
Chief Scientist @ VitVio, specialising in Multimodal Learning. Ex-PhD @SchoolOfEng_UoE, MSc @InfAtEd, BSc @csmcr. Formerly @AmazonScience, @CERN, @Microsoft.
Warsaw, Poland
Joined January 2011
- Tweets77
- Following341
- Followers144
- Likes306
A little highlight from @nvidia GTC Berlin, had the chance to chat with @TIME for a quick interview. Thanks for having me!
Greg Jacenków, chief scientist at VitVio, explains how the company is working to connect systems in the operating room.
Greg Jacenków on how VitVio uses AI to collaborate in operating rooms
1
69
exciting times ahead! 🚀
It's official - #DHLLaunchpad Cohort 6 is here! 🚀
We are excited to introduce the 23 #digitalhealth companies selected for Cohort 6 of our Launchpad programme.
Find out how their digital #innovations are poised to transform #health and #care:
digitalhealth.london/cohort-…
2
163
If you're in Warsaw around October 26-29, don't miss one of Poland's biggest ML conferences, and a chance to chat with Amazon scientists.
@AmazonScience x @AmazonNewsPL x @MLinPL
Meet the speaker representing our sponsor, @amazon!
🤖 Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models
3
271
Grzegorz Jacenków retweeted
🚨 New dataset! I'm releasing a synthetic chest X-ray dataset on @huggingface datasets.
This was created as part of a paper entitled Privacy Distillation (more details soon).
We ensured the images can NOT be used for re-identification!
huggingface.co/datasets/SinK…
Grzegorz Jacenków retweeted
Finally, MIMIC-IV-Note is what we've just released. Deidentified free-text clinical notes for everyone in MIMIC-IV; specifically discharge summaries (330k) and radiology reports (2.5m) - around 600 million tokens in the discharge summaries alone.
physionet.org/content/mimic-…
Grzegorz Jacenków retweeted
Currently seeking a software engineer to join my team working on AI for healthcare. If you're looking to work in a dynamic multidisciplinary environment on building transformative tools and technologies, this could be for you!
We are #hiring ! We have a fantastic #opportunity available for a Software Engineer to join our R&D centre of excellence in Edinburgh. To find out more and to apply, please go to: lnkd.in/eqEHYwXn We would love to work with you! #softwareengineer #medicalresearch
Grzegorz Jacenków retweeted
Please retweet widely. Looking for a postdoc in representation learning. We want to learn good representations with (causal) generative models with rare/imbalanced data. You will work with bright minds, on a prestigious grant and interact with industry. DM me for more info.
Grzegorz Jacenków retweeted
I'm very proud to say our paper "Sketched RT3D: how to reconstruct billions of photons per second" received the best student paper at @ieeeICASSP this year. Thanks to my co-authors @TachellaJulian and Mike Davies for their great work. Check it out here - ieeexplore.ieee.org/document…
Grzegorz Jacenków retweeted
(1/3) I am happy to share that our paper "Diffusion Causal Models for Counterfactual Estimation" will be presented next week at @CLeaR_2022. Check poster session 1 (11/04 - 4pm) or our 90s video! Huge thanks to @STsaftaris and the rest of the team at vios.science!
Hey #ISBI2022! Are you keen on learning how we can classify chest X-rays like radiologists?
Join the oral session tomorrow (30th March) in Multimodal Fusion at 5:30 PM (IST) / 12:00 PM (UTC) to learn more!
📄 arxiv.org/abs/2202.06076
🎮 github.com/jacenkow/mmbt
Join our group for an opportunity to contribute to the next generation of healthcare AI!
Please spread widely: PhD position in causality, representation learning and applications in healthcare. (funded by @CanonMedicalEDI @RAEngNews). Co-supervised by @alisonQoneil. Come and join @SnchzPedro_ @Xiaoliu33745946 @jacenkow and the VIOS team.
findaphd.com/phds/project/ca…
3
Grzegorz Jacenków retweeted
Please spread widely: Interesting in causality and in applications in healthcare. Looking for a PhD student (co-supervised with @ewenharrison) to join our group as part of @acrcedincare. findaphd.com/phds/project/ca…
A fantastic opportunity you can’t miss during the #MICCAI 2021! A glimpse into an exciting field of disentangled representation learning.
Learn about disentangled representations and medical imaging at the 2nd DREAM tutorial at #miccai2021. This edition, after hugely successful 1st run, has more speakers, causality, new models, practical examples, and notes. vios.science/tutorials/dream… @MICCAI_Society @MiccaiStudents
3
Grzegorz Jacenków retweeted
Monster survey out of our group on the risks of data leakage and privacy of ML models during inference. Thanks to @iCAIRD_Scot @CanonMedicalEDI, @RAEngNews for support. With @MarijaJegorova @MurraySmithRod @alisonQoneil @stucdubh, Charlie M & Chaitanya k. arxiv.org/abs/2107.01614
So imagine you can generate rare diseases or conditions at scale... mix different heart parts between patients to generate new example using disentangled anatomy arithmetic 🤯 #MICCAI2021
Our paper on performing arithmetic operations with disentangled *spatial* and *semantic* anatomical factors has been accepted in #MICCAI2021.
We investigate the use of this arithmetic in controllable cardiac image synthesis.
arxiv: arxiv.org/abs/2107.01748
8
Hot off the press! My fabulous colleagues (@Xiaoliu33745946, @spirosthermos) proposed the first method to combine meta-learning and disentanglement. Why? Better performance on unseen domains (e.g. images from different scanners or hospitals). arxiv.org/abs/2106.13292 #MICCAI2021
Grzegorz Jacenków retweeted
Another opportunity to join our amazing team - apply online or contact me directly for more information :)
We are recruiting for a Machine Learning Scientist in our Artificial Intelligence Research Team in Edinburgh. For more info and to apply directly, please go to: lnkd.in/dtwXg6a we would love to hear from you! #machinelearning #scientist #hiring
Grzegorz Jacenków retweeted
Hot off the press! Injecting expert knowledge via templates - an extension to our work on extracting labels from radiology reports using @iCAIRD_Scot data. Check out the paper here: mdpi.com/1046980 @MDPIOpenAccess @CanonMedicalEDI @DataLabScotland @StAndrewsCS
Our story was also published by @turinginst - turing.ac.uk/news/researcher…
I had a pleasure to collaborate with very talented people on the Hateful Memes Challenge organised by @facebookai and @drivendataorg. We ended up in the top 1%. Thank you @bertievidgen, @Elena_Kochkina, @harish, @alisonQoneil, @xrysoflhs, @HelenMargetts, and @STsaftaris!
1

























