Peter MacMahon

Thank you @theajnr. Our study has the potential to be particularly impactful in those health systems with a limited out-of-hours MRI service. CT can effectively distinguish between cases requiring urgent intervention and those that can be managed conservatively. @HSELive

@bhwords @nelson_piercy This is too complicated. The standard of care in the non-pregnant population is CT (if appropriate), not venous ultrasound or V/Q. Radiation dose in pregnancy should no longer be a significant factor.

Diagnosis of VTE in pregnancy @nelson_piercy gives a stellar talk describing the difficulties of diagnosing PE in pregnancy

The continuing AI revolution- 2024 looks set to be an important period in the growth of #AI use in #Irish healthcare medicalindependent.ie/in-the-news/ne… @TheMaterFoundat @uniofgalway @eHealthIreland @Slaintecare #mater #artificialintelligence #ehealth #digitalhealth #medtech #MedEd

Of course the lead author Ciara Gillespie deserves nearly all the credit for completing this remarkable work! @fniainle @mwrowan @FerdiaBolster @UCDMedicine @EurRadiology @radiologyirl @drjendonnelly @MaterTrauma @HSELive @ThrombosisIrL

🎉A heartfelt thanks to all involved in our OPTICA study, just published in European Radiology. which validated the safety of low-dose CT in pregnancy 🙏 Special gratitude to 113 pregnant Irish women who participated. Your contribution was invaluable in advancing care for others

The Mater Misericordiae University Hospital in Dublin has announced that it has become the first hospital in Ireland to use Artificial Intelligence across its radiology department rte.ie/news/health/20…

I don't talk much about this - I obtained one of the first FDA approvals in ML + radiology and it informs much of how I think about AI systems and their impact on the world. If you're a pure technologist, you should read the following: There's so much to unpack for both why Geoff was wrong, and why his future predictions should not be taken seriously either. Geoff made a classic error that technologists often make, which is to observe a particular behavior (identifying some subset of radiology scans correctly) against some task (identifying hemorrhage on CT head scans correctly), and then to extrapolate based on that task alone. The reality is that reducing any job, especially a wildly complex job that requires a decade of training, to a handful of tasks is quite absurd. Here's a bunch of stuff you wouldn't know about radiologists unless you built an AI company WITH them instead of opining about their job disappearing from an ivory tower. (1) Radiologists are NOT performing 2d pattern recognition - they have a 3d world model of the brain and its physical dynamics in their head. The motion and behavior of their brain to various traumas informs their prediction of hemorrhage determination. (2) Radiologists have a whole host of grounded models to make determinations, and actually, one of the most important first order determination they make is whether there is anything notably wrong with a brain structure that "feels" off. As a result, classifiers aren’t actually performing the same task even as radiologists. (3) Radiologists, because they have a grounded brain model, only need to see a single example of a rare and obscure condition to both remember it and identify it in the future. This long tail of rare conditions to avoid missing is a large part of their training, and no one has any clue how to make a model that acts similar in this way. (4) There’s so many ways to make Radiologist lives easier instead of just replacing them, it doesn’t even make sense to try. I interviewed and hired 25 radiologists, whose primary and chief complaint was that they had to reboot their computers several times a day. (5) A large part of the radiologist job is communicating their findings with physicians, so if you are thinking about automating them away you also need to understand the complex interactions between them and different clinics, which often are unique. (6) Every hospital is a snowflake, data is held under lock and key, so your algorithm might not work in a bunch of hospitals. Worse, the imagenet datasets have such wildly different feature sets they don’t do much for pretraining for you. (7) Have you ever tried to make anything in healthcare? The entire system is optimized to avoid introducing any harm to patients - explaining the ramifications of that would take an entire book, but suffice to say even if you had an algorithm that could automate away radiologists I don’t even know if you could create a viable adoption strategy in the US regulatory environment. (8) The reality is that for every application, the amount of specific and UNKNOWABLE domain knowledge is immense. LONG STORY SHORT: thinkers have a pattern where they are so divorced from implementation details that applications seem trivial, when in reality, the small details are exactly where value accrues. Should you be worried about GPT5 being used to automate vulnerability detection on websites before they’re patched? Maybe. Should you be worried GPT5 is going to interact with SOCIAL systems and destroy our society single-handedly? No absolutely not.

Coming soon:

Should we stop injecting particulate corticosteroids in and around the spine? Our invited review in @SkeletalRadiol may be of interest to all who perform epidural steroid injections. @MaterRadiology @UCDMedicine rdcu.be/cW9me

@irvinederm Needs proper study. From the paper referenced on poster: "increased fluoroscopy use was not associated with an increased breast cancer prevalence." "We also did not detect an increased breast cancer risk by radiation exposure group or specialty type"

Must also apply to vascular and IR colleagues Striking and concerning finding

Radiology and the Climate Crisis, a #RadInTraining author interview. Dr. Buckley, radiology resident summarizes his @radiology_rsna article pubs.rsna.org/doi/abs/10.114… youtube.com/user/Radiology…

Congrats to Mater Radiology Spr Bryan Buckley who provides a thought provoking perspective about medical imaging data storage and climate change in the prestigious journal Radiology. @MaterTrauma @UCDMedicine @IrishDocsEnv @HSELive @HSE_DA @HSE_NIMIS @radiology_rsna @UCDCompSci

@MaterJobs are currently looking for a Research Fellow in Artificial Intelligence. Please apply at the link below or click on our careers page for more information. #ArtificialInteligence #jobfairy #materhospital mater-hospital.rezoomo.com/job/18475/

Interested in medical imaging, anatomy, AI? We in @MaterTrauma @MaterRadiology are looking for a research fellow to work with @UCDCompSci and @IBMWatsonHealth for the next 3 years, and help develop AI algorithms to automatically analyse trauma CTs! Advert link retweeted below

@drfranok @ross_moy @FerdiaBolster Yes definitely can be done. Quite good imaging possible. Probably do CT of needle to confirm securely in marrow first. Not sure how modern contrast pumps, that are very good at detecting pressure problems with intravenous use, would respond though.

"Multiphase CT Angiography: A Useful Technique in Acute Stroke Imaging—Collaterals and Beyond" | #NeuroRad bit.ly/3lhpYyq

Dr Hare stressed how #imaging has been vital for making a quick #COVID19 diagnosis to help hospital triage, given swabs can take 24-48hrs, with up to 1/3 false negatives. #RCRTalks

Check out our paper on image-guided corticosteroid injections during the lockdown phase. Important read to plan for the next phase @SkeletalRadiol @intskeletal @MGHImaging @cychang1414 rdcu.be/b9AD2

@MaterStroke @MaterTrauma @Irishheart_ie @MaterRadiology Would be a nice addition to the Mater's Emergency Radiology service! Nice companion to our portable CT Could possibly, maybe, make sense in Ireland given relatively limited access to MRI for ED patients. USA experience discussed below hyperfine.io/events/portabl… @HyperfineR

Portable MRI scanners for stroke care not too far away? youtu.be/4TDzY02mg4E @MaterTrauma @Irishheart_ie @MaterRadiology