Nicola Pezzotti

Scientist, Engineer and Leader in
Artificial Intelligence, Visual Analytics and Computer Science

Follow me on GitHub

About me

I am a scientist, engineer, and leader, with a diverse set of interests, focusing on the development of algorithmic techniques and solutions that have a concrete and positive impact on the world.

As a scientist, I develop several algorithmic solutions that led to discoveries presented in important venues such as “Nature Communications”, “Nature Immunology” and the “Journal of Experimental Medicine”. My work in single-cell analysis, led to the discovery of previously unknown cell types, thanks to the development of scalable dimensionality reduction approaches. I also lead large-scale research activities, such as the AI4MRI lab between Philips and LUMC. I enjoy working on complex and previously unsolved problems, with a drive for excellence

As an engineer, I implement solutions that are scalable and proven to work well in the real world. In my career, I have covered a diverse set of topics including industrial automation, computer vision, 3D reconstruction and processing, machine learning, deep learning, and artificial intelligence in general. I had success on all of them thanks to a key focus on software excellence and a fast-delivery mindset. As an example, I drove our Philips team to win the fastMRI challenge and convert it into our FDA-approved SmartSpeed product in less than 3 years, while training our staff on hybrid deep learning. Also, my contributions to 3D scanning technology were instrumental in the acquisition of the OpenTechnology startup by FARO.

As a leader, I drive teams to success thanks to a win-win and agile mindset. I led very diverse teams, from very junior to senior teams, from small ones to teams of more than 15 people, and from engineering to research-focused teams. I am experienced in driving teams both in my organization and across organizations. For example, I drive several public-private partnerships leveraging my joint appointment as an assistant professor at TU Eindhoven.

I worked in a diverse set of environments. I have several years of experience in freelancing, startup to scaleup, big tech, the healthcare industry, and publicly funded research institutions. I worked at Google AI with Alexander Mordvintsev, the creator of Google’s DeepDream, where I was recognized as one of the best research efforts in 2018. I currently work at Philips Research, focusing on the development of robust Artificial-Intelligence solutions for healthcare. I also have a joint appointment as an assistant professor at TU Eindhoven, focusing on human-centered AI, and I collaborate with several research groups across the world.

More information, and links to several news and achievements can be found on my LinkedIn page

Selected Publications

A detailed list of my publications can be found on my Google Scholar page or on Semantic Scholar

  • N. Pezzotti, S. Yousefi, M. Elmahdy, J. Van Gemert, C. Schuelke, M. Doneva, T. Nielsen, S. Kastryulin, B.P.F. Lelieveldt, M. Van Osch, E. De Weerdt, M. Staring An adaptive intelligence algorithm for undersampled knee MRI reconstruction. IEEE Access, 2020. PDF.
  • N. Pezzotti, J. Thijssen, A. Mordvintsev, T. Höllt, B. van Lew, B.P.F. Lelieveldt, E. Eisemann, A. Vilanova. GPGPU Linear Complexity t-SNE Optimization. Transaction on Visualization and Computer Graphics (Proceedings of IEEE VIS 2019), 2019. Preprint, Demo, Google AI post
  • V. van Unen*, T. Hollt*, N. Pezzotti*, N. Li, M. J.T. Reinders, E. Eisemann, A. Vilanova, F. Koning, B. P.F. Lelieveldt. Interactive Visual Analysis of Mass Cytometry Data by Hierarchical Stochastic Neighbor Embedding Reveals Rare Cell Types. Nature Communications, 2017. Website PDF
  • N. Pezzotti, T. Höllt, J. van Gemert, B.P.F. Lelieveldt, E. Eisemann, A. Vilanova. DeepEyes: Progressive Visual Analytics for Designing Deep Neural Networks. Transaction on Visualization and Computer Graphics (Proceedings of IEEE VIS 2017), 2018. PDF, Video
  • N. Pezzotti, T. Höllt, B.P.F. Lelieveldt, E. Eisemann, A. Vilanova. Hierarchical Stochastic Neighbor Embedding. Computer Graphics Forum (Proc. of EuroVis), 2016. PDF, Suppl. Mat., Video, Slides
  • T. Höllt, N. Pezzotti, V. van Unen, F. Koning, E. Eisemann, B.P.F. Lelieveldt, A. Vilanova. Cytosplore: Interactive Immune Cell Phenotyping for Large Single-Cell Datasets. Computer Graphics Forum (Proc. of EuroVis), 2016. PDF
  • N. Pezzotti, B.P.F. Lelieveldt, L. van der Maaten, T. Höllt, E. Eisemann, and A. Vilanova. Approximated and User Steerable tSNE for Progressive Visual Analytics. Transaction on Visualization and Computer Graphics (Presented at IEEE VIS 2016), 2016. PDF, Suppl. Mat., Video I, Video II, Video III

Awards

  • 2021 - Philips Innovation Award: deep learning methodologies for improved image quality in MRI
  • 2021 - Won the IEEE CoG Bot Bowl III competition, developing the first and only machine learning algorithm that is able to win in Blood Bowl
  • 2020 - Philips Innovation Award: tools and techniques for Deep Learning and trustworthy AI
  • 2020 - Best Scientific Paper Award in Computer Vision - Philips AI Conference
  • 2020 - Highest Business Potential Award in Computer Vision - Philips AI conference
  • 2020 - Recipient of the Outstanding Achievement Award at Philips Research
  • 2019 - Winner of the first FastMRI challenge organized by Facebook AI Research and NYU Langone Health - Results, Philips Research Blog, Recordings
  • 2019 - IEEE VGTC 2019 Best Dissertation Award
  • 2019 - Dirk Bartz Prize for Visual Computing in Medicine
  • 2019 - PhD Cum Laude - Awarded to 5% of PhD candidates in the Netherlands
  • 2018 - Portraits of Science 2018 - TU Delft Excellence in Research
  • 2006 - Awarded in “Expo Del capitale umano 2006” for academic merit
  • 2005 - Silver medal in the Italian selection for the International Olympiad in Informatics (IOI)

News

I’ve started to share updates only via LinkedIn. You can see all updates on my LinkedIn timeline. I also share stuff on Twitter: have a look at Twitter my feed.

Here some older updates:

My old blog can be found here