We present the framework GUCCI (Guided Cardiac Cohort Investigation), which provides a guided visual analytics workflow to analyze cohort-based measured blood flow data in the aorta. In the past, many specialized techniques have been developed for the visual exploration of such data sets for a better understanding of the influence of morphological and hemodynamic conditions on cardiovascular diseases. However, there is a lack of dedicated techniques that allow visual comparison of multiple data sets and defined cohorts, which is essential to characterize pathologies. GUCCI offers visual analytics techniques and novel visualization methods to guide the user through the comparison of predefined cohorts, such as healthy volunteers and patients with a pathologically altered aorta. The combination of overview and glyph-based depictions together with statistical cohort-specific information allows investigating differences and similarities of the time-dependent data. Our framework was evaluated in a qualitative user study with three radiologists specialized in cardiac imaging and two experts in medical blood flow visualization. They were able to discover cohort-specific characteristics, which supports the derivation of standard values as well as the assessment of pathology-related severity and the need for treatment.

An accurate assessment of the cardiovascular system and prediction of cardiovascular diseases (CVDs) are crucial. Cardiac blood flow data provide insights about patient-specific hemodynamics. However, there is a lack of machine learning approaches for a feature-based classification of heart-healthy people and patients with CVDs. In this paper, we investigate the potential of morphological and hemodynamic features extracted from measured blood flow data in the aorta to classify heart-healthy volunteers (HHV) and patients with bicuspid aortic valve (BAV). Furthermore, we determine features that distinguish male vs. female patients and elderly HHV vs. BAV patients. We propose a data analysis pipeline for cardiac status classification, encompassing feature selection, model training, and hyperparameter tuning. Our results suggest substantial differences in flow features of the aorta between HHV and BAV patients. The excellent performance of the classifiers separating between elderly HHV and BAV patients indicates that aging is not associated with pathological morphology and hemodynamics. Our models represent a first step towards automated diagnosis of CVS using interpretable machine learning models.

Abstract Rupture risk assessment is a key to devise patient‐specific treatment plans of cerebral aneurysms. To understand and predict the development of aneurysms and other vascular diseases over time, both hemodynamic flow patterns and their effect on the vessel surface need to be analyzed. Flow structures close to the vessel wall often correlate directly with local changes in surface parameters, such as pressure or wall shear stress. Yet, in many existing applications, the analyses of flow and surface features are either somewhat detached from one another or only globally available. Especially for the identification of specific blood flow characteristics that cause local startling parameters on the vessel surface, like elevated pressure values, an interactive analysis tool is missing. The explorative visualization of flow data is challenging due to the complexity of the underlying data. In order to find meaningful structures in the entirety of the flow, the data has to be filtered based on the respective explorative aim. In this paper, we present a combination of visualization, filtering and interaction techniques for explorative analysis of blood flow with a focus on the relation of local surface parameters and underlying flow structures. Coherent bundles of pathlines can be interactively selected based on their relation to features of the vessel wall and further refined based on their own hemodynamic features. This allows the user to interactively select and explore flow structures locally affecting a certain region on the vessel wall and therefore to understand the cause and effect relationship between these entities. Additionally, multiple selected flow structures can be compared with respect to their quantitative parameters, such as flow speed. We confirmed the usefulness of our approach by conducting an informal interview with two expert neuroradiologists and an expert in flow simulation. In addition, we recorded several insights the neuroradiologists were able to gain with the help of our tool.