IIIT-Hyderabad study cautions against blindly trusting medical AI models
Researchers at IIIT-Hyderabad have cautioned against blindly trusting medical AI models after auditing four vision-language models on chest X-rays. The study found that diagnostic information could influence image localisation, while radiologists preferred broader areas around abnormalities in some cases.
Read original article on Telangana Today →Related news
-
WR to operate night block between Mahim and Mumbai Central on Oct 11
-
Aaditya Thackeray questions ECI over 7.90 lakh-voter drop in SIR draft roll
-
Should children have a four-day school week?
-
Protesters allege assault in custody, abuse in Tihar after demanding FIR against Delhi Police ACP
-
‘What is the urgency?’: Delhi HC defers IYC protest plea to Monday
-
Police visit mosques, ask people to avoid going to Jantar Mantar
-
Protest buzz grows at JNU; students say travel curbs point to success
-
‘Adapting to New Zealand conditions key for India’: Pacer Lockie Ferguson