Radiology -- too many scans. Are we losing the art of physical exam in medicine? Are medical students taught physical exam thoroughly or just which tests to order? Enjoy this fun video 😀

Radiology reading room - feel free to meme

Radiology reading room

Was curious how LLMs such as Chat GPT and Grok 3 were interpreting medical imaging scans such as MRI, CT, X-ray, etc.. so I asked them directly 😀 It seems Chat GPT is using : Visual Feature Analysis: (LLM-based reasoning, not CNNs) 1. Pattern recognition: Based on training with many labeled examples (text-image pairs) 2. Medical knowledge: Reasoning using anatomical, pathological, and radiological concepts. They are not using convolutional neural networks (CNNs) like some established radiology AI tools. This is really interesting because they are learning by associating images of scans with associated descriptive text, I assume from digitized books or reference articles when the LLM is trained. This is similar to how basic book knowledge is obtained by radiology residents. They LLM's should eventually get better and learn to diagnose textbook medical cases consistently. In clinical practice, majority of the cases are not "classic" textbook cases, whether you have to infer a novel concept or diagnose with artifact/suboptimal images. This is where practical knowledge is gained in residency and with experience. It is definitely possible the LLMs can make this leap as well...very interesting times.

Another interesting scenario for LLMs interpreting MRI medical scans is that the output can change. Here is MRI of basal ganglia abnormality. It gets it right on the first shot, but when asked again, it clearly hallucinates and thinks that it is looking at a car instrument panel showing low tire pressure. Still early days yet, but very interesting!!

Here are some sample tests of gpt 4.5 and grok 3 trying their interpretive skills on brain MRI. They both accurately nail the large stroke. However it is somewhat of a black box in how they arrived at the interpretation when you ask it to annotate the abnormality. As a radiologist I've been playing with these LLMs since the beginning. It's impressive how far they have advanced in the last 6 months. Really fascinating stuff - this is rapidly accelerating!!

Computer vision for medical scans is still very early but will be interesting where it goes As a radiologist myself I have been playing with some of the LLMs, still not there yet. Think computer vision for medical scans can be solved but maybe needs CNNs rather than LLMs similar to full self driving

Made a fun song/video for Radiology. It's called "Just read fast...and don't miss that bleed" It's for all us radiologists who have to read CT scans, MRI scans, imaging super fast in this radiologist shortage. Hope you enjoy and have a laugh!

Cavum Velum Interpositum Epidermoid Cyst This is one you don't see often! #Neurology #neurotwitter #neurosurgery #MedEd #MedTwitter #radtwitter #radiology @TheASNR #neuroimaging #neuroradiology @RSNA #futureradres #RadRes #FOAMed #FOAMrad #neurorad

Any physicians tired of all the bogus quality metrics and measures that we have to endure to get paid properly - Such as CMS MIPS (merit based incentive payment system) and other quality metrics put in place by health systems or employers?? It seems like every year they take the old metrics out and put new ones to make it harder and more onerous to meet. Some of the metrics are gamed so badly that even if you meet 99.9% you can be still in the lowest quartile and potentially incur a penalty. Time to push back and give more time for actual patient care rather than wasting time to make your metrics look good on a spreadsheet so you can get adequately compensated by some middle man! This song is for you!!

My fun conversation with grok as we interpret a brain MRI together x.com/i/grok/share/xW9hNmoIt…

patient: I fell ED: CT scan patient: I have chest pain ED: trops and then CT scan patient: I- ED: CT scan

US national debt crisis in song form. Maybe DOGE can turn the tide?

They said AI would take over radiology, but here we are now with a radiologist shortage #Neurology #neurotwitter #neurosurgery #MedEd #MedTwitter #radtwitter #radiology @TheASNR #neuroimaging #neuroradiology @RSNA #futureradres #RadRes #FOAMed #FOAMrad #neurorad

To solve Radiology image interpretation, a computer vision problem, we may need CNNs more than LLMs. Just like the FSD problem there are so many edge cases in terms of image acquisition as well as novel situations which requires some intuition without prior specific training in that context. So maybe a combo of CNNs to get the computer vision part to 99% and LLMs for the fund of knowledge (text based).

Grok not letting me test out MRI skills - is it restricted?? x.com/i/grok/share/xY2gyiuXK…

Also seen in the same week as the rare case of Rosai-Dorfmann intracranially. This was LCH - Langherans cell histiocytosis CT shows the beveled appearance of calvarium MRI shows the scalp, calvarial, and dural involvment #Neurology #neurotwitter #neurosurgery #MedEd #MedTwitter #radtwitter #radiology @TheASNR #neuroimaging #neuroradiology @RSNA