Upcoming Invited and PhD seminars 2023

Dr. Aleksei Tiulpin

21st of September 2023 

16h

Room 55.309

Title: Osteoarthritis progression modeling and what we have been missing 

Abstract: He will discuss his past and recent research on modeling the progression of knee osteoarthritis using different modalities and methodological approaches, culminating with his lab’s recent work on active surveillance.

Biography: Dr. Aleksei Tiulpin is an assistant professor at the University of Oulu, where he leads the Intelligent Medical Systems (IMEDS) research group. Additionally, he is a visiting professor at Aalto University in the Department of Electrical Engineering. Prior to this, Dr. Tiulpin conducted postdoctoral research at the Department of Computer Science at Aalto University and the Department of Electrical Engineering at KU Leuven. Dr. Tiulpin holds the title of docent (habilitation) from the University of Oulu in Machine Learning for Medical Imaging, and he is a member of ELLIS. He has published in MICCAI, IEEE TMI, PNAS, and other top venues. Currently, Dr. Tiulpin is broadly interested in building medical AI systems that can estimate their own uncertainty, process high-dimensional multimodal medical data, interact with users, and optimize clinical utility in general. 

 

Past Invited and PhD seminars 2023

John J. Costi

5th of July 2023 

10:30 h

Room 52.119 (Roc Boronat building)

Title: A multiaxial and multiscale assessment of lower back injury mechanisms

Abstract: Chronic low back pain (LBP) is a crippling condition that affects quality of life and is a significant burden on the health care system and the workforce. The mechanisms of LBP are poorly understood; however, it is well known that the loss of intervertebral disc height due to degeneration is a common cause of low back and referred pain.


Poor vascularity and slow repair of the disc render it susceptible to circumferential tears, which are present from the teenage years and arise from the delamination of adjacent lamellae within the annulus fibrosus. These tears are associated with disc degeneration and likely increase the risk of herniation (aka ‘a slipped disc’) via either a single overload or repetitive lifting events.


The major underlying microstructural components contributing to these tears are collagen and elastin, which are found within the extracellular matrix in the annulus fibrosus. However, there is limited understanding of how degeneration affects the mechanical properties of collagen type I individual fibre bundles (microscale), and of isolated fibrils (nanoscale). Furthermore, there are significant gaps with respect to both the ultrastructural organisation and mechanical properties of the elastic fibre network between adjacent lamellae (i.e., interlamellar matrix: ILM). Taken together, a new understanding of the role that the ILM plays during progressive loading to disc herniation, and the internal disc deformations during repetitive simulated lifting motions is required.


This presentation will discuss my program of research on the multiscale assessment of the effects of disc degeneration and herniation. A sophisticated multiaxial hexapod robot was developed for simulating lifting loads on cadaver lumbar segments, together with the measurement of internal disc deformations for determining a lifting injury threshold.
Current research that extends on these findings will also be discussed.

Biography:  John is a Mechanical Engineer who completed his PhD on the biomechanics of the intervertebral disc in 2004 at Flinders University. In 2005-2006 he undertook a postdoctoral fellowship at the University of Vermont in Burlington, Vermont, USA. In 2009, he joined The College of Science and Engineering, Flinders University in his current position as an Academic staff member where he teaches Solid Mechanics and Biomechanics. From 2009-2011 he led a collaborative team to design and develop a novel, award-winning, six-degree-of-freedom hexapod robot for the three- dimensional loading of biological joints and tissues. His program of research aims to understand the fundamental
multiscale properties of normal, degenerated, and injured discs, and their mechanisms of failure, and to develop medical devices to treat these problems. He has been working in the field of orthopaedic biomechanics research for almost 30 years.


He holds several leadership roles: Vice President and President-Elect of the Spine Society of Australia, Head of the Biomechanics and Implants Laboratory and Director of Flinders Surgical Lab. John is a Fellow of the Institution of Engineers Australia (Biomedical and Mechanical Engineering Colleges, 2015-), Fellow of International Orthopaedic Research of the International Combined Orthopaedic Research Societies (2019-), and was a recipient of the Spine Society of Australia Spinal Research Award (2017, 2019).

Adrian Galdran 

Thursday, 15th of June 2023 

Room 51.100 15:00 h

Title: A Tutorial on Model Calibration for Neural Nets 

Abstract: A calibrated machine learning model produces probabilistic predictions that are well-aligned with real probabilities: it tends to be more certain when it is correct. Unfortunately, the unique characteristics of modern neural networks, e.g. over-parametrization or iterative training dynamics, can often result in overfitting the training data and generating over-confident predictions. The goal of this talk is to introduce machine learning practitioners to the main ideas and methods of modern model calibration: its formal definition, how we can measure it, and how we can improve it. This talk is part of a tutorial (accepted to MICCAI 2023) on uncertainty quantification for medical image analysis, and it will also have a short hands-on code session: we will train a skin lesion classifier in pytorch, measure its calibration, and learn a post-processing transform to improve it.   

Biography:  Adrian Galdran is a Marie Skłodowska-Curie Research Fellow at Universitat Pompeu Fabra in Barcelona jointly with the Australian Institute of Machine Learning in Adelaide, leading a project on Uncertainty Quantification for medical imaging. Prior to this, he worked as lecturer/post-doctoral researcher in biomedical image analysis at Bournemouth University in the UK, ETS Montréal in Canada and INESC-TEC Porto in Portugal.

 

Schahram Dustdar 

Friday 24th of February 2023, 14:30 am 52.123 

Title: Edge Intelligence - Research Opportunities in the Distributed Computing  Continuum 

Abstract: As humans, Internet of Things, software services and AI continue to  become the entangled fabric of distributed systems, systems engineers and researchers  are facing novel challenges. In this talk, we analyze the role of AI in the context of IoT, Edge, and Cloud in the co-evolution of distributed systems for the new decade. We  identify challenges and discuss a roadmap that these new distributed systems have to  address in order to bring intelligence to the edge. We take a closer look at how a cyber physical fabric will be complemented by AI operationalization to enable seamless end to-end distributed systems. 

Biography: Schahram Dustdar is a Full Professor of Computer Science at the  Vienna Technical University, heading the Research Division of Distributed Systems at the TU Wien, Austria. He holds several honorary positions: University of California (USC) Los Angeles; Monash University in Melbourne, Shanghai University, Macquarie University in Sydney, University Pompeu Fabra, Barcelona, Spain.  

From Dec 2016 until Jan 2017 he was a Visiting Professor at the University of Sevilla,  Spain and from January until June 2017 he was a Visiting Professor at UC Berkeley, USA.  

From 1999 – 2007 he worked as the co founder and chief scientist of Caramba Labs Software AG in Vienna (acquired by ProjectNetWorld AG), a venture capital co-funded software company focused on  software for collaborative processes in teams. He is co-founder of edorer.com (an  EdTech company based in the US) and co-founder and chief scientist of Sinoaus.net,  a Nanjing, China based R&D organization focusing on IoT and Edge Intelligence. 

He is founding co-Editor-in-Chief of ACM Transactions on Internet of Things (ACM  TIoT) as well as Editor-in-Chief of Computing (Springer). He is an Associate Editor of  IEEE Transactions on Services Computing, IEEE Transactions on Cloud Computing,  ACM Computing Surveys, ACM Transactions on the Web, and ACM Transactions on  Internet Technology, as well as on the editorial board of IEEE Internet Computing and  IEEEComputer. 

Dustdar is recipient of multiple awards: IEEE TCSVC Outstanding Leadership Award  (2018), IEEE TCSC Award for Excellence in Scalable Computing (2019), ACM  Distinguished Scientist (2009), ACM Distinguished Speaker (2021), IBM Faculty  Award (2012). He is an elected member of the Academia Europaea: The Academy of  Europe, as well as an IEEE Fellow (2016) and an Asia-Pacific Artificial Intelligence  Association (AAIA) Fellow (2021) and the AAIA president (2021).

   

 

Past Research Seminars

Seminars take place at UPF, Campus Poblenou, Roc Boronat, 138, Barcelona and will only be streamed/recorded if the speaker has granted permission.  Rooms 55.309 / 55.410 streaming / Auditorium streaming 

EiTIC members: If you are interested in giving a Research Seminar or you would like to invite a speaker, please  contact with Joana Clotet  and fill in the following form RSDetails Form