Quantitative analysis of pre- and post-operative valvular annulus deformations following valvular insufficiency

Valvular insufficiency is a growingly common valvular heart disease that frequently is associated with regurgitation. Atrioventricular incompetency can lead to overall ventricular and atrial enlargement, volume overload, heart impairment and, if not treated, can culminate in heart failure. With the advances in technology and the increasing interest in devices that have lower post-operative burden on patients, transcatheter mitral and tricuspid valve repair systems are going through a phase of rapid development and growing use. In this work, we aimed to quantitatively assess the morphology of mitral and tricuspid annuli in patients who underwent transcatheter valve repair with MitraClip/TriClip, before and after the intervention, using three-dimensional transoesophageal echocardiography images, in order to evaluate the geometrical changes of the annulus following the intervention. For our purposes, firstly, we implemented a tool for the visualization and navigation of the volumetric data across the cardiac cycle. Then, in order to track the annulus over the cardiac cycle, we extracted five rotational slices from the volume data, selected two initial points on each slice, and tracked these points across the cardiac cycle using KLT algorithm. In a first stage we led a parameters optimization for the tracking method, and we studied the sensitivity of the KLT algorithm to the initialization points, that are manually chosen by the user. In a second stage, we analysed 10 subjects (5 for mitral regurgitation and 5 for tricuspid regurgitation), tracking their annulus before and after valve repairment. In conclusion, we found in all our 10 subjects that immediately after the intervention there is a shortening of the major diameters of the valves, mainly the shortest diameter, due to the clip application, that leads to a reduction of the perimeter and the area of the annulus.

Evaluating the Impact of Recommender Systems to Society

Nowadays, Recommender systems play a key role in managing information overload, particularly in areas such as e-commerce, music and cinema. However, despite their good-natured goal, in recent years there has been a growing awareness of their involvement in creating unwanted effects on society, such as creating biases of popularity or filter bubble. This thesis is an attempt to investigate the role of RS and its stakeholders in creating such effects. A simulation study will be performed using EcoAgent, an RL-based multi-stakeholder recommendation system, in a simulation environment that captures key user interactions, suppliers and the recommender system in order to identify possible unhealthy scenarios for stakeholders. In particular, we focus on analyzing the document catalog to see how the diversity of topics that users have access to varies during interactions. Finally, some post-processing methods will be defined on EcoAgent, one reactive and one proactive, which allows us to manipulate the agent’s behavior in order to study whether and how the topic distribution of documents is affected by content providers and by the fairness of the system.