iToBoS project improves early detection of skin cancer

12 Mar 2025

Fraunhofer HHI and partners develop full-body scanner linked to AI diagnostic platform.

A project consortium funded by the EU and including the Fraunhofer Heinrich Hertz Institute (Fraunhofer HHI) has developed a novel platform for early detection of skin cancer.

The iToBoS (Intelligent Total Body Scanner for Early Detection of Melanoma) device includes a novel total body scanner allied to an AI diagnostic system, one that integrates medical records, genomics data and in vivo imaging into the diagnostic process.

Coordinated by Spain's University of Gerona, the iToBoS project is supported by €12 million of EU funding.

"The project has multiple goals: to increase the automated preliminary medical history throughput, optimize early detection of cancers, ease the burden on healthcare professionals, lower the risk to patients and reduce the number of unnecessary biopsies performed," commented the consortium.

The iToBoS optical body scanner has been developed by Bosch at the company's Spain research center. Designed to a scan a patient in six minutes with a resolution of 20 microns per pixel, the project's prototype is constructed around collaborative robots (or cobots) for dynamic adjustment of camera positions, accommodating a wide array of patient profiles.

One significant aspect of this imaging system is the use of liquid lenses from project partner Optotune for image acquisition, based on two immiscible liquids with different refractive indices. The company is implementing its gravity compensation technology in the project's lenses, allowing them to be used in any orientation without coma aberrations induced by gravity. These aberrations can be an intrinsic drawback in some liquid lenses.

Cross-linking huge volumes of data

"The decision to integrate liquid lenses into iToBoS' full-body scanner was taken due to the need to take thousands of pictures in the shortest amount of time," noted the project in its literature. "The compactness and fast-focusing capabilities of the liquid lenses made them the best solution."

AI plays a major part in the iToBoS platform, which will incorporate both conventional AI and explainable AI (XAI) from Fraunhofer HHI to identify and track the development of melanomas on patients' skin, and integrate the image scans together with all available patient data on demographics, UV damage, risk group and other factors.

"With our XAI methods, we’ve succeeded in rendering the solution-finding process of AI systems transparent and overcoming the 'black box' aspect," said Sebastian Lapuschkin, head of the Explainable Artificial Intelligence research group.

"Thanks to our explainable AI methods, we don't just identify anomalous moles but actually explain at the same time what makes them different. Being able to cross-link these huge volumes of data offers the opportunity to learn more about skin cancer and people's potential for developing it."

The project is using meta datasets collected in Spain and Australia in its AI system, and intends to extend the pool of data to other populations from around the world. In the long term, the iToBoS full-body scanner could also be used to identify other skin diseases such as neurodermatitis.