Ana Matoso

@anamatoso.bsky.social

PhD student in Biomedical Engineering @ ISR-Lisboa and Hospital da Luz. Working on AI applications in glioma MRI

To whoever works in a PT university, FCT/FCCN has a platform that enables the use of different AI models without the common use limits: www.iaedu.pt/pt Now they have, gpt4o, o4mini, 4o with search and mistral large. Very nice to see this push in AI democratization, but I have some caveats. 1/4🧵

IAedu FCT | IAedu

O IAedu é a plataforma desenvolvida pela FCCN, serviços digitais da FCT, que democratiza o acesso à inteligência artificial no ensino superior e investigação em Portugal.

iaedu.pt

Great article discussing the use of AI in schools www.nature.com/articles/d41... I view tools like ChatGPT like the creation of the calculator or of the computer. They greatly simplified our work, but we need to understand them to work with them so that we can do more complex things in the end

Universities are embracing AI: will students get smarter or stop thinking?

Millions of students arriving at campuses are now using artificial intelligence. Worries abound.

nature.com

Anyone who works with MRI will tell you MRI scientists are very imaginative with naming. Some examples include: CAIPIRINHA and FIESTA (acquisition techniques) and FLIRT and MELODIC (analysis tools) just to name a few. And this week I just learned a new cool one 1/2🧵

Last week, I attended the 2nd Annual Meeting of the #Net4Brain COST Action in Bucharest. It featured numerous multidisciplinary talks, ranging from liquid biopsies to MRI, all applied to brain cancer. It was a wonderful opportunity to (finally) see colleagues in person and to meet new ones.

BildBild

GliMR will be at #ESMRMB25 In addition to joining us in the Precongress Day on October 8, make sure to submit your ESMRMB25 abstract to the GliMR ESMRMB Working Group to present your latest findings at the ESMRMB GliMR Session of ESMRMB25! Want to know how? See the🧵 Deadline is May 16, 17:00 CEST

Bild

Interested in ASL? Several GliMR members are organizing an amazing workshop! It will provide theoretical aspects of ASL and practical workshops on data processing and analysis using ExploreASL. You can find more details here: tinyurl.com/ASLLis. The workshop is free, but registration is required.

Bild

Very nice paper on how, in the race for SoTA results, it appears that we have fallen into a peculiar trap: only reporting the peak/average performance thus overlooking the variability of the results. I hope this paper becomes an eye-opener for those who work in AI in Healthcare. 🧵 1/3

Curt Langlotz@curtlanglotz.bsky.social · 2y ago

Love this. Bold face numbers in a table don't cut it: "For >60% of papers, the 2nd-ranked method was within the CI of the 1st-ranked method. Current publications typically don't provide sufficient evidence to support which models could be translated into clinical practice" arxiv.org/abs/2409.17763

Great interview on how we perceive AI and on the morality of using it for decision-making. As an engineer, I find it important (and refreshing) to listen to philosophers talking about this to be able to see it from a different lens Some favourite quotes in 🧵 www.vox.com/future-perfe...

Shannon Vallor says AI does present an existential risk — but not the one you think

AI is not a “stochastic parrot,” It’s a mirror, says the philosopher.

vox.com

Doing science is about perseverance, about showing up and not be deterred by bad outcomes and sometimes about building creative solutions. Thus, small wins should also be celebrated. Much like wordle, where today was a good day Wordle 1252 2/6 ⬛⬛🟩🟩🟨 🟩🟩🟩🟩🟩

Some incredible images of the human brain using a 11.7T MRI scanner. It can do a T2* image with 0.19×0.19×1 mm3 resolution 🤯 Images like this make me think of the law of diminishing returns: is it worth replacing a 3T scanner with this one in the clinic? shorturl.at/M90aT

In vivo imaging of the human brain with the Iseult 11.7-T MRI scanner - Nature Methods

In a technological tour de force, a whole-body 11.7-T MRI scanner has been developed. Here images of the human brain are presented while safety for the imaged human volunteers has been ascertained.

nature.com

An important distinction needs to be made here. It's great that @bsky.app says they won't use our data to train GenAI (not to say they won't ever, but that's for another day). But this doesn't mean that other companies won't. Don't be fooled: every post is for sure being scrapped by somebody else.

Bluesky@bsky.app · 2y ago

A number of artists and creators have made their home on Bluesky, and we hear their concerns with other platforms training on their data. We do not use any of your content to train generative AI, and have no intention of doing so.