Advanced technology in interventional cardiology: A roadmap for the future of precision coronary interventions

Annotated computed tomography coronary angiogram images and associated data of normal and diseased arteries

Computed Tomography Coronary Angiography (CTCA) is a non-invasive method to evaluate coronary artery anatomy and disease. CTCA is ideal for geometry reconstruction to create virtual models of coronary arteries. To our knowledge there is no public dataset that includes centrelines and segmentation of the full coronary tree. We provide anonymized CTCA images, voxel-wise annotations and associated data in the form of centrelines, calcification scores and meshes of the coronary lumen in 20 normal and 20 diseased cases. Images were obtained along with patient information with informed, written consent as part of the Coronary Atlas. Cases were classified as normal (zero calcium score with no signs of stenosis) or diseased (confirmed coronary artery disease). Manual voxel-wise segmentations by three experts were combined using majority voting to generate the final annotations. Provided data can be used for a variety of research purposes, such as 3D printing patient-specific models, development and validation of segmentation algorithms, education and training of medical personnel and in-silico analyses such as testing of medical devices.

Robotics, imaging, and artificial intelligence in the catheterisation laboratory

The catheterisation laboratory today combines diagnosis and therapeutics, through various imaging modalities and a prolific list of interventional tools, led by balloons and stents. In this review, we focus primarily on advances in image-based coronary interventions. The X-ray images that are the primary modality for diagnosis and interventions are combined with novel tools for visualisation and display, including multi-imaging co-registration modalities with three- and four-dimensional presentations. Interpretation of the physiologic significance of coronary stenosis based on prior angiographic images is being explored and implemented. Major efforts to reduce X-ray exposure to the staff and the patients, using computer-based algorithms for image processing, and novel methods to limit the radiation spread are being explored. The use of artificial intelligence (AI) and machine learning for better patient care requires attention to universal methods for sharing and combining large data sets and for allowing interpretation and analysis of large cohorts of patients. Barriers to data sharing using integrated and universal protocols should be overcome to allow these methods to become widely applicable. Robotic catheterisation takes the physician away from the ionising radiation spot, enables coronary angioplasty and stenting without compromising safety, and may allow increased precision. Remote coronary procedures over the internet, that have been explored in virtual and animal studies and already applied to patients in a small pilot study, open possibilities for sharing experience across the world without travelling. Application of those technologies to neurovascular, and particularly stroke interventions, may be very timely in view of the need for expert neuro-interventionalists located mostly in central areas.

A primer on artificial intelligence for the paediatric cardiologist

The combination of pediatric cardiology being both a perceptual and a cognitive subspecialty demands a complex decision-making model which makes artificial intelligence a particularly attractive technology with great potential. The prototypical artificial intelligence system would autonomously impute patient data into a collaborative database that stores, syncs, interprets and ultimately classifies the patient's profile to specific disease phenotypes to compare against a large aggregate of shared peer health data and outcomes, the current medical body of literature and ongoing trials to offer morbidity and mortality prediction, drug therapy options targeted to each patient's genetic profile, tailored surgical plans and recommendations for timing of sequential imaging. The focus of this review paper is to offer a primer on artificial intelligence and paediatric cardiology by briefly discussing the history of artificial intelligence in medicine, modern and future applications in adult and paediatric cardiology across selected concentrations, and current barriers to implementation of these technologies.

Precision Medicine in Interventional Cardiology

Precision medicine has recently become widely advocated. It revolves around the individual patient, taking into account genetic, biomarker, phenotypic or psychosocial characteristics and uses biological, mechanical and/or personal variables to optimise individual therapy. In silico testing, such as the Virtual Physiological Human project, is being promoted to predict risk and to test treatments and medical devices. It combines artificial intelligence and computational modelling to select the best therapeutic option for the individual patient.

Haptic Telerobotic Cardiovascular Intervention: A Review of Approaches, Methods, and Future Perspectives

Cardiac diseases are recognized as the leading cause of mortality, hospitalization, and medical prescription globally. The gold standard for the treatment of coronary artery stenosis is the percutaneous cardiac intervention that is performed under live X-ray imaging. Substantial clinical evidence shows that the surgeon and staff are prone to serious health problems due to X-ray exposure and occupational hazards. Telerobotic vascular intervention systems with a master-slave architecture reduced the X-ray exposure and enhanced the clinical outcomes; however, the loss of haptic feedback during surgery has been the main limitation of such systems. This paper is a review of the state of the art for haptic telerobotic cardiovascular interventions. A survey on the literature published between 2000 and 2019 was performed. Results of the survey were screened based on their relevance to this paper. Also, the leading research disciplines were identified based on the results of the survey. Furthermore, different approaches for sensor-based and model-based haptic telerobotic cardiovascular intervention, haptic rendering and actuation, and the pertinent methods were critically reviewed and compared. In the end, the current limitations of the state of the art, unexplored research areas as well as the future perspective of the research on this technology were laid out.

3D printing for congenital heart disease: a single site's initial three-yearexperience

Background

3D printing is an ideal manufacturing process for creating patient-matched models (anatomical models) for surgical and interventional planning. Cardiac anatomical models have been described in numerous case studies and journal publications. However, few studies attempt to describe wider impact of the novel planning augmentation tool. The work here presents the evolution of an institution’s first 3 full years of 3D prints following consistent integration of the technology into clinical workflow (2012–2014) - a center which produced 79 models for surgical planning (within that time frame). Patient outcomes and technology acceptance following implementation of 3D printing were reviewed.

Methods

A retrospective analysis was designed to investigate the anatomical model’s impact on time-based surgical metrics. A contemporaneous cohort of standard-of-care pre-procedural planning (no anatomical models) was identified for comparative analysis. A post-surgery technology acceptance assessment was also employed in a smaller subset to measure perceived efficacy of the anatomical models. The data was examined.

Results

Within the timeframe of the study, 928 primary-case cardiothoracic surgeries (encompassing both CHD and non-CHD surgeries) took place at the practicing pediatric hospital. One hundred sixty four anatomical models had been generated for various purposes. An inclusion criterion based on lesion type limited those with anatomic models to 33; there were 113 cases matching the same criterion that received no anatomical model. Time-based metrics such as case length-of-time showed a mean reduction in overall time for anatomical models. These reductions were not statistically significant. The technology acceptance survey did demonstrate strong perceived efficacy. Anecdotal vignettes further support the technology acceptance.

Discussion & conclusion

The anatomical models demonstrate trends for reduced operating room and case length of time when compared with similar surgeries in the same time-period; in turn, these reductions could have significant impact on patient outcomes and operating room economics. While analysis did not yield robust statistical powering, strong Cohen’s d values suggest poor powering may be more related to sample size than non-ideal outcomes. The utility of planning with an anatomical model is further supported by the technology acceptance study which demonstrated that surgeons perceive the anatomical models to be an effective tool in surgical planning for a complex CHD repair. A prospective multi-center trial is currently in progress to further validate or reject these findings.

Three-dimensional printing: changing clinical care or just a passing fad?

PURPOSE OF REVIEW

Advances in medical imaging and three-dimensional (3D) reconstruction software have enabled a proliferation of 3D modeling and 3D printing for clinical applications. In particular, 3D printing has garnered an extraordinary media presence over the past few years. There is growing optimism that 3D printing can address patient specificity and complexity for improved interventional and surgical planning. Will this relatively untested technology bring about a paradigm shift in the clinical environment, or is it just a transient fad?

RECENT FINDINGS

Case studies and series centered around 3D printing are omnipresent in clinical and engineering journals. These primarily qualitative studies support the potential efficacy of the emerging technology. Few studies analyze the value of 3D printing, weighing its potential benefits against increasing costs (e.g., institutional overhead, labor, and materials).

SUMMARY

Clinical integration of 3D printing is growing rapidly, and its adoption into clinical practice presents unique workflow challenges. There are numerous clinical trials on the horizon that will finally help to elucidate the measured impact of 3D printing on clinical outcomes through quantitative analyses of clinical and economic metrics. The contrived integration of 3D printing into clinical practice seems all but certain as the value of this technology becomes more and more evident.

Promoting Collaborations Between Radiologists and Scientists

Radiology as a discipline thrives on the dynamic interplay between technological and clinical advances. Progress in almost all facets of the imaging sciences is highly dependent on complex tools sourced from physics, engineering, biology, and the clinical sciences to obtain, process, and view imaging studies. The application of these tools, however, requires broad and deep medical knowledge about disease pathophysiology and its relationship with medical imaging. This relationship between clinical medicine and imaging technology, nurtured and fostered over the past 75 years, has cultivated extraordinarily rich collaborative opportunities between basic scientists, engineers, and physicians. In this review, we attempt to provide a framework to identify both currently successful collaborative ventures and future opportunities for scientific partnership. This invited review is a product of a special working group within the Association of University Radiologists-Radiology Research Alliance.

Personalized Management of Cardiovascular Disorders

Personalized management of cardiovascular disorders (CVD), also referred to as personalized or precision cardiology in accordance with general principles of personalized medicine, is selection of the best treatment for an individual patient. It involves the integration of various "omics" technologies such as genomics and proteomics as well as other new technologies such as nanobiotechnology. Molecular diagnostics and biomarkers are important for linking diagnosis with therapy and monitoring therapy. Because CVD involve perturbations of large complex biological networks, a systems biology approach to CVD risk stratification may be used for improving risk-estimating algorithms, and modeling of personalized benefit of treatment may be helpful for guiding the choice of intervention. Bioinformatics tools are helpful in analyzing and integrating large amounts of data from various sources. Personalized therapy is considered during drug development, including methods of targeted drug delivery and clinical trials. Individualized recommendations consider multiple factors - genetic as well as epigenetic - for patients' risk of heart disease. Examples of personalized treatment are those of chronic myocardial ischemia, heart failure, and hypertension. Similar approaches can be used for the management of atrial fibrillation and hypercholesterolemia, as well as the use of anticoagulants. Personalized management includes pharmacotherapy, surgery, lifestyle modifications, and combinations thereof. Further progress in understanding the pathomechanism of complex cardiovascular diseases and identification of causative factors at the individual patient level will provide opportunities for the development of personalized cardiology. Application of principles of personalized medicine will improve the care of the patients with CVD.