Big Heart Data: Advancing Health Informatics Through Data Sharing in Cardiovascular Imaging

Abstract

The burden of heart disease is rapidly worsening due to increasing prevalence of obesity and diabetes. Data sharing and open database resources for heart health informatics are important for advancing our understanding of cardiovascular function, disease progression and therapeutics. Data sharing enables valuable information, often obtained at considerable expense and effort, to be re-used beyond the specific objectives of the original study. Many government funding agencies and journal publishers are requiring data re-use, and are providing mechanisms for data curation and archival. Tools and infrastructure are available to archive anonymous data from a wide range of studies, from descriptive epidemiological data to gigabytes of imaging data. Meta-analyses can be performed to combine raw data from disparate studies to obtain unique comparisons or to enhance statistical power. Open benchmark datasets are invaluable for validating data analysis algorithms and objectively comparing results. This review provides a rationale for increased data sharing and surveys recent progress in the cardiovascular domain. We also highlight the potential of recent large cardiovascular epidemiological studies enabling collaborative efforts to facilitate data sharing, algorithms benchmarking, disease modeling and statistical atlases.

A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion

“…It is one of the pioneering work in advancing cardiac data sharing and inferring health informatics from a big data set (Suinesiaputra et al, 2014b). The CAP data set has already successfully lead to fruitful research findings in cardiac image analysis and has also been used in many workshops, such as the STACOM workshop series and many MICCAI segmentation and motion tracking challenges 1 .…”

A Deep Learning Network for Right Ventricle Segmentation in Short:Axis MRI

“…In the actually clinical diagnosis of cardiac diseases, the cardiac magnetic resonance (CMR) is an important imaging modality and widely used because of its special advantages such as non-invasive detection, low radiation doses and high imaging quality [9]. Generally speaking, CMR is considered as gold standard in cardiac disease diagnosis especially in LV and RV function estimation.…”

Cardiovascular Research: Past, Present and Future

“…The Anatomical Models Database (AMDB, formerly euHeart) is a web based resource that allows researchers to computationally model cardiac electrophysiology and mechanics using information from geometriccardiac models. It allows the user to generate a geometric heart model based on binary images of the heart and cardiac parameters 56 while the Virtual Imaging Platform (VIP) focuses on multi-modality medical image simulation. 57 Other resources include iDASH (integrated Data analysis, anonymization and sharing), designed to share and access medical data in general, 58 PhysioNet holds ECG and biomedical data from healthy subjects and cardiac patients 59 and the Cardio Vascular Research Grid (CVRG) aims to provide a more complex resource for sharing genomic, proteomic, imaging and clinical data from cardiovascular research.…”