
AI models fail when x-ray settings change
Medical AI models are passing clinical tests by reading machine settings instead of actual patient disease.
Discover the newest research about AI innovations in 🖼️ Computer Vision.

Medical AI models are passing clinical tests by reading machine settings instead of actual patient disease.

A new AI tool reveals that many prostate cancers upgraded during active surveillance were actually mischaracterized from the very start.

A new deep learning model diagnoses anemia from lip photos far better than experienced emergency room doctors.

Hospitals are drowning in imaging volumes, but buying new CT scanners to improve image quality is a financial non-starter for most struggling health systems.

A new deep-learning model diagnoses autoimmune hepatitis with expert-level accuracy in some scenarios, but its failure against hepatitis B reveals a critical diagnostic blind spot.

A new AI model can detect lethal pancreatic tumors up to three years before they show up on standard medical scans.

Throwing millions at AI imaging algorithms will not solve the UK’s cancer crisis without the human staff to act on the results.

A smartphone camera might soon replace the physical throat swab, shifting the front line of infectious disease diagnosis from the clinic to the palm of your hand.

Standard radiation therapy treats every brain tumor margin the same way, but deep learning reveals that tumor geometry and location dictate how cancer spreads.

A new clinical trial shows that real-time computer vision can guide neurosurgeons through high-stakes brain procedures, but early software bugs prove the clinic is still a messy testing ground.