Recalling a screener with one-view asymmetry for rolled views seems anachronistic in the era of DBT. I haven't asked for them since Ye Olde Days pre tomo. Does anyone out there find them adding value when you're already performing spot compression with DBT? (Review of outside films; both screener and diagnostic were performed with DBT).

AI continuing to offer significant time reductions in the part of papers I find most time-consuming. Next — any assistance with cropping and standardizing contrast window levels of the radiology images would be great. (The fun part is picking out the images of course).

Extremely pleased to see work by my collaborator @ArtieShen, his stellar PhD student @erasromani, and my @NYUImaging friend and colleague Dr. Chenchan Huang (among many others) recognized for their work on AI-based pancreatic cyst characterization as an @AuntMinnie Scientific Paper of the Year semifinalist. This group has worked tirelessly on the difficult problem of deciding which pancreatic cysts are at true risk of cancer, and how they are selected for EUS biopsy vs following. I expect more papers of equal quality from them on this important topic over the next few years. Some other incredible papers in this category too, including the MASAI trial results. (Was that only January??).

I understand that many physicians are reluctant to create social media accounts, but this type of impersonation is a wake-up call. You can always create, set it to locked, and mostly ignore it. The reporting system probably could have kicked in much faster if the doctor in question already had an account, as the @X reporting pathway for impersonation requires you provide the handle of the "real" person.

Absolutely using this.

Check your work when generating AI medical figures…

And that’s the day the Culture was born, kids.

This morning's Claude version of model self-exploration, was, apparently, a fake reviewer response letter intended as a creative writing assignment: "Point 2. The reviewer asks us to justify the choice of a 12-month follow-up window, noting that "the clinical rationale is thin." The rationale is thin. The window was chosen in 2021 by the original principal investigator, who is no longer on the project. The protocol records the number and not the reasoning. We searched the shared drive for a design memo and found none. We found a folder named "followup_ideas" with one file in it, a spreadsheet with a single column of dates." I think I need to revise the Claude prompt a bit. xitter.cf/heacockmd/status/21053…

Have set up two recurring Astra medium tasks this week, inspired by this post discussing how Claude was researching crabs. xitter.cf/dioscuri/status/210493… 1) random task not intended to be related to my stored data or preferences 2) random task that should draw on my stored data and preferences For #1 in particular, I asked the model to show its work. For #1, Astra has headed into a two-day exploration of three point shapes. Since I dislike geometry, it's unlikely to be using stored memory. For #2, it came back with some readings on Plutarch's Life of Themistocles and the next day with some background on the Gehlen Organization. It's been an interesting way to start the day. Tempted to set it up on Claude now as well to double the fun.

Getting ahead of the reposts on this one. A Swedish health system has decided, based on the ScreenTrust trial, that one radiologist + AI is as good as two radiologists reading a mammogram. The MASAI trial had similar results. They’re now officially doing this outside of the trial. This will allow the radiologists more time to read other studies and reduce backlogs. No radiologists are being replaced. It is a very logical and expected conclusion to these excellent trials The US standard of care is a single reader plus CAD (now often AI CAD). We do not use double reads for mammograms, so these study results have interesting implications but do not directly apply to the breast imaging pipeline here. Is there room for discussion of autonomous reads of low-scoring mammograms? Sure. But they are still discussions, with no clear pathway in the US at this time. Screening mammograms are a part of my job but only a small fraction. In short: everyone expected this after the study results. Mammography was the one time that two radiologists read the same study, and now everyone is moving to a single reader system (here augmented by AI). Please note Radiology Business did not make any wrong assumptions; I just expect this will get reposted missing all the context.

I heard @matt_is_nice's initial concept for @ZaniahHealth through @nikillinit's OOP and am delighted to see it has finally been announced. The team brings deep expertise in endoscopy foundation models that they're now applying to a new consumer health product. Take a peek at Zaniah's new take on capsule endoscopy, launching later this year.

Another masterpiece.

Is it time for a radiology society devoted to AI opportunistic screening yet? The field seems to be gathering momentum: -Breast 5-year AI risk: good data, commercially deployed -Osteoporosis screening from CTs: mature, commercially deployed -ASCVD risk from CT/mammo: emerging, commercially deployed (mature in the form of quantification of calcs at least) -5-year cancer risk from chest CT: good data -Cardiometabolic risk from CXR, abdominal CT/MRI: hot topic of interest/research And that's just off the top of my head. We're in the imaging biomarker explosion era. Or even broader if you consider our cardiology colleagues and what they're doing with echo...

Not a fan of "redemonstrated" in radiology reports. A five dollar word when a five cent one (stable) will do.

I weep for the remake of Ice Princess.