Ana Matoso

Interested in learning more about the role of AI in the clinical workflow of glioma management?

Then make sure to sign up for our next webinar on November 14th at 12h00 CET.
Register now at tinyurl.com/5n8avrcn

Add this event to your calendar: tinyurl.com/7zj4mhmm

Universities are embracing AI: will students get smarter or stop thinking? Millions of students arriving at campuses are now using artificial intelligence. Worries abound.

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

It's on days like these when @awscloud.bsky.social is down that I realize:
1) how many websites rely on it
2) that we should be grateful for @waybackmachine.bsky.social
3) that in sensitive/critial scenarios, on premise solutions are better as you are not reliable/waiting on a third party to fix it

Music-Based Magnetic Resonance Fingerprinting to Improve Patient Comfort During MRI Exams The unpleasant acoustic noise is an important drawback of almost every magnetic resonance imaging scan. Instead of reducing the acoustic noise to improve patient comfort, a method is proposed to mitig...

If you ever done an MRI you know about all the weird sounds it makes. Well, weird no more!

There's a sequence (MRF-Music) that makes the sounds you hear during an MRI to play at the beat of any song you want. This will make the exam much more tolerable and confortable
Link: tinyurl.com/bdhwnsak

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🧵

After the long wait, GliMR gets together once again! 🎊

We are organizing a full day of activities for the Pre-Conference day of #ESMRMB25 on October 8th.
🌍 It will take place at Palais du Pharo in Marseille, France, from 9h-17h.

Register now at esmrmb2025.mycongressonline.net

New paper in Imaging Neuroscience by Marta Xavier, Patrícia Figueiredo, et al:

Consistency of resting-state correlations between fMRI networks and EEG band power

doi.org/10.1162/IMAG...

New paper in Imaging Neuroscience by Catarina Domingos, Patrícia Figueiredo et al.:

Cerebrovascular reactivity mapping using breath-hold BOLD-fMRI: Comparison of signal models combined with voxelwise lag optimization

doi.org/10.1162/IMAG...

There, I presented a poster, having won a best poster award. I'm grateful for this recognition of our work, and so I would like to thank the organizing committee for this award.

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.

And you can't visit Honolulu without doing 2 things: catching a lot of sunsets, and doing the Diamond Head trail (171m elevation, avg 8.6% incline)- which, with the "warm-up" of doing the Lulumahu Falls trail (avg 20% incline) before, was quite easy and worth it for the view of the city.

Last week, I attended the @ismrm.bsky.social Annual Meeting in beautiful Honolulu, Hawai'i with my colleagues from @isrlisboa.bsky.social. There, I presented a pitch and a poster on my PhD work titled "Prediction of treatment response in a longitudinal glioblastoma dataset using deep learning".

Deep learning can help with glioblastoma prognosis. Ask your questions to @anamatoso.bsky.social at her power pitch and digital poster "Prediction of treatment response in a longitudinal glioblastoma dataset using deep learning". 13:50, Theater 1, computer 19.

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

YouTube video by ISR Lisboa CNN Inovação | ISR-Lisboa

We're happy to share the latest episode of CNN INOVAÇÃO, which showcases our activities at #ISRLisboa. 🦾

Get to know different groups and projects, from the voice of our team, motivated to bring forth the vision of this @istecnico.bsky.social research unit. 🙌
🔗 www.youtube.com/watch?v=MBkl...

After almost 1.5 years working on deep learning applied to medical imaging, a colleague of mine told me about this website that lets you create incredible figures of neural networks.
Just comes to show how you never stop learning and how important it is to share your work
alexlenail.me/NN-SVG/

Mais do que ser bem sucedida na qualidade, consegue reavivar o que havia há +10 anos atrás de só haver 1ep/semana, o que nos faz ansiar e conspirar tudo com todos.
Já revi a série desde o início, e acho que vê-la em binge watching não lhe faria jus, é preciso digerir cada ep, pq tudo ali foi pensado

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.

Too many papers are written on AI tools for medical imaging from a computer science perspective and without the clinical application in mind.

🧵 3/3
And so perhaps it's time we reassess the target metrics of our models so that they are more aligned with the reality of medical practice, where reliability is just as important if not more, than accuracy.

It all comes down to trust.

🧵 2/3
It cannot be understated that, especially in a medical context, robustness is crucial for both risk assessment and for the comparison of different solutions.

As such, it should be reported on.
However, we need to be wary, because significance can be easily achieved with big enough data.

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

Congratulations Genevieve and team! 👏

4/4 🧵 - On phronesis pt2

"It has to be open to challenge. Understanding what it is to live well with others and what we owe to one another — that conversation can’t ever stop. And so I’m very reluctant to pursue the development of machines that are designed to find an optimal answer and stop there"

🧵3/4 - On practical wisdom (phronesis)

"I think if we had a truly moral machine (...) It would be able to articulate reasons and appreciate our reasons, and negotiate those reasons with us in a way that wasn’t just mirroring the consensus that we’d already reached."

🧵2/4 - On the quality of the training data:

"I’ve been skeptical about the moral machines project, because it usually ends up just trying to crowdsource moral judgments [and train AI on those human intuitions] — but the whole point is that the crowd isn’t always right!"

🧵1/4 - On our interaction with LLMs

"When we engage with it, we’re a lot like Narcissus, the mythical boy who sees his beautiful reflection in the water and becomes transfixed by it, thinking it’s another person."

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.

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...

YouTube video by Instituto Superior Técnico Debate com candidatos aos Órgãos do Técnico

Quero agradecer aos responsáveis pelo canal de youtube do @istecnico.bsky.social cujo trabalho tem aumentado de qualidade e tornado a democracia no técnico mais transparente e aberta. Exemplos como este vídeo são bem vindos e espero que no futuro mais divulgados
www.youtube.com/watch?v=5m7T...

I have recently changed to @ente.io for my 2FA codes, which is an open-source app and, besides the countdown, they show what the next code will be. No more time wasted waiting for the timer to change the code.