AI tool enables faster skin cancer detection

Detection of melanoma and a range of other skin diseases is set to become faster and more accurate, thanks to the development of a new AI-powered tool that analyses multiple imaging types simultaneously.

Created by an international team of researchers led by Monash University, PanDerm is understood to be one of the first AI models built specifically to assist with real-world dermatological medical practice by analysing multiple types of images, including close-up photos, dermoscopic images, pathology slides and total body photographs. Trained on more than two million skin images, data for the model was sourced from 11 institutions in multiple countries. It has been described in the journal Nature Medicine.

“By training PanDerm on diverse data from different imaging techniques, we’ve created a system that can understand skin conditions the way dermatologists do: by synthesising information from various visual sources,” said first author Siyuan Yan, a PhD student at Monash University.

“This allows for more holistic analysis of skin diseases than previous single-modality AI systems.”

Unlike existing models, which are trained to perform a single task (such as diagnosing skin cancer from dermoscopic images), PanDerm was evaluated on a wide range of clinical tasks, such as skin cancer screening, predicting the chance of cancer returning or spreading, skin type assessment, mole counting, tracking lesion changes, diagnosing a wide range of skin conditions, and segmenting lesions. It was found to consistently deliver best-in-class results, often with just 5–10% of the labelled data normally required.

In clinical settings, PanDerm serves as a support tool that analyses the spectrum of skin images that doctors routinely use. The system processes these images and provides diagnostic probability assessments, helping clinicians interpret visual data with confidence. This is particularly valuable for improving diagnostic accuracy among non-specialists, detecting subtle lesion changes over time, and assessing patient risk levels.

“This kind of assistance could support earlier diagnosis and more consistent monitoring for patients at risk of melanoma,” said lead co-author Professor Victoria Mar, Alfred Health Victorian Melanoma Service Director.

A series of evaluations showed PanDerm improves skin cancer diagnosis accuracy by 11% when used by doctors. The model has also helped non-dermatologist healthcare professionals improve diagnostic accuracy on various other skin conditions by 16.5%.

Lead co-author Associate Professor Zongyuan Ge, from Monash University, noted that previous AI models have struggled to integrate and process various data types and imaging methods, reducing their usefulness to doctors in different real-world settings. Differences in imaging and diagnosis techniques could also arise due to different levels of resources available in urban, regional and rural healthcare spaces, added lead co-author Professor H Peter Soyer.

“PanDerm … could be particularly valuable in busy or resource-limited settings, or in primary care where access to dermatologists may be limited,” noted Soyer, who is Director of The University of Queensland’s Dermatology Research Centre.

“We have seen that the tool was also able to perform strongly even when trained on only a small amount of labelled data — a key advantage in diverse medical settings where standard annotated data is often limited.”

Senior co-author Professor Harald Kittler, from the Medical University of Vienna, said PanDerm demonstrates how global collaboration and diverse clinical data can be used to build AI tools that are not only technically strong but also clinically relevant across different healthcare systems.

“Its ability to support diagnosis in varied real-world settings, including in Europe, is a step forward in making dermatological expertise more accessible and consistent worldwide,” Kittler said.

PanDerm is currently in the evaluation phase before broader healthcare implementation. Looking to the future, the researchers aim to develop more comprehensive evaluation frameworks that address a wider range of dermatological conditions and clinical variants.

Ultimately, the team plans to establish standardised protocols for cross-demographic assessments and further investigate the model’s performance in varied real-world clinical settings, with a particular focus on ensuring equitable performance across different patient populations and healthcare environments.

Image credit: iStock.com/Anastasiia Yanishevska