Cardiopulmonary resuscitation (CPR) hands-on workshop

 

Become proficient in basic life support skills based on the European Resuscitation Council guidelines, learn the chain of survival in out-hospital cardiac arrest and the importance early on-site patient defibrillation. Learn through hands-on experience and apply the theory ina scenario with a CPR ‘dummies’ and AED training equipment. Practice early recognition of a cardiac arrest – assessing a victim’s vital signs and calling for help, early cardio-pulmonal resuscitation – chest compressions

and mouth-to-mouth breathing, and early defibrillation using an AED.

 

Number of participants: 25

Duration: 45 minutes

Introduction and Motivation

 

 

 

Hands-on Sessions:

 

1) Cartilage multi-scale modelling, from human body motion to tissue turnover

Instructors: Simone Tassani, Carlos Ruiz, Laura Baumgartner

Chronic modification of the mechanical fields on the articular cartilage can trigger/accelerate catabolic responses in chondrocytes. In this hands on motion analyses will be done in the UPF MoCA LAB, and knee joint forces will be calculated from inverse dynamic analyses (The gait of two volunteers selected among the participants will be analysed - Volunteers will need to wear stretch sport clothes to allow proper movement analysis). These forces will be further translated as boundary conditions on a cartilage tissue finite element model. Multiphysics simulations performed with FEBio will give the possibility to introduce the effect of preexisting tissue damage, e.g. osteoarthritis. The calculated mechanical fields will be further used to feed an agent-based model of cartilaginous cells, developed in NetLOGO, so as to explore the catabolic response of these cells in terms of inflammation and protein expressions. For the smooth implementation of the workshop, students will be divided into three focus groups.

  

 

2) Machine learning and tissue modelling for image-guided brain surgery

Instructors:Mario Ceresa, Jérôme Noailly

In this hands-on the students will learn the basic concepts of surgical planning and navigation of brain surgery: image processing, robotics and surgical tracking. They will simulate a real intervention on a 3D printed phantom using a  robotic arm model controlled by a raspberry pi. Furthermore, students will generate a nonlinear Brain tissue biomechanical model to inform the system about tactic signals and anticipate the time-dependency of tissue deformations during and after surgery.

 

3) Computational anatomy: from MRI to clinical morphological metrics – (i) deep learning solutions to segment images, to correct artefacts; (ii) 3D model personalization solutions; (iii) machine learning solutions to find the signature of disease

Instructors: Esther Puyol and Pablo Lamata & Eric Kerfoot

 

Accurate assessment of cardiac anatomy and function is crucial in aiding diagnosis for a wide range of cardiovascular pathologies as well as for optimisation clinical procedures. Left-ventricular (LV) remodelling and function has been traditionally assessed using global indicators from MRI such as ejection fraction, stroke volume or ventricular mass. Recent advances in computational techniques now allows a much more detailed quantification of LV shape and function, and offer the promise of fully automated, robust and accurate assessment. These tools are now revealing the subtle signs of cardiac disease, thus improving our understanding of underlying mechanisms and enabling an earlier diagnosis and optimal therapy planning. 

 

The aims of this workshop are:

1) To learn the basis of machine / deep learning, and apply it in two problems: (i) the automatic segmentation of clinical images, and (ii) the diagnosis and prognosis of cardiac disease.

2) To learn the basis of the personalization of computational meshes to medical images, and of the statistical shape models, applying it to the problem of clinical diagnosis.

 
In conclusion, in this workshop you will learn to build an end-to-end diagnosis tool from cardiac magnetic resonance imaging.

 

4) Machine learning for arrhythmia detection in electrocardiography measurements

Instructors: Cecilia Nunes, Gabriel Bernardino

This hands-on session will cover basic concepts of machine learning including the differences between supervised and unsupervised learning, overfitting and regularization, and model and parameter selection. As practical applications, we propose the use of supervised learning to identify pathological cardiac shapes, followed by dimensionality reduction to detect arrhythmia in electrocardiography measurements.

 

****************************************

 

Guided visit to the Barcelona Supercomputing Center (BSC - CNS)

The visit to the Barcelona Supercomputing Center  is programmed for Tuesday, June 11th, at 14:45 (until 15:30 h.).
Limited to 30 participants.