BRATS Africa: Building Inclusive AI in Radiology
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Intro-From the RSNA, this is the Radiology Artificial Intelligence Podcast.My name is Paul Yi, and I'm a radiologist and co-host of the podcast.And my name is Ali Tejani, and I'm a radiologist and co-host of the podcast.Each month, we dive into the hottest topics in radiology AI and talk with leading experts, thought leaders, and movers and shakers in the field.Dr. Ali Tejani-Welcome back to the Radiology AI Podcast.Paul, you know, it's been a while since we've been together to record one of these episodes.How have you been?I feel like I haven't seen you in a while.Dr. Paul Yi-No, I've been doing pretty good.You know, summer, it's been pretty hot, but I like the sun and getting out when I can.How about you?Dr. Ali Tejani-Yeah, about the same.Pretty sunny where I just moved out to, so can't complain.Wish I would travel more, though.I definitely need to travel and, you know, I figured, while we're not able to make it out to some exciting places, maybe we can talk to a couple of friends who've had some exciting experiences and we can live vicariously through their experience. Dr. Paul Yi-Whatever could you mean?Dr. Ali Tejani-Well, let's ask them.Let's find out.So we have a couple of guests here.Udonna, can you start by telling us more about yourself and where you are and what you're doing?Dr. Udunna Anazodo-Yeah.Thank you so much for having me here.My name is Udunna and I'm based in Montreal.It's sunny right now.We've had a little bit of a, well, I say summer spell, and that's nice.But a couple of weeks ago I was in Nigeria, I was in Lagos, Nigeria as well, doing some work, which we're going to get into today.But my main aim and focus is sort of creating really exciting ways to image the brain without contrast, which I do every day at the Montreal Institute at McGill University, which is where I'm based.Dr. Ali Tejani-Fantastic.So I haven't been to Canada, so again, already living through your experiences there.Marouf, how about yourself?
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it