Two open PhD positions in Device-Related Thrombus Modelling and Machine Learning in Left Atrial Appendage Occluder Device Optimisation
Back Two open PhD positions in Device-Related Thrombus Modelling and Machine Learning in Left Atrial Appendage Occluder Device Optimisation
Two open PhD positions in Device-Related Thrombus Modelling and Machine Learning in Left Atrial Appendage Occluder Device Optimisation
Two PhD positions are available at the BCN MedTech Research Unit (https://www.upf.edu/web/bcn-medtech/), Department of Information & Communication Technologies (DTIC) of the Universitat Pompeu Fabra (UPF), Barcelona, Spain, as part of the EU Horizon 2020 SimCardioTest project (2021-2024; SC1-DTH-06-2020, Grant agreement No. 101016496), ideally starting September 2021 (earlier start should also be possible). SimCardioTest is a recently granted European project involving a large consortium of clinical, industrial and academic partners (see Figure 1), with the main goal of developing a standardised and secure cloud-based platform where in-silico trials run seamlessly. UPF is the leader of the cardiac use case related to left atrial appendage occluder (LAAO) devices, where we will demonstrate the platform effectiveness, along with the required verification and validation processes and certification support to optimise LAAO device settings.
Fig. 1. SimCardioTest in-silico trials: a life buoy for healthcare innovation in cardiovascular disease.
LAAO devices are good examples of the most advanced generation of implantable devices that are having a large impact in the treatment of cardiac patients, in particular the ones suffering from atrial fibrillation. Non-valvular atrial fibrillation, the most common sustained cardiac rhythm disturbance in Europe, disrupts the normal behaviour of the heart and creates the appropriate environment to generate thrombus, the so-called Virchow’s triad (e.g., hypercoagulability, haemodynamics changes, and endothelial injury dysfunction). Around 99% of AF-related strokes originate from thrombus formed in a cavity of the left atrium, the left atrial appendage (LAA). Since AF causes a deceleration of blood flow, a stasis can occur, increasing the risk of thrombus formation in the LAA. The thrombus can loosen and be transported through the circulatory system to the brain, causing a cardioembolic stroke. Until recently, the main therapeutic solution to treat cardioembolic accidents was based on oral anticoagulation (OAC) therapy. During the past 20 years, LAAO devices have been developed as an alternative when OACs are not appropriate, due to high risk of bleeding or because of patient limitations. However, there are still important questions on the selection of the right device for a given patient as well as the optimal positioning. In-silico trials on such devices can provide crucial mechanistic insights thanks to the details of computational fluid dynamics simulations. The joint work with one of the largest companies producing such devices (Boston Scientific, USA), clinical partners with large patient databases (IHU Bordeaux, France) and other academic partners specialized in fluid simulations (Simula Research Lab, Norway) will enable to focus on the important aspects of such device.
Fig. 2. VIDAA platform developed at UPF for pre-interventional planning of LAAO implantation.
Specifically, the following three crucial aspects for LAAO devices will be investigated using various modelling approaches: 1) Improvement of patient selection; 2) Optimisation and personalisation of device settings; and 3) Prediction of treatment response. The first aspect deals with assessing the risk of thrombus formation of an atrial fibrillation patient before device implantation, based on a morphological analysis of the left atrial geometry extracted from medical images and on in-silico indices from fluid dynamics simulations. The VIDAA platform, a web-based interactive platform developed at UPF during the last years (Fig. 2) will be used to explore the LAA geometry of a given patient and extract simple morphological indices.
PhD project 1 (PhD1): Computational models for the prediction of device-related thrombus in LAAO devices
In collaboration with other partners of the consortium (mainly Boston Scientific, IHU Bordeaux and Simula), as well as several junior/senior researchers at UPF, PhD1 will work on the development of computational models to simulate the thrombus formation process after LAAO device implantation, using cascade and agent-based models, to couple with computational fluid dynamics (CFD) simulations. Fast fluid simulations with GPU-based solvers or deep-learning will also be investigated. A portfolio of realistic CAD models of LAAO devices will be created. Additionally, the effects of (anti-coagulants, anti-platelets) drug therapies will also be modelled. Virtual contrast agents and porous flow modelling through device frames after implantation will also be investigated to characterise acute response. PhD1 will also contribute to the generation of a large virtual population of in-silico fluid simulations and the development of quantitative metrics to characterise flow dynamics. These tasks will leverage on the past research by UPF members on LAAO-based fluid simulations (e.g., Aguado et al., 2019, https://doi.org/10.3389/fphys.2019.00237; Mill et al., 2020, https://doi:org/10.1016/j.cjca.2019.12.036) and agent-based models of atherosclerosis (Olivares et al., 2017, https://doi:org/10.1093/bioinformatics/btw551). PhD1 will be directly supervised by Pr Oscar Camara and Dr Jérôme Noailly from BCN MedTech at UPF.
PhD2 project (PhD2): Machine learning for the optimisation of device and drug therapy treatment in patients with atrial fibrillation
In collaboration with other partners of the consortium (mainly Inria, IHU Bordeaux, Boston Scientific), and junior/senior researchers at UPF, PhD2 will work on the development of machine learning tools to predict the optimal LAAO device settings for each individual patient. Morphological descriptors of the LA and LAA will be extracted to characterise their geometry, which will be combined with in-silico indices provided by fluid simulations run with multiple combinations of LAAO device settings. Unsupervised clustering methods such as the ones based on Multiple Kernel Learning, in which UPF has long-standing experience (e.g., Sanchez-Martinez et al., 2018, https://doi.org/10.1161/CIRCIMAGING.117.007138) will be explored to identify patterns among the data for a better understanding of the most relevant biomarkers predicting good prognosis. The use of deep learning techniques as surrogates of fluid simulations, based on our ongoing work (e.g., Morales et al., 2019, https://doi.org/10.1007/978-3-030-39074-7_17; Acebes et al., 2020, https://doi.org/10.1007/978-3-030-68107-4_4). PhD2 will be directly supervised by Pr Oscar Camara and Pr Gemma Piella from BCN MedTech at UPF.
Universitat Pompeu Fabra was established in 1990 as a public university with a strong dedication to excellence in research and teaching. UPF is a public, international and research-intensive university that, in just twenty-five years, has earned a place for itself among the best universities in Europe. UPF is the first Spanish university in the world Top 200, positioned in 152nd worldwide and 65th in Europe (Times Higher Education ranking THE2021), and ranked as 10th university under 50 years of age (THE2020) and 5th among young universities in Europe, out of 414 listed institutions. On April 2014, it was the 1st Spanish University to obtain the “HR Excellence in Research” distinction. UPF was ranked 1st among universities in Spain and among the top 50 in Europe with regard to the field of Computer Science (THE2019, THE2020 and THE2021 ranking by Subject). The Department of Information and Communication Technologies (DTIC) of UPF initiated its activity in 1999 and has an important track record of active participation in EU projects (67 H2020 projects with a total budget for the department of 30 million EUR). DTIC has a large number of ERC grants (19). It is one of the two Spanish ICT departments that had been awarded the Maria de Maeztu excellence by the Spanish government for the quality and relevance of its pioneering scientific research, and as the top IT research concentration in Spain. The DTIC, which has over 60% of international researchers from 48 different countries, is located on the Poblenou campus, in the heart of the Barcelona 22@ technology district, which includes high-tech companies, technology centres and public administrations, creating an outstanding area for RTD projects. BCN MedTech (https://www.upf.edu/web/bcn-medtech/) is a research unit at UPF that acts as an interdisciplinary and translational platform in biomedical engineering research. It was created in 2016 to integrate transversal competencies in computational methods, tackle health problems and contribute to the technological improvement of the healthcare industry for safer and more predictive medicine. Since then, the unit has been participating in more than 200 RDI projects, 1.000 publications, 19 patents and 57 PhD theses. Activities focus on biomedical image analysis and processing, data mining, complex systems and signal analyses, tissue and organ modelling, multi-scale simulations and biomedical electronics. BCN MedTech has 60 full-time researchers, including one ICREA and 4 faculty professors. It combines international, national and regional projects with the collaboration of both companies and research centres. In 2020, the unit had 7 European, 6 national and 10 regional competitive funds. In 2020, the research unit has been recognized as a TECNIO centre, a label from the Catalan government that acknowledges the value of the research unit's projects in terms of translation of the technology to the market.
Profile of the candidate
We are looking for highly motivated young researchers with a MSc degree (or equivalent) in Biomedical Engineering, Data Science, Physics, Mechanical Engineering, Applied Mathematics, Computational Science, or related disciplines, willing to study and do research at the leading edge of biomedical engineering. Experience in computer sciences and having proven programming skills would be of importance. High motivation is the only essential pre-requisite; our top-quality research standards demand hard work, which only strong motivation and commitment can ensure. Nevertheless, candidates already familiar with the following methodologies would ensure a faster start of the project: PhD1: Computational Fluid Simulations for biomedical applications, Ansys, Paraview, mesh manipulation software (e.g., MeshMixer, Meshlab, GMSH, Paraview, etc.), agent-based models. PhD2: Supervised and unsupervised machine learning algorithms, computational models. Candidates must have excellent teamwork and communication skills and be enthusiastic about collaborating with a diverse range of international partners. We expect them to be fluent in oral and, particularly, writing English, as it will be the language used to interrelate with the different partners. Interest in clinical translation is essential since meetings with clinicians will regularly take place. Female applicants are explicitly encouraged to apply and will be treated preferentially whenever they are equally qualified as other male candidates. More information on the requirements for a PhD position at the Universitat Pompeu Fabra can be found on https://www.upf.edu/web/etic/doctorat and http://www.upf.edu/doctorats/en
An initial training plan will be set up by selecting the best opportunities in the PhD programme of UPF and available initiatives within our collaborators. Clinical training will be organized depending on the needs and background of the researcher. BCN-MedTech offers an ideal working environment, mainly due to the large critical mass of experienced senior investigators in diverse areas of biomedical engineering, junior postdoctoral researchers and an international team of talented young PhD students; there is always someone that can help! In addition, the extensive network of collaborations, including clinical and large infrastructure partners, gives us a privileged access to unique data, software and technological facilities. The maximum score usually obtained in individual national and international fellowships evaluating the institution repeatedly demonstrates the excellent training environment of BCN-MedTech. These PhDs will be funded with resources based on the SimCardioTest project. A four-year contract will be offered. The first two years start with around 1370 euros gross monthly salary (approx. 16.5k euros per year), which is progressively increased during the PhD (3rd year of 1.450 euros gross month salary, total of 17600 euros approx.; 4th year around 1800 euros gross monthly salary, total of 22k euros approx.). You won’t get rich, for sure; still, our PhD students have a decent living in Barcelona. Additionally, we encourage and support our students to apply for individual fellowships, which are usually better paid (https://www.upf.edu/web/phdfunding). Complements can be discussed.
The PhD students can also volunteer to be involved in teaching activities, which is a good opportunity to get familiar, from the beginning of their career, with those tasks. Teaching hours are payed at standard rates (around 70 euros / h) beyond the base salary.The teaching topics are chosen depending on the PhD background, preferentially in the biomedical engineering BSc and MSc degrees we manage (https://www.upf.edu/en/web/etic/bachelor-degree-biomedicalengineering-2016). Supervising practicum internships as well as BSc and MSc thesis is also possible.
The selection committee uses a number of indicators to evaluate the applicant’s preparedness, motivation and potential.
1st phase, remote pre-selection:
The Scientific, Technological & Academic excellence will be considered at first, based on:
• Quality of the CV, in general
• Any demonstrated research experience, particularly if supported by evidence such as scientific publications, patents, participation in scientific congresses, …
• Undergraduate performance: overall, with a special focus on relevant field-specific courses
• Any demonstrated previous recognitions (grants, awards, …)
• Reference letters provided by professors and senior scientists: Two refence letters are expected. Referees are asked to address analytical capabilities, technical proficiency, ability to work independently and motivation/commitment.
• Statement of purpose: past research experience, motivation for applying to this particular PhD project, academic fit, contribution of the project to the candidate’s future careers plans, ...
• Additional relevant skills (field-specific): demonstrated, e.g., through previous projects, and or through previous participation in scientific contests, trainings, ...
2nd phase, interview(s):
Should the candidate be preselected at phase 1, a second phase will consist in at least one interview through which the motivation, the proactive behaviour, the capacity to work collaboratively, the organizational skills, the communication skills and the capacity to engage in a scientific discussion and manage problems, will be assessed, among other aspects. The final decision will be the result of a consensus of an evaluation committee that will take into account the results of both recruitment phases 1 and 2.
The candidate will be informed of the section results by email. Application process All the documents that prove the eligibility of the candidate and should be provided.
As for the selection process candidates are expected to provide at least the following documents:
• A brief introduction letter (no more than one A4 page) that summarizes the documents and the nature of the information provided for the selection
• A full CV
• The two requested reference letters
• The letter of purpose (no more than two A4 pages)
All documents must be sent by email to Pr Oscar Camara .
Deadline: 26th April 2021