Computers do better than pathologists in predicting lung cancer type, severity

Re:Computers do better than pathologists in predicting lung ... by Strilanc on Monday August 22, 2016 @01:11PM (#12337771)

Yet another press release that fails to reference the study it's talking about. Not to mention giving no quantitative details about its lead ('Trounced'? By how much?).

The study is "Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features" by Kun-Hsing Yu et al. It's open access: http://www.nature.com/ncomms/2016/160816/ncomms12474/full/nc...

[ Parent | on HN ]

Re:Computers do better than pathologists in predicting lung ... by daveguy on Monday August 22, 2016 @03:58PM (#12338971)

Computers trounce* pathologists...

* by an un-quantified amount using only histology slides -- a limitation not enforced in actual medical practice.

[ Parent | on HN ]

Re:Computers do better than pathologists in predicting lung ... by cicero19 on Monday August 22, 2016 @06:01PM (#12339772)

yeah.. seriously.. what academic journal would accept that kind of statement.

[ Parent | on HN ]

Re:Computers do better than pathologists in predicting lung ... by ChristianBundy on Monday August 22, 2016 @06:05PM (#12339792)

Nature, apparently.

[ Parent | on HN ]

Re:Computers do better than pathologists in predicting lung ... by leereeves on Monday August 22, 2016 @06:30PM (#12339914)

Nature Communications, which publishes a dozen articles every working day.

(2191 so far in 2016)

[ Parent | on HN ]

Re:Computers do better than pathologists in predicting lung ... by delazeur on Tuesday August 23, 2016 @01:26AM (#12341593)

Nature and Science appear to accept a lot a "controversial" articles that don't really live up to their reputation for rigor.

[ Parent | on HN ]

Re:Computers do better than pathologists in predicting lung ... by frozenport on Monday August 22, 2016 @08:58PM (#12340570)

Indeed, this is a press release and not journalism.

[ Parent | on HN ]