Assessing Risk and Predicting Outcomes in Coronary Artery Disease: Physiology, Anatomy, or Biology?

Cardiovascular imaging has been able to demonstrate its importance identifying subjects at risk for future cardiac events. There is extensive evidence demonstrating that anatomic, physiologic, and biologic data can successfully risk stratify patients. A plethora of biomarkers predictive of patients’ risk have been identified. Although cardiovascular imaging modalities are capable of patient risk stratification, whether they are cost effective over clinical, historical, and biochemical data is uncertain. The incremental value provided by stress positron emission tomography and single photon emission CT has been extensively demonstrated. In addition, an increasing body of evidence supports the concept that coronary CT angiography is also able to stratify patients in regard to their risk of future cardiovascular events. The availability of hybrid myocardial perfusion imaging/CT technology permits simultaneous acquisition of anatomic, functional, structural information, and the potential for use of molecular techniques. The future application of these modalities will require extending the risk stratification paradigm to the identification of optimal patient management.     

Breakthroughs in modern cancer therapy and elusive cardiotoxicity: Critical research‐practice gaps,challenges, and insights

To date, five cancer treatment modalities have been defined. The three traditional modalities of cancer treatment are surgery, radiotherapy, and conventional chemotherapy, and the two modern modalities include molecularly targeted therapy (the fourth modality) and immunotherapy (the fifth modality). The cardiotoxicity associated with conventional chemotherapy and radiotherapy is well known. Similar adverse cardiac events are resurging with the fourth modality. Aside from the conventional and newer targeted agents, even the most newly developed, immune‐based therapeutic modalities of anticancer treatment (the fifth modality), e.g., immune checkpoint inhibitors and chimeric antigen receptor (CAR) T‐cell therapy, have unfortunately led to potentially lethal cardiotoxicity in patients. Cardiac complications represent unresolved and potentially life‐threatening conditions in cancer survivors, while effective clinical management remains quite challenging. As a consequence, morbidity and mortality related to cardiac complications now threaten to offset some favorable benefits of modern cancer treatments in cancer‐related survival, regardless of the oncologic prognosis. This review focuses on identifying critical research‐practice gaps, addressing real‐world challenges and pinpointing real‐time insights in general terms under the context of clinical cardiotoxicity induced by the fourth and fifth modalities of cancer treatment. The information ranges from basic science to clinical management in the field of cardio‐oncology and crosses the interface between oncology and onco‐pharmacology. The complexity of the ongoing clinical problem is addressed at different levels. A better understanding of these research‐practice gaps may advance research initiatives on the development of mechanism‐based diagnoses and treatments for the effective clinical management of cardiotoxicity.     

Three-dimensional Echocardiographic Analysis of left Atrial size and Volumetric Function — Clinical Implications and Comparison with Other Imaging Modalities

Since a number of imaging approaches are used to measure left atrial volume, it is important to know whether values obtained by different imaging modalities or by the same imaging modality using different measurement algorithms are interchangeable. This is particularly relevant for follow-up examinations. The advent of real-time full-volume three-dimensional echocardiography allows rapid measurement of chamber volume without making geometric assumptions. Furthermore, the semiautomatic methods allow repeat measurement of volume changes during the cardiac cycle thus permitting volumetric quantification of atrial function. Although three-dimensional imaging modalities including magnetic resonance imaging and computed tomography are considered as non-invasive reference methods for cardiac chamber volume determination they are less available, more costly, more time consuming and have other specific limitations, and therefore are less suitable for atrial volume and function measurement in daily clinical practice. In this article we provide a critical review of available literature validating and comparing different non-invasive three-dimensional imaging modalities and measurement algorithms used for determination of left atrial volumes with special reference to three- dimensional echocardiography.     

Cost-Effectiveness of Cardiac Magnetic Resonance

In the context of the dramatic growth of health care, the costs associated with cardiovascular imaging have come under increasing scrutiny. Increasingly, the clinical use of cardiovascular imaging requires justification with respect to both its clinical value and cost-effectiveness. Indeed, the use of cardiovascular imaging has been questioned due to a lack of evidence that its inclusion in a testing strategy will result in enhanced patient benefit. To this end, we review the basic principles and methods of cost-effectiveness analyses as applied to cardiovascular imaging. Further, we review cost-effectiveness studies of cardiac MR imaging to determine the depth of available evidence supporting this modality.     

Imaging in population science: cardiovascular magnetic resonance in 100,000 participants of UK Biobank - rationale,challenges and approaches

UK Biobank is a prospective cohort study with 500,000 participants aged 40 to 69. Recently an enhanced imaging study received funding. Cardiovascular magnetic resonance (CMR) will be part of a multi-organ, multi-modality imaging visit in 3–4 dedicated UK Biobank imaging centres that will acquire and store imaging data from 100,000 participants (subject to successful piloting). In each of UK Biobank’s dedicated bespoke imaging centres, it is proposed that 15–20 participants will undergo a 2 to 3 hour visit per day, seven days a week over a period of 5–6 years. The imaging modalities will include brain MRI at 3 Tesla, CMR and abdominal MRI at 1.5 Tesla, carotid ultrasound and DEXA scans using carefully selected protocols. We reviewed the rationale, challenges and proposed approaches for concise phenotyping using CMR on such a large scale. Here, we discuss the benefits of this imaging study and review existing and planned population based cardiovascular imaging in prospective cohort studies. We will evaluate the CMR protocol, feasibility, process optimisation and costs. Procedures for incidental findings, quality control and data processing and analysis are also presented. As is the case for all other data in the UK Biobank resource, this database of images and related information will be made available through UK Biobank’s Access Procedures to researchers (irrespective of their country of origin and whether they are academic or commercial) for health-related research that is in the public interest.     

Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data

Fusing multi-modality data is crucial for accurate identification of brain disorder as different modalities can provide complementary perspectives of complex neurodegenerative disease. However, there are at least four common issues associated with the existing fusion methods. First, many existing fusion methods simply concatenate features from each modality without considering the correlations among different modalities. Second, most existing methods often make prediction based on a single classifier, which might not be able to address the heterogeneity of the Alzheimer’s disease (AD) progression. Third, many existing methods often employ feature selection (or reduction) and classifier training in two independent steps, without considering the fact that the two pipelined steps are highly related to each other. Forth, there are missing neuroimaging data for some of the participants (e.g., missing PET data), due to the participants’ “no-show” or dropout. In this paper, to address the above issues, we propose an early AD diagnosis framework via novel multi-modality latent space inducing ensemble SVM classifier. Specifically, we first project the neuroimaging data from different modalities into a latent space, and then map the learned latent representations into the label space to learn multiple diversified classifiers. Finally, we obtain the more reliable classification results by using an ensemble strategy. More importantly, we present a Complete Multi-modality Latent Space (CMLS) learning model for complete multi-modality data and also an Incomplete Multi-modality Latent Space (IMLS) learning model for incomplete multi-modality data. Extensive experiments using the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset have demonstrated that our proposed models outperform other state-of-the-art methods.     

View-aligned hypergraph learning for Alzheimer’s disease diagnosis with incomplete multi-modality data

Effectively utilizing incomplete multi-modality data for the diagnosis of Alzheimer’s disease (AD) and its prodrome (i.e., mild cognitive impairment, MCI) remains an active area of research. Several multi-view learning methods have been recently developed for AD/MCI diagnosis by using incomplete multi-modality data, with each view corresponding to a specific modality or a combination of several modalities. However, existing methods usually ignore the underlying coherence among views, which may lead to sub-optimal learning performance. In this paper, we propose a view-aligned hypergraph learning (VAHL) method to explicitly model the coherence among views. Specifically, we first divide the original data into several views based on the availability of different modalities and then construct a hypergraph in each view space based on sparse representation. A view-aligned hypergraph classification (VAHC) model is then proposed, by using a view-aligned regularizer to capture coherence among views. We further assemble the class probability scores generated from VAHC, via a multi-view label fusion method for making a final classification decision. We evaluate our method on the baseline ADNI-1 database with 807 subjects and three modalities (i.e., MRI, PET, and CSF). Experimental results demonstrate that our method outperforms state-of-the-art methods that use incomplete multi-modality data for AD/MCI diagnosis.     

Hybrid SPECT-CT and PET-CT: Current Concepts and Developments

Cardiac hybrid imaging combines different modalities in order to obtain complementary anatomical and functional information in a single imaging study. Coronary CT angiography (CTA) and myocardial perfusion imaging with single photon emission computed tomography (SPECT) or positron emission tomography (PET) are established noninvasive modalities for the diagnosis of coronary artery disease (CAD). Hybrid SPECT-CT or PET-CT is a promising tool for evaluation of CAD since it allows visualization of coronary atherosclerotic lesions and their consequences on myocardial blood flow in a single study. This appears to offer superior diagnostic accuracy for the detection of flow-limiting stenosis in patients with intermediate risk for CAD as compared with stand-alone imaging, especially by improving the positive predictive value. This article will review the concepts and currently available clinical experiences from cardiac hybrid imaging as well as discuss potential future applications.     

Cardiac Masses on Cardiac CT: A Review

Cardiac masses are rare entities that can be broadly categorized as either neoplastic or non-neoplastic. Neoplastic masses include benign and malignant tumors. In the heart, metastatic tumors are more common than primary malignant tumors. Whether incidentally found or diagnosed as a result of patients’ symptoms, cardiac masses can be identified and further characterized by a range of cardiovascular imaging options. While echocardiography remains the first-line imaging modality, cardiac computed tomography (cardiac CT) has become an increasingly utilized modality for the assessment of cardiac masses, especially when other imaging modalities are non-diagnostic or contraindicated. With high isotropic spatial and temporal resolution, fast acquisition times, and multiplanar image reconstruction capabilities, cardiac CT offers an alternative to cardiovascular magnetic resonance imaging in many patients. Additionally, cardiac masses may be incidentally discovered during cardiac CT for other reasons, requiring imagers to understand the unique features of a diverse range of cardiac masses. Herein, we define the characteristic imaging features of commonly encountered and selected cardiac masses and define the role of cardiac CT among noninvasive imaging options.     

Cardiac evaluation.

Over the past decade there has been a dramatic, rapid development of new imaging modalities used in the evaluation of the cardiac patient. These newer techniques are frequently complex and specialized in their application and interpretation. Nonetheless, the prevalence of cardiac disease in the United States, and the wide application of these diagnostic tests, mandate that the well-rounded clinician has a basic understanding of the utility of these diagnostic modalities. Unfortunately, the burgeoning field of cardiac imaging seems at times to overshadow our most important basic diagnostic tools, namely, the history, physical exam, chest radiograph, and electrocardiogram (ECG). This review will attempt to impart a basic understanding of the newer cardiac diagnostic tests and their utility in various disease states. Emphasis on the importance of the basic clinical exam and the precise integration of specific diagnostic tests into the cardiac evaluation will be emphasized. The article will deliver a basic review of exercise treadmill testing, echocardiography, radionuclide imaging techniques, magnetic resonance imaging, and cardiac catheterization. It is hoped that this review will impart to the noncardiologist clinician a basic understanding of the cardiovascular diagnostic techniques so that an accurate, precise, cost-effective, efficient diagnostic plan for the patient with cardiovascular disease can be developed and applied.     

Common feature learning for brain tumor MRI synthesis by context-aware generative adversarial network

Multi-modal structural Magnetic Resonance Image (MRI) provides complementary information and has been used widely for diagnosis and treatment planning of gliomas. While machine learning is popularly adopted to process and analyze MRI images, most existing tools are based on complete sets of multi-modality images that are costly and sometimes impossible to acquire in real clinical scenarios. In this work, we address the challenge of multi-modality glioma MRI synthesis often with incomplete MRI modalities. We propose 3D Common-feature learning-based Context-aware Generative Adversarial Network (CoCa-GAN) for this purpose. In particular, our proposed CoCa-GAN method adopts the encoder-decoder architecture to map the input modalities into a common feature space by the encoder, from which (1) the missing target modality(-ies) can be synthesized by the decoder, and also (2) the jointly conducted segmentation of the gliomas can help the synthesis task to better focus on the tumor regions. The synthesis and segmentation tasks share the same common feature space, while multi-task learning boosts both their performances. In particular, for the encoder to derive the common feature space, we propose and validate two different models, i.e., (1) early-fusion CoCa-GAN (eCoCa-GAN) and (2) intermediate-fusion CoCa-GAN (iCoCa-GAN). The experimental results demonstrate that the proposed iCoCa-GAN outperforms other state-of-the-art methods in synthesis of missing image modalities. Moreover, our method is flexible to handle the arbitrary combination of input/output image modalities, which makes it feasible to process brain tumor MRI data in real clinical circumstances.     

Modality alignment contrastive learning for severity assessment of COVID-19 from lung ultrasound and clinical information

The outbreak of COVID-19 around the world has caused great pressure to the health care system, and many efforts have been devoted to artificial intelligence (AI)-based analysis of CT and chest X-ray images to help alleviate the shortage of radiologists and improve the diagnosis efficiency. However, only a few works focus on AI-based lung ultrasound (LUS) analysis in spite of its significant role in COVID-19.In this work, we aim to propose a novel method for severity assessment of COVID-19 patients from LUS and clinical information. Great challenges exist regarding the heterogeneous data, multi-modality information, and highly nonlinear mapping. To overcome these challenges, we first propose a dual-level supervised multiple instance learning module (DSA-MIL) to effectively combine the zone-level representations into patient-level representations. Then a novel modality alignment contrastive learning module (MA-CLR) is presented to combine representations of the two modalities, LUS and clinical information, by matching the two spaces while keeping the discriminative features. To train the nonlinear mapping, a staged representation transfer (SRT) strategy is introduced to maximumly leverage the semantic and discriminative information from the training data.We trained the model with LUS data of 233 patients, and validated it with 80 patients. Our method can effectively combine the two modalities and achieve accuracy of 75.0% for 4-level patient severity assessment, and 87.5% for the binary severe/non-severe identification. Besides, our method also provides interpretation of the severity assessment by grading each of the lung zone (with accuracy of 85.28%) and identifying the pathological patterns of each lung zone. Our method has a great potential in real clinical practice for COVID-19 patients, especially for pregnant women and children, in aspects of progress monitoring, prognosis stratification, and patient management.     

Cardiac Stem Cell Imaging by SPECT and PET

After the initial enthusiasm of the preclinical studies of stem cell therapy (SCT) for cardiac diseases a rather rapid translation into clinical trials was accompanied by inconsistent results and at best modest benefit. This has lead to a reverse translation form bedside to bench in order to fully elucidate the fate and mechanism of action of the transplanted cells and find methods to boost their acute engraftment, long term survival and functional effects. Advanced imaging techniques are the only way to achieve this goal in humans. Among them radionuclide imaging is the most mature platform to provide quantitative information on short and long term bio-distribution of the transplanted cells in combination with structural and functional changes of the host organ in clinical practice for the short term future. In this paper we review the contribution of radionuclide imaging in the so far accumulated knowledge regarding SCT for heart diseases, its future potential and challenges.     

更新观念，迎接心血管疾病诊疗的影像时代

心血管影像技术已成为心血管疾病诊断和治疗的最重要手段,对于不同的疾病,应优先选用特定的影像检查技术。心血管临床医生应该掌握最基本的影像知识,从而提高疾病的诊疗质量。     

United adversarial learning for liver tumor segmentation and detection of multi-modality non-contrast MRI

Simultaneous segmentation and detection of liver tumors (hemangioma and hepatocellular carcinoma (HCC)) by using multi-modality non-contrast magnetic resonance imaging (NCMRI) are crucial for the clinical diagnosis. However, it is still a challenging task due to: (1) the HCC information on NCMRI is insufficient makes extraction of liver tumors feature difficult; (2) diverse imaging characteristics in multi-modality NCMRI causes feature fusion and selection difficult; (3) no specific information between hemangioma and HCC on NCMRI cause liver tumors detection difficult. In this study, we propose a united adversarial learning framework (UAL) for simultaneous liver tumors segmentation and detection using multi-modality NCMRI. The UAL first utilizes a multi-view aware encoder to extract multi-modality NCMRI information for liver tumor segmentation and detection. In this encoder, a novel edge dissimilarity feature pyramid module is designed to facilitate the complementary multi-modality feature extraction. Secondly, the newly designed fusion and selection channel is used to fuse the multi-modality feature and make the decision of the feature selection. Then, the proposed mechanism of coordinate sharing with padding integrates the multi-task of segmentation and detection so that it enables multi-task to perform united adversarial learning in one discriminator. Lastly, an innovative multi-phase radiomics guided discriminator exploits the clear and specific tumor information to improve the multi-task performance via the adversarial learning strategy. The UAL is validated in corresponding multi-modality NCMRI (i.e. T1FS pre-contrast MRI, T2FS MRI, and DWI) and three phases contrast-enhanced MRI of 255 clinical subjects. The experiments show that UAL gains high performance with the dice similarity coefficient of 83.63%, the pixel accuracy of 97.75%, the intersection-over-union of 81.30%, the sensitivity of 92.13%, the specificity of 93.75%, and the detection accuracy of 92.94%, which demonstrate that UAL has great potential in the clinical diagnosis of liver tumors.     

Cardiac Micro-PET-CT

Molecular imaging is a rapidly emerging field, with the use of multi-modality or hybrid technology scanners for in vivo investigations covering a broad spectrum of disease. Cardiac micro-PET-CT is one such promising multimodality. Standalone imaging technologies such as PET and CT have existed for several decades, however, they have only recently been utilized in concert, mainly for clinical cancer imaging. Cardiovascular events are responsible for nearly one-third of deaths in North America every year. Atherosclerosis, coronary artery disease (CAD), and heart failure are the most common types of heart disease. Cardiac imaging-related research into their prevention and treatment has contributed to a decrease in mortality. This review outlines the recent progress in the development and application of advanced cardiac micro-PET-CT technology. Current development of novel PET radiotracers focusing on diagnosis and characterization of different stages of atherosclerosis is discussed, as well as myocardial perfusion radiotracers mimicking previously established SPECT tracers and others. Small animal (mouse and rat) models of disease investigated with cardiac imaging are becoming more common, and will facilitate rapid translation to clinical studies with improvement in micro-PET-CT technology. Also, increasingly popular animal models for cardiovascular disease research such as mini-pigs and rabbits are used with interventional therapies, including catheterization due to larger artery sizes. The emergence of cardiac CT will be discussed with comparison between preclinical and clinical approaches, including consideration of radiation doses.     

Ultrasound Imaging Technologies for Breast Cancer Detection and Management: A Review

Ultrasound imaging is a commonly used modality for breast cancer detection and diagnosis. In this review, we summarize ultrasound imaging technologies and their clinical applications for the management of breast cancer patients. The technologies include ultrasound elastography, contrast-enhanced ultrasound, 3-D ultrasound, automatic breast ultrasound and computer-aided detection of breast ultrasound. We summarize the study results seen in the literature and discuss their future directions. We also provide a review of ultrasound-guided, breast biopsy and the fusion of ultrasound with other imaging modalities, especially magnetic resonance imaging (MRI). For comparison, we also discuss the diagnostic performance of mammography, MRI, positron emission tomography and computed tomography for breast cancer diagnosis at the end of this review. New ultrasound imaging techniques, ultrasound-guided biopsy and the fusion of ultrasound with other modalities provide important tools for the management of breast patients.     

Imaging in the Evaluation of the Patient with New-Onset Heart Failure

New-onset heart failure is a common clinical scenario which presents several diagnostic challenges to the clinician. Noninvasive cardiac imaging with echocardiography, radionuclide imaging, computed tomography, and cardiovascular magnetic resonance plays an essential role in the evaluation of such patients. This article will review the application of noninvasive imaging for diagnosis and management planning in the patient with new-onset heart failure.     

Molecular Imaging of Stem Cell Transplantation in Myocardial Disease

Stem cell therapy has been heralded as a novel therapeutic option for cardiovascular disease. In vivo molecular imaging has emerged as an indispensible tool in investigating stem cell biology post-transplantation into the myocardium and in evaluating the therapeutic efficacy. This review highlights the features of each molecular imaging modality and discusses how these modalities have been applied to evaluate stem cell therapy.