Lunit announced that a study in South Korea’s national breast cancer screening programme has validated the real-world effectiveness of its AI-powered mammography screening.
The study, published in Nature Communications, highlights how AI-assisted mammography interpretation significantly improves breast cancer detection without increasing recall rates.
Led by Professor Yun-Woo Chang from Soonchunhyang University Seoul Hospital, the study involved collaboration with radiologists from six academic hospitals in South Korea.
It analysed routine mammography scans of 24,543 women aged 40 and above, taken between February 2021 and December 2022 as part of the national screening programme.
The study compared the performance of breast radiologists interpreting mammograms with and without Lunit’s AI-based detection solution, Lunit INSIGHT MMG.
Its results showed that AI-assisted radiologists detected 13.8% more breast cancers than those using conventional methods.
The cancer detection rate increased from 5.01 to 5.70 per 1,000 with AI assistance, while recall rates remained unchanged, ensuring improved clinical effectiveness.
AI assistance resulted in a significant improvement in detecting small-sized tumours and node-negative cancers, crucial for early detection.
The study also evaluated Lunit INSIGHT MMG’s impact on general radiologists through a simulated retrospective study, revealing a 26.4% increase in cancer detection rates.
The study lead and corresponding author professor Chang said: “This prospective study offers compelling real-world evidence that AI can improve early cancer detection while maintaining effectiveness and reducing unnecessary patient anxiety caused by false positives in a single-reading setting.”
The study builds upon Lunit INSIGHT MMG improving breast cancer detection in a trial conducted at Capio St. Göran Hospital in Sweden, in a double-reading setting.
Capio St. Göran Hospital became the first to replace one of two radiologists with AI.
Lunit INSIGHT MMG is already deployed in national programmes in Australia, Iceland, Qatar, Saudi Arabia, Singapore, and Sweden, enhancing efficiency and diagnostic accuracy.
The diagnostics company said that the study findings would influence global screening protocols, particularly in countries practising single-reading mammography.
Also, the study supports AI’s role in optimising cancer detection and reducing radiologists’ workload, especially amid a shortage of specialised professionals, said Lunit.
Lunit CEO Brandon Suh said: “This latest prospective study in South Korea further solidifies Lunit INSIGHT MMG’s potential as an indispensable tool in breast cancer screening.
“Whether in a single-reader or double-reader setting, AI can serve as a powerful force multiplier, assisting radiologists in detecting cancer earlier and more accurately.”
“As AI adoption accelerates, we remain committed to driving innovation and making AI-powered cancer screening the new standard of care.
“By working closely with healthcare providers worldwide, we aim to ensure that AI benefits as many patients as possible.”
