and exogenous contrast agents. It is crucial for radiologists to understand these risks and how to mitigate them to protect themselves, their colleagues, and their patients from avoidable harm and to comply with safety regulations at MR imaging sites. Basic knowledge of MR imaging physics and hardware is necessary for radiologists to understand the origin of safety regulations and to avoid common misconceptions that could compromise safety. Each of the components of the MR imaging unit can be a factor in injuries to patients and personnel. Safety risks include translational force and torque, projectile injury, excessive specific absorption rate, burns, peripheral neurostimulation, interactions with active implants and devices, and acoustic injury. Standards for MR imaging device safety terminology were first issued in 2005 and are required by the U.S. Food and Drug Administration, with devices labeled as "MR safe," "MR unsafe," or "MR conditional." MR imaging contrast agent safety is also discussed. Additional technical and safety policies relate to pediatric, unconscious, incapacitated, or pregnant patients and pregnant imaging personnel. Division of the MR imaging environment into four distinct, clearly labeled zones--with progressive restriction of entry and increased supervision for higher zones--is a mandatory and key aspect in avoidance of MR imaging-related accidents. All MR imaging facilities should have a documented plan to handle emergencies within zone IV, including cardiac arrest or code, magnet quench, and fires. Policies from the authors' own practice are provided for additional reference. Online supplemental material is available for this article.

Magnetic resonance imaging in patients with a subcutaneous implantable cardioverter-defibrillator

Aims

Our aim was to evaluate the potential for safely imaging patients with a new type of implantable cardioverter-defibrillator called the subcutaneous implantable cardioverter-defibrillator (S-ICD) in a 1.5 T magnetic resonance imaging (MRI) scanner. With the increasing number of patients with cardiac implantable devices who are indicated for MRI, there is a growing need for establishing MRI compatibility of cardiac implantable devices.

Methods and Results

Patients with implanted S-ICD systems underwent one or more types of anatomical MRI scans. The S-ICD was programmed off and patients were monitored throughout the imaging procedure. Device function was evaluated pre- and post-scan. Patients were asked to report immediately any pain, torqueing movement, or heating sensation in the area of the pocket or electrode. Fifteen patients underwent a total of 22 examinations at 1.5 T. Scans included brain, spine, knee, and heart. Two patients were re-scanned due to complaints of heating over the can during lumbar scans, which was caused by a thermistor probe placed on the skin to measure skin temperature. All the remaining scans occurred without incident. No evidence of device malfunction was observed.

Conclusion

This study is the first to domonstrate the feasibility of exposing S-ICD patients to MRI using the scanning and monitoring protocol described. More data are required to support S-ICD as a MRI conditional device.

Images as drivers of progress in cardiac computational modelling

Computational models have become a fundamental tool in cardiac research. Models are evolving to cover multiple scales and physical mechanisms. They are moving towards mechanistic descriptions of personalised structure and function, including effects of natural variability. These developments are underpinned to a large extent by advances in imaging technologies. This article reviews how novel imaging technologies, or the innovative use and extension of established ones, integrate with computational models and drive novel insights into cardiac biophysics. In terms of structural characterization, we discuss how imaging is allowing a wide range of scales to be considered, from cellular levels to whole organs. We analyse how the evolution from structural to functional imaging is opening new avenues for computational models, and in this respect we review methods for measurement of electrical activity, mechanics and flow. Finally, we consider ways in which combined imaging and modelling research is likely to continue advancing cardiac research, and identify some of the main challenges that remain to be solved.

Cardiac imaging in the geriatric population: what do we think we know, and what do we need to learn?

Cardiac imaging plays an important role in coronary artery disease (CAD), congestive heart failure (HF) and valvular heart disease (VHD) in the elderly. Imaging defines the structure and function of the cardiac system, refining the understanding of patients' anatomy and physiology and informing a host of clinical care decisions, including prognosis. Yet there is a paucity of evidence to guide the rational use of many imaging modalities in patients of advanced age, a population with considerable clinical heterogeneity, high prevalence and burden of cardiovascular disease (CVD) and atypical presentations of CVD. This paper discusses important considerations for cardiac imaging for older adults, particularly in regard to CAD, VHD and HF, and then presents domains for future research to produce data that would inform clinical care guidelines, appropriate use criteria and imaging lab protocols to address the unique needs of the fast-growing elderly population.