1/11 The poll has ended: 53% (scan time) vs 47% (sample size)! Here's our in-depth take on brain-wide association studies (with a 134-page supplement!): biorxiv.org/content/10.110… Led by Leon Ooi Csaba Orban, there are a few twists, so do read till the end! Our previous study ...

Wow, with the new UK Biobank rules, the dataset has just become way too expensive for the kind of computationally intensive work my lab does...

I did a quick estimation, and our connectome resource would have required up to 30,000 GBP to compute on RAP! Considering that similar computing resources are provided by research institutes worldwide, the centralized approach being enforced seems irrationally complicated!

New paper in Imaging Neuroscience by Naren Wulan, B.T. Thomas Yeo, et al: Translating phenotypic prediction models from big to small anatomical MRI data using meta-matching doi.org/10.1162/imag_a…

‼️ Paper alert ‼️ Our paper, “DeepResBat: Deep Residual Batch Harmonization Accounting for Covariate Distribution Differences”, has been published in Medical Image Analysis! Thomas Yeo Juan (Helen) Zhou @AgingMACC doi.org/10.1016/j.medi…

This paper led by Lijun AN | 安丽军 is out in Medical Image Analysis! sciencedirect.com/science/articl…

Super excited about our revised study! 4 more datasets showing robustness across fMRI sequences, racial groups, disorders, lifespan, phenotypic domains & resting/task FC: doi.org/10.1101/2024.0… Leon Ooi Shaoshi Zhang Csaba Orban broke the lab's record with a 76-page response!

Check out the latest update on our study! We dive into the nuances of the tradeoff between scan time and sample size in BWAS analyses. A special thanks to all the coauthors who contributed their datasets to make this possible!

Promising tool to explore sample size and scan time for boosting individual-level prediction accuracy! Do check it out !

🚨 Predicting Alzheimer's Progression 🚨 A thread 🧵 1/ Accurate prediction of Alzheimer’s progression is critical for early intervention. How can we make predictions more precise and generalizable? 🧠✨ 📝 Read the preprint led by Chen Zhang : doi.org/10.1101/2024.1…

🚨 Brain Age vs Direct Models in Alzheimer’s disease (AD) 🚨 A thread 🧵 1/ Brain age is a powerful indicator of general brain health, trained on massive datasets. But does this translate to better prediction for specific outcomes, like AD? Preprint by Trevor Tan :

Thrilled to share our latest work on the importance of considering social identities in brain imaging research, now out in Nature Neuroscience. rdcu.be/d4XWM

Thanks to everyone's feedback, we have updated our calculator to optimize sample size N & scan time T for fMRI studies. The first new feature is that users can explore how different N & T leads to different accuracy, e.g., N=1000 & T=30min => 81% accuracy.🧵

1/ Excited to share our latest preprint! 🚀 We introduce Spectral Normative Modeling (SNM)—a novel approach leveraging graph spectral methods to advance brain charting towards personalized precision medicine. 🔗medrxiv.org/content/10.110….

🚀 Explore Spectral Normative Modeling in action! We’ve built an interactive visualization showcasing high-resolution normative reference ranges generated via SNM. 🔗 Try it here: sina-mansour.github.io/normative_brai…

It's finally here! Use the Network Correspondence Toolbox to help interpret your neuroimaging findings 🧠 nature.com/articles/s4146…

While the world burns, we cook up a new preprint! doi.org/10.1101/2025.0… Biophysical modeling is a key tool to derive mechanistic insights into the brain. These models are governed by biologically meaningful parameters (unlike deep neural nets), but the dirty secret ... 1/N

(1/10) How do brain networks and cognition co-evolve as children enter adolescence? While valuable, cross-sectional studies offer only a single snapshot of brain–cognition relationships, missing the dynamic changes that longitudinal designs can reveal. We hypothesize that

1/11 Excited to share our @Naturestudy led by Leon Ooi Csaba Orban Shaoshi Zhang doi.org/10.1038/s41586… It is well-known that AI performance scales with logarithm of sample size (Kaplan, McCandlish 2020), but in many domains, sample size can be # participants or # measurements...

Nature Longer scans boost prediction and cut costs in brain-wide association studies nature.com/articles/s4158…