Deep learning interpretation of echocardiograms.

Ghorbani A, Ouyang D, Abid A, He B, Chen JH, Harrington RA, Liang DH, Ashley EA, Zou JY. · 2020

Read Deep learning interpretation of echocardiograms. by Ghorbani A, Ouyang D, Abid A, He B, Chen JH, Harrington RA, Liang DH, Ashley EA, Zou JY. (2020) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc6981156.txt.

Description

Ghorbani and co-authors teach deep learning to read heart ultrasound scans. Their study appeared in NPJ Digital Medicine. Echocardiography is the most common heart imaging method, capturing fine detail in space and time. Human reading is slow, and some patterns escape the eye.

Their model, EchoNet, learned from a large new set of scans. It spotted pacemaker leads and an enlarged left atrium with strong accuracy. It measured heart chamber volumes and pumping strength, the ejection fraction. It also guessed body traits that humans cannot read from a scan: age, sex, weight, and height, each with moderate accuracy. Checks confirmed the model attends to the right structures for explainable tasks. The authors see help for busy clinics and for places short of cardiologists.

Catalog record

CREATORGhorbani A, Ouyang D, Abid A, He B, Chen JH, Harrington RA, Liang DH, Ashley EA, Zou JY.
YEAR2020
COLLECTIONPAPERS
FORMATTXT
FILE SIZE50 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC6981156

Browse the full library · About the Tower of Babel