A new artificial intelligence (AI) tool developed at the University of Melbourne is helping transform how skin cancer is detected.
The technology has the potential to save lives, reduce unnecessary biopsies and cut healthcare costs, while addressing long-standing equity gaps in diagnosis.
Research Fellow Dr Noor E Karishma Shaik is integrating AI with thermal multimodal imaging for point of care diagnosis to identify abnormal skin lesions in real time.
"Current diagnostic methods rely heavily on visual inspections, followed by biopsies, but this is a flawed approach as it's prone to both under and over-diagnosis," Dr Shaik said.
"Our non-invasive technology not only removes the risk of human error but is less time-consuming and costly and works equally well across all skin tones."
In a recent pilot study at the Skin Health Institute (SHI), the AI tool achieved 94 per cent diagnostic accuracy. Four medical clinicians and 30 patients endorsed the tool, praising its clinical value and ease of use.
"Unlike existing camera or microscope-based systems, this handheld technology captures multiple data types simultaneously, including heat and physiological information, enabling clinicians to see beneath the surface of the skin," Dr Shaik said.
SHI Director of Research and Partner Investigator Associate Professor Peter Foley, said the development of this technology represents a major advance in dermatological diagnostics.
"The ability to assess lesions objectively in real time is exactly the kind of innovation the field needs," Associate Professor Foley said.
"What impressed us most is how accessible this technology could become, not just for specialists, but for general practitioners across the country, particularly in rural and remote areas where access to specialist care is limited."
Skin cancer affects two in three Australians by age 70, and one person dies from the disease every six hours.
In 2024, more than 600,000 unnecessary skin biopsies were performed in Australia, costing over $400 million.
"We are solving a real-world problem by helping to deliver faster care, reducing the number of invasive procedures and providing more equitable access to early diagnosis," Dr Shaik said.
A commercial-scale trial with MoleMap Australia, which begins in August, aims to validate the device in real-world clinical settings and inform regulatory approval.
Following the trial, commercial rollout is expected within two to three years.
