Assoc Prof @HopkinsNeurorad @HeadNeckRads | educator, editor, podcaster interested in diagnostic excellence
Baltimore, MD
- Tweets 14,606
- Following 4,696
- Followers 18,505
- Likes 18,900
Pinned Tweet
Expert radiologists: have you made a great call? Publish your greatest hits with 𝘙𝘢𝘥𝘪𝘰𝘭𝘰𝘨𝘺 Diagnosis Please. Email proposals radiology@rsna.org👇
As the new editor for this section, I have some tips below
8
15
108
25,620
Editors should know that you can improve your Journal Impact Factor by publishing highly cited non-research/non-review content: perspectives/editorials, news, and short teaching images/cases. Citations to these count for the numerator and not denominator.
9
904
What do you call this diffuse brain vascular abnormality?
Watch @theshadowfixer explain on @TheAJNR Podcast the review by @pranj_rad piped.video/g_cBhepJYjU?si=-8xY…
6
11
80
7,595
Subscribe to the podcast on Apple (newly with video!) or Spotify: share.transistor.fm/s/79a33c…
Read the paper: ajnr.org/content/47/7/1776 @pranj_rad @dhairyalakhani
5
12
1,641
An annoying feature of @ChatGPT for Clinicians is its refusal to do any arithmetic related to a medical question, not present in the free consumer version.
6
3
26
5,739
A better feature would be a skill that when math is needed, you turn on some deterministic code to calculate it. Am I missing something here? @thekaransinghal
595
Indication for IAC brain MR: “illness, unspecified.”
Please. Just tell me something.
🩻 New Wet Read from C. Douglas Phillips, MD, FACR (@CDP_Rad)?
"AI is out there, lurking. It seems it is either going to replace us or generate the need for many more of us, depending on who you read."
Read 'Please. Just Tell Me Something' here: bit.ly/4yWKpoE
#Radiology #Imaging #Radiologist #MedicalImaging #AI #RadAI #RadiologyAI
8
2
28
5,185
If you don’t know how to tell me something, check out this thread:
New interns are starting soon. Here are my #TipsForNewDocs from a radiologist. 🧵
When your senior resident or attending tells you to order an imaging test, make sure you understand the purpose. If you don't, ask them! What are you hoping to answer with the study?
3
782
Patient with history of stroke presents with an episode of lightheadedness followed by loss of consciousness x20 min. Seizure en route to ED.
Brain attack team activated. Take a look at this CTA head and neck here and see if anything pops out.
9
12
85
38,754
For radiologists, the main lesson is that PE can sometimes be detected at the bottom of CTA neck, highly dependent on the contrast timing. It's usually incidental but sometimes not (ie, in this case it explained the original reason for getting the study).
The prevalence of PE on neck CTA has been reported 0.3-1.1%.
doi.org/10.1007/s11547-018-0…
doi.org/10.1097/md.000000000…
doi.org/10.1017/cjn.2017.288
2
2
15
2,003
Miss rates of incidental PE on neck CTA are high (96% in this study of 4873 carotid CTAs: doi.org/10.1007/s11547-018-0…).
Be safe out there. CTA neck is an incidental minefield. Glance at the pulmonary arteries included at the bottom of the scan range of neck CTA.
1
1
23
1,615
Elderly patient with AFib (not taking prescribed Eliquis) presents with dizziness and generalized weakness 5 days.
CTA head and neck requested.
Take a close look at these images. I've made it artificially easy for you by choosing the relevant 30 out of 2k images.🧵
8
5
107
17,451
CTA incidentals are commonly missed.
In this study, radiologists retrospectively reviewed 1175 stroke CTAs.
Incidental findings of MAJOR potential clinical relevance were in 6.4% of the studies, and these were NOT reported by the radiologist 43% of the time. doi.org/10.1016/j.clineuro.2…
Be careful out there!
2
6
1,164
For a companion case on a CTA head and neck, see this prior post
Featured Case of the Day on @Radiopaedia
Brain attack team activation: right facial droop
What do you suspect? doi.org/10.53347/rID-188784 #neurorad
5
1,399
Francis Deng, MD retweeted
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.
Health system will use AI instead of radiologists for breast imaging 2nd reads ow.ly/nGPO50ZSTCn
4
8
44
9,400