Hospitals do not always have the opportunity to collect data in tidy, uniform batches. A clinic may have a handful of carefully labeled images from one scanner while holding thousands of unlabeled scans from other centers, each with different settings, patient mixes and imaging artifacts. That jumble makes a hard task—medical image segmentation—even harder still. Models trained under neat assumptions can stumble when deployed elsewhere, particularly on small, faint or low-contrast targets.
New training method helps AI models handle messy, varied medical image data
Reader’s Picks
-
Around the world, girls are challenging gender norms in creative, courageous and often overlooked ways—but the risks are high, a [...]
-
A new study, called the MENCALLHELP2 project, has explored the content, nature and characteristics of call data received by the [...]
-
Influencers use oppression, manipulation and weaponization to police Black women on social media, according to new research uncovering the entrenched [...]