The overall aim of the iToBoS project is to build new diagnostic tools for the early detection of melanoma, exploiting all the available information of the patient.
The platform includes a novel total body scanner and a Computer Aided Diagnostics (CAD) tool, allowing the final system to incorporate basic demographic data (e.g., age, sex and socio-economic data), clinical phenotype (i.e., anatomical location of every lesion and skin phototype), genotype (i.e., mutations in hereditary melanoma genes and genetic variations in melanoma susceptibility genes) and an imaging phenotype including number and size of naevi, degree and area of photo-damaged skin, as well as clinical dermoscopic image characteristics of the lesions, acquired by the total-body high-resolution scanner.
The iToBoS project hopes to demonstrate that the combination of this personal data will result in a more accurate, detailed and structured assessment of the pigmented skin lesions of the patient, compared to traditional dermoscopy.
This data will be the basis for an AI powered cognitive assistant, which aims to identify and categorise lesions as well as provide explanations to the physicians about why the AI decides that a lesion is of high or low risk, the detected features and the patterns related to melanoma (or other skin malignancies).
As the result of these project goals the main categories of data managed by iToBoS are:
- Medical history data (patient and family).
- Genomic data.
- Phenotype (skin images, eye colour, hair colour, skin colour) and data derived from it (labelled annotations, 3D avatar, etc.).
- AI models and AI cognitive assistant generated explanatory information.
The project will develop and validate an AI cognitive assistant tool to empower healthcare practitioners, offering risk assessment for every lesion. Thus, data from this project will provide valuable contributions to the dermoscopy field that will be usable for future research and improved clinical assessment.