Simon Eickhoff
News & Views on Brain mapping | Machine-Learning | Translational Neuroscience. And triathlon
Director INM-7 FZ Jülich; Professor for Systems Neuroscience HHU Düsseldorf
- Our #metaanalysis (n = 231) in JAMAPsych reveals consistent brain abnormalities across #sleep disorders involving affective and cognitive hubs in sgACC, amygdala/hippocampus Short-term sleep deprivation shows a distinct picture, affecting the thalamus jamanetwork.com/journals/jam...
- NOW, Join if you're interessted Topic: DGKN Hackroom 2025 — Tool Talks Time: Mar 14, 2025 10:30 - 12h fz-juelich-de.zoom.us/j/6792251876... Data Management: 10:30 – 11:00 Datalad: GPDR conform collaboration Jtrack: remote wearable assessment
- Analysis Methods: 11:00 – 11:30 Harmonize: Leakage in data harmonization JuSpace: cross-modal brain map correlation Applied Concepts: 11:30 – 12:00 Causal modeling for Confounds in ML Subtypes of major depression
- The limiting factor for MRI based prediction of behavioral traits may be neither the imaging nor the pipeline or learning algorith but rather the reliability of the target phenotypes Thought provoking work my Martin Gell et al: www.nature.com/articles/s41...
- [Not loaded yet]
- Fully agreed. This adds another layer of complexity We likely need to differentiate three aspects here - "True" changes of the trait - State-changes due to, e.g., sleep - Measurement error All three can and will superimpose
- [Not loaded yet]
- In my view, the take-home message is slightly different from the BWAS paper. The latter argued you need large N. This paper shows that if your target is unreliable, even very large numbers can’t save you Also, association vs prediction
- This is what happens if preprints are treated as „scientific literature“ Don’t get me wrong, I am all for preprinting. But unfortunately, it is often ignored that anybody can preprint anything
- Looked into BlueSky a while ago… really empty at that time X becoming useless for interesting reads and discussions on science send me in a social-media hiatus Back now and excited about things to come
- Love the started-packs. What seems really missing yet is „machine-learning in Neuroimaging / brain medicine“ 🧠 If you work in that (or a related) field introduce yourself below. I will put together the list Please share widely to reach all newcomers 🙏🏽
[Not loaded yet]- 🙋♂️🍻
- We are looking for a community manager and development coordinator for DataLad !! The full description with contact info is at: files.inm7.de/mih/position...
- Spread the word 📣 Announcing the first BrainHack at the DGKN meeting next month !! After being a staple at OHBM, this will be the first hackroom at a German (clinical) neuroscience meeting Enjoy the spirit of open science with tutorials, hackathons and an unconference 🔜 Join us in Frankfurt
- Somehow it seems that computational models were immune to the current sample-size worries in #neuroimaging Turns out they are not 😱 DCM models and connections need 100+ subjects to give stable results New work by Alexander Silchenko & Felix Hoffstaedter: onlinelibrary.wiley.com/doi/10.1002/...
- [Not loaded yet]
- [Not loaded yet]
- Ju = Jüliche 😅
- Finally in the public 🚀 JuLearn: an easy-to-use library for leakage-free evaluation and inspection of ML models JuLearn is an open-source Python library simplifying the entry into the ML world -> design & evaluate ML pipelines without encountering common pitfalls arxiv.org/abs/2310.12568
- [Not loaded yet]
- It got a bit chilly in the end, but given that it is already mid-October… 😊
- Fantastic but very worrisome work by Sami Hamdan: Confound removal in machine learning can itself lead to leakage -> After information about the target from the features using standard approaches you can STILL predict it well academic.oup.com/gigascience/... #neuroskyence #MLSky #neuroimaging
- Finally out 🎉 - our meta-analysis of 403 neuroimaging studies on language (1/3) In addition to providing robust evidence on the engagement of classical language regions during language tasks, we also investigated the processing of linguistic subdomains: semantics, syntax, phonology and pragmatics!
- Link to the paper in the final part of the thread (or rather, my moderately successful first try of a BSky thread) bsky.app/profile/sbe.... #neuroskyence #neuroimaging #PsychSky #cogpsyc #SciSky #lingsky
- Finally out 🎉 - our meta-analysis of 403 neuroimaging studies on language (3/3) Quite some functional specialization in subcortical areas, too. This and many more details can be found here: psycnet.apa.org/fulltext/202... Paper is open access !!
- Finally out 🎉 - our meta-analysis of 403 neuroimaging studies on language (3/3) Quite some functional specialization in subcortical areas, too. This and many more details can be found here: psycnet.apa.org/fulltext/202... Paper is open access !!
- [Not loaded yet]
- Still learning this thing here 😅 Thanks !!
- Finally out 🎉 - our meta-analysis of 403 neuroimaging studies on language (2/3) We ended up discovering truly subdomain-specific brain areas in spite of substantial covergence Functional specialization was most pronounced in the cortex but we also found considerable cerebellar effects
- [Not loaded yet]
- I am not alone 😄 Seriously, how can you deliberately miss out on the little dopamine rush every time you get to zero ☺️
- Just wondering, am I the only person living (and loving) inbox-zero for years? I use my inbox as a todo list and make extensive use of „defer / put back“. Works amazing and each time I am back to empty it feels rewarding
- A main goal of our institute is to provide open software & resources - DataLad (data-management) - JTrack (mHealth / wearable suite) - JuLearn (user-friendly ML library) - ANIMA (meta-analyses results) - JuSpace (MRI-PET integration) - many more... Full catalogue: www.fz-juelich.de/en/inm/inm-7...
- Pitching skeptical views on #neuroimaging and machine-learning at the rating-state Brain conference. That meeting fully reflected my split feelings at the moment. The conference was stimulating, meeting colleagues was fun and discussions exciting. But travel is simply annoying
- My (likely) last paper in Neuroimage: A systrematic evaluation of ALE meta-analyses for morphometric data, i.e., Anatomical Likelihood Estimation. www.sciencedirect.com/science/arti...
- Interested in research data management, git-annex and DataLad Need to get your #neuroscience data organized? Need to deal with distributed data, provenance tracking or pipeline management? Join us at distribits in Düsseldorf - easy travel & great beer fosstodon.org/@distribits/...
- [Not loaded yet]
- [Not loaded yet]
- In my view, science Twitter was always OK. Pointed opinions are fine But since blue-tick crypto, click-bait and „you are using Chat-GPT wrong, follow me for more advice“ accounts totally took over timelines, signal-to-noise became really poor
- [Not loaded yet]
- Actually, emotion and cognition may not be so separate after all. There are phenotypic correlations and a shared genetic component. Anatomically, the key zone of convergence seems to be the superior frontal cortex. More details: www.sciencedirect.com/science/arti...
- [Not loaded yet]
- I would always prefer bioArxiv, the ability to read a html-Version is a massive plus. In particular on small screens. Looking at a pdf from PsyArXiv on a mobile is no fun
- Not sure, how many are here already to whom this would be of interest, but I‘ll try All others, please share 🙏🏽 We are currently considering to strengthen open (#neuroimaging) science in the German clinical societies like DGKN, DGPPN etc. Would you like to contribute / engage / help ?
- What a tour de force on personality factors, brain health & #neuroskyence: www.nature.com/articles/s44... Includes relationship with multiple diseases, analysis of modulating factors and #neuroimaging Large sample and long follow-up. But why use items as proxies rather than actual Big-5 scores?
- [Not loaded yet]
- Feels like X without all the spam. Looking forward to the new experience 👍🏼
- [Not loaded yet]
- Great idea, thanks! For the still fully naive newbies: how do you post to this feed?
- [Not loaded yet]
- Guess we are all new to this… but it can’t be worse than what Twitter has become (at least for me)
