The emergence of AI-generated art within therapeutic settings necessitates the establishment of guidelines to address ethical and privacy concerns including informed consent, data protection, and the confidentiality of patients’ medical images and resultant artworks.

The goal of this competition is to develop state-of-the-art machine learning techniques for detecting multiple skin lesions in clinical images.

The design of the iToBoS scanner places a strong emphasis on patient protection, particularly in the context of its robotic components operating in close proximity to the patient. 

The COVID-19 pandemic accelerated the adoption of digital technologies in many areas of medicine.

In this blog we present more details about the iToBoS dataset: skin region images extracted from 3D total body photographs for lesion detection.

iToBoS research partners from The University of Queensland have recently published an invited article with the Italian Journal of Dermatology and Venereology, titled ‘Genetic testing for familial melanoma’. 

The Hospital Operator Interface, or HMI, plays a crucial role in the operation of the scanner.

An AI cognitive assistant is developed that will fuse information from multiple data sources, providing melanoma risk estimation both on the patient level as well as per-lesion.

The initial and crucial step in total body imaging involves the optical imaging unit. Illumination is provided by 10 high-brightness LEDs, delivering over 150,000 lumens for uniformly distributed lighting.

In developing the "Arch" prototype of the scanner, patient safety was paramount.