News for hackers. Stuff that matters.

A comment on AI Recognises Race in Medical Images. Parent comment

Re:AI Recognises Race in Medical Images by shadowgovt on Tuesday September 14, 2021 @12:00PM (#28526757)
They accounted for specifically intensity maximum, but your overall concern is solid; I don't see anything in the paper suggesting they accounted for a full spectrum of risk factors (broad-image noise, rotation, individual "stuck pixels" that could create a hard-to-spot thumbprint in the image, for example).
[ Parent | on HN ]
Re:AI Recognises Race in Medical Images by mlnewb2 on Wednesday September 15, 2021 @05:28PM (#28544609)
Simply testing in multiple external populations already rejects this hypothesis, unless you think they all had the same scanners with the same stuck pixels.

They also tested several variants of noise.

[ Parent | on HN ]