Ellie Talius

[Nature Biomedical Engineering @natBME]

A self-supervised model trained on chest X-ray images that lack explicit annotations performs pathology-classification tasks with accuracies comparable to those of radiologists.

https://t.co/7msqvEmTiy

[Pranav Rajpurkar @pranavrajpurkar]

Great coverage of our recent #CheXzero publication for self-supervised learning using radiology images and reports. Coverage by @EkaterinaPeshev @harvardmed

https://t.co/EW9bvftOMx

[Ellie Talius @EllieTalius]

super excited to announce that our paper, “Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning” has been published in @natBME !

[Pranav Rajpurkar @pranavrajpurkar]

Today, we're publishing CheXzero in @natBME 🚀

We show we can detect diseases from chest X-ray images at the level of radiologists *without labeling for individual diseases*.

How do we do it? By teaching the model to read the radiology report.
https://t.co/lakxNzWQH3

[UNC_CoachEskind @CoachEskind_UNC]

So pumped to have Ellie join the @StanfordXCTF family!