Ruben Dörfel

As a junior researcher at a university that covers OA APCs in most conventional and top-tier journals, I have little incentive to not publish there. Morally, I would, of course, like to publish with non-profit orgs etc., but unfortunately, this is more expensive for me than publishing in Nature.

EurIPS includes a call for both Workshops and Affinity Workshops!
We look forward to making #EurIPS a diverse and inclusive event with you.

The submission deadlines are August 22nd, AoE.

More information at:
eurips.cc/call-for-wor...
eurips.cc/call-for-aff...

Updated my Python project setup guide - originally created for my students but might be useful for other researchers and data scientists. Covers pyenv, poetry, git, and project structure best practices. Open to suggestions for improvements.

rdoerfel.github.io/blog/2025/En...

Updated my Python project setup guide - originally created for my students but might be useful for other researchers and data scientists. Covers pyenv, poetry, git, and project structure best practices. Open to suggestions for improvements.

rdoerfel.github.io/blog/2025/En...

Similar setup here. Also looking for suggestions. Especially on something like report generation

Lol. Nothing more American than that.

Such a danish thing to do!

New article out at Human Brain Mapping showing that brain age ≠ brain ageing (estimating brain age on all available features).

This is not the only article showcasing this. Brain age is still useful, but be careful about the longitudinal claims.

doi.org/10.1002/hbm....

FOMO25 accepted at #MICCAI2025! 🚀

Excited to announce the first challenge at MICCAI focusing on the development of self-supervised pretraining of foundation models for brain MRI! 🧠

With access to a large-scale dataset, codebase, cash prices and multiple tracks.

Read more ⬇️

It happened to me earlier last year. We had to double-check with the editor that we understood correctly.

Prediction of brain age using structural magnetic resonance imaging: A comparison of clinical validity of publicly available software packages Predicting brain age from structural magnetic resonance images is commonly used as a biomarker of biological aging and brain health. Ideally, as a clinically valid biomarker, brain age should indicate...

I'm happy to share our latest pre-print on assessing the clinical validity of brain age as a biomarker of aging-related diseases and structural and memory decline in the brain!
www.medrxiv.org/content/10.1...
(1/7)

And of course, thanks a lot to all the great people involved: Brice Ozenne, @melanieganzben1.bsky.social , @jaralaus.bsky.social, and @pontusps.bsky.social (7/7)

This is still a work in progress, so I'd be happy to discuss our methods and results! Also, any feedback on the overview figure is welcome. (6/7)

Rather than relying solely on cross-sectional predictions, future studies could focus on longitudinal modeling to better capture aging-related changes. (5/7)

We found that baseline brain age performs similarly to grey matter volume in terms of diagnostic and prognostic performance and does not strongly correlate with clinical outcomes such as memory decline or gray matter atrophy. (4/7)

We evaluated six publicly available brain age prediction models using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) to assess their ability to differentiate clinical groups, predict disease progression, and track memory decline and gray matter atrophy. (3/7)

Brain age estimates from MRI have become increasingly popular in research involving neuroimaging. While often interpreted as an indicator of aging, it remains unclear if brain age reflects meaningful biological processes and associated changes. (2/7)

Prediction of brain age using structural magnetic resonance imaging: A comparison of clinical validity of publicly available software packages Predicting brain age from structural magnetic resonance images is commonly used as a biomarker of biological aging and brain health. Ideally, as a clinically valid biomarker, brain age should indicate...

I'm happy to share our latest pre-print on assessing the clinical validity of brain age as a biomarker of aging-related diseases and structural and memory decline in the brain!
www.medrxiv.org/content/10.1...
(1/7)

Screenshot of the Imaging neuroscience paper linked above

Remember the whole #narps (www.narps.info) splash?

We are very interested in how to utilize the multiverse in neuroimaging. Because no matter how we process biological data, if we do something reasonable, the underlying results shouldn't change too much - because biology doesn't change, right?

Prediction of brain age using structural magnetic resonance imaging: A comparison of clinical validity of publicly available software packages Predicting brain age from structural magnetic resonance images is commonly used as a biomarker of biological aging and brain health. Ideally, as a clinically valid biomarker, brain age should indicate...

Prediction of brain age using structural magnetic resonance imaging: A comparison of clinical validity of publicly available software packages

Led by @rdoerfel.bsky.social

doi.org/10.1101/2025...

Hier das Fazit - aber wie immer: So eine Grafik erzählt nicht die ganze Geschichte, schaut rein und guckt die Quellen an - überprüft gern alles selbst.

Ah yes. I think I got it:
\delta_{x_i} is centered / has zero mean.
So with \mean(\delta_{x_i) = 0, we get:
E(\delta_{x_i}^2) = E( (\delta_{x_i}-\mean(\delta_{x_i}) )= Var(\delta_x)

I see. And we can't estimate it directly anyway.

Anyhow, I have a question regarding equation (7). I'm somehow missing the link between E[\delta_{x_i}^2] = Var(\delta_{x}).

If I'm not mistaken, if we take \hat{x_i} as the mean, we get for E[\delta_{x_i}^2] = E[(xi-\hat{x_i})^2] = Var(X).

Great paper! I very much like the idea of the generative model for distinct modes. Whether the subject-specific aging rate is constant over time might be debatable though.

In vivo medical imaging for assessing geroprotective interventions in humans - GeroScience There is a growing interest in developing drugs with a general geroprotective effect, aimed at slowing down aging. Several compounds have been shown to increase the lifespan and reduce the incidence o...

Great review by Svensson et al. on how to systematically evaluate geroprotective interventions in humans!

link.springer.com/article/10.1...

1/3

#Longevity #AgingResearch #Medicine #Science

Effective geroprotective interventions must demonstrate effects across multiple physiological systems simultaneously. Single measurements are insufficient - comprehensive assessment is essential. If there is a general geroprotective effect, we should see it in multiple sites. 3/3

The authors review aging-related pathologies and well-established ways to measure them. For most diseases, well-validated protocols that are used both clinically and by pharmaceutical companies exist, and the infrastructure is readily available in most modern hospitals. 2/3

In vivo medical imaging for assessing geroprotective interventions in humans - GeroScience There is a growing interest in developing drugs with a general geroprotective effect, aimed at slowing down aging. Several compounds have been shown to increase the lifespan and reduce the incidence o...

Great review by Svensson et al. on how to systematically evaluate geroprotective interventions in humans!

link.springer.com/article/10.1...

1/3