AI and Smartphones Are Improving Early Cancer Detection

AI can greatly improve the accuracy of cancer detection from MRI, X-ray and other medical imaging. Approximately 25% of cases of lung cancer diagnosis are missed when doctors check chest x-rays. New AI systems are catching more of the detectable lung cancer cases.

An iPhone-based AI system looking for tongue cancer had a detection accuracy (percentage of correct prediction) of nearly 90%. The detection inference time was around seven milliseconds. These inexpensive systems are usable in low and middle-income countries. 70% of cancer deaths are in low and middle-income countries. Cancer kills ten million people every year.

AI-powered systems have also been able to accurately detect skin cancer in 95% of images of cancerous moles and benign spots, whereas a team of 58 dermatologists was accurate 87% of the time.

Deep learning to digital breast tomosynthesis (DBT: an advanced method for cancer detection in which an X-ray arm sweeps over the breast, taking multiple images in seconds) improves cancer detection. It reduced false-positive recalls compared to screening with digital mammography (DM) alone. New AI cancer detection sensitivity increased from 77% to 85% while cutting detection time by half.

SOURCES – EETimes, British Journal of General Practice, Radiological Society of North America
Written by Brian Wang,

3 thoughts on “AI and Smartphones Are Improving Early Cancer Detection”

  1. Already happening for pregnancy, according to some stories floating around.

    So if google ads all suddenly start being for funeral homes, you'll know why

  2. Early identification is still critical in treatment, so this is a positive development. One of the unintended positive consequences of the COVID lockdowns is insurers and providers moving aggressively into digital technology (i.e. telehealth, virtual doctor visits, etc) that is required to take advantage of it.

    The potential privacy concerns will only be addressed after people are adversely affected. HIPAA penalties are, I think, insufficient to get the technology companies to be proactive.

Comments are closed.