Check out #PanEcho, now in @jama.com
✅ open weights
✅ multiview multitask reporting
✅ international validation
✅ works with POCUS
Amazing effort @cardslab.bsky.social
@giholste.bsky.social @rohankhera.bsky.social
+ @atlaswang.bsky.social, Márton Tokodi & Attila Kovács
#CardioSky #EchoSky
Figure 4. Task-Specific ViewRelevance
An #AI system that automatically interprets echocardiograms maintained high accuracy across geography and time from complete and limited studies.
https://ja.ma/4jYWBgI
Thank you @erictopol.bsky.social for highlighting our work! Huge honor
This is the product of deep interdisciplinary collaboration btw engineers & clinicians. Grateful to teammates & mentors @ekoikonomou.bsky.social @rohankhera.bsky.social
+ Model is publicly available! github.com/CarDS-Yale/P...
Vibe coded a new personal website: www.gholste.me
Do I know how Next.js works? Not in the slightest. Am I using it in my website? Apparently!
Have to say I'm very impressed with @v0.dev, saved me hours and hours
Working on #AI for #echofirst? Use PanEcho!
Why PanEcho? The model is trained on >1M echos from all views on 39 diverse tasks, meaning...
- PanEcho is a powerful transfer learner
- It takes *one line* of Python code
See github.com/CarDS-Yale/P... for details + reach out with Qs
I appreciate the very kind words. I feel like I'm the lucky one!
Presented at #AHA24 Late Breaking session, we are pleased to announce #PanEcho - Complete AI-enabled echocardiography interpretation with multi-task deep learning.
Led by @giholste.bsky.social & @ekoikonomou.bsky.social
@cardslab.bsky.social
Preprint, code, and model: cards-lab.org/panecho
