NEW research shows AI can ask another AI for a second opinion on medical scans.
"One part of the AI system tries to mimic how radiologists read medical images by labelling them, while the other AI part judges the quality of the AI-generated labelled scans by benchmarking them against the limited labelled scans provided by radiologists," said PhD candidate Himashi Peiris, Faculty of Engineering, Monash University.
Peiris added the research design set out to create a competition between the two components of a "dual-view" AI system.
"The traditional method for scans relies on the interpretation of individuals, which is time-consuming and prone to errors and extended waiting for patients seeking treatments."
The algorithm developed by the Monash researchers allows multiple AI models to leverage the unique advantages of labelled and unlabelled data, and learn from each other's predictions to help improve overall accuracy.
"Across the three publicly accessible medical datasets, utilising a 10% labelled data setting, we achieved an average improvement of 3% compared to the most recent state-of-the-art approach under identical conditions," said Peiris.
"Our algorithm has produced groundbreaking results in semi-supervised learning, enabling AI models to make more informed decisions, validate their initial assessments, and uncover more accurate diagnoses and treatment decisions."
The above article was sent to subscribers in Pharmacy Daily's issue from 26 Jul 23
To see the full newsletter, see the embedded issue below or CLICK HERE to download Pharmacy Daily from 26 Jul 23
