Profile cover photo
Profile photo
Yuri Velichko
300 followers
300 followers
About
Yuri's posts

Post has shared content
I'm very excited about the work our group (g.co/brain) is doing in various areas of medical imaging. Today, we published a preprint of a paper titled "Detecting Cancer Metastases on Gigapixel Pathology Images" by Yun Liu, Krishna Gadepalli, Mohammad Norouzi, George E. Dahl, Timo Kohlberger, Aleksey Boyko, Subhashini Venugopalan, Aleksei Timofeev, Philip Q. Nelson, Greg Corrado, Jason D. Hipp, Lily Peng, and Martin C. Stumpe.

Some key statistics from the paper used to evaluate the effectiveness of this work:

Tumor localization score (FROC): ("find all the tumors")
0.89 (our model)
0.73 (human pathologists with infinite time)

Sensitivity at 8 false positives:
0.92 (our model)
0.73 (human pathologists with infinite time)

(It's also worth point out that Yun Liu is a member of the Google Brain Residency program: g.co/brainresidency)

This work follows on our earlier work on detection of diabetic retinopathy in retinal images.

Pathology blog post: https://research.googleblog.com/2017/03/assisting-pathologists-in-detecting.html
Paper preprint:
https://drive.google.com/file/d/0B1T58bZ5vYa-ZjlSRmIyc3M3MTQ/view

Earlier blog post on diabetic retinopathy work: https://research.googleblog.com/2016/11/deep-learning-for-detection-of-diabetic.html

Edit: update paper preprint link to different URL (but same content)


Post has attachment

Post has attachment
Gravitational dipole?

Post has attachment

Post has attachment

Post has attachment

Post has attachment

Post has attachment
The Economic Fallout

Post has shared content
First episode of the upcoming series is free on Google play right now.
The show starts on NatGeo nov 14.
#wewentintothedarknesssoyoucouldfindthelight

Post has attachment
Wait while more posts are being loaded