Deep Learning to Improve Breast Cancer Detection on Screening Mammography.

Shen L, Margolies LR, Rothstein JH, Fluder E, McBride R, Sieh W. · 2019

Read Deep Learning to Improve Breast Cancer Detection on Screening Mammography. by Shen L, Margolies LR, Rothstein JH, Fluder E, McBride R, Sieh W. (2019) 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-pmc6715802.txt.

Description

Shen and co-authors built a deep learning system to spot breast cancer on screening mammograms. Reading these X-ray images is hard, and expert labels for each lesion are rare. Their method trains in stages, so later stages need only a whole-image cancer label. That makes far more images usable for training.

On film mammograms from a public database, averaging four models reached an AUC of 0.91 across the full test set. On digital images from a second database, the averaged score rose to 0.98 with strong accuracy. AUC here gauges how well the system ranks cancer cases above non-cancer ones. The results rival earlier methods.

Catalog record

CREATORShen L, Margolies LR, Rothstein JH, Fluder E, McBride R, Sieh W.
YEAR2019
COLLECTIONPAPERS
FORMATTXT
FILE SIZE59 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC6715802

Browse the full library · About the Tower of Babel