The overall aim of the iToBoS project is to build a new diagnostic tool for the early detection of melanoma; it will include a novel total body scanner and an AI-enabled Computer Aided Diagnostics (CAD) tool, exploiting all the available information of the patient. This holistic assessment tool should understand the specific characteristics of every patient in order to enable a personalised, early detection of melanoma.

The developments within the project will lead to a precision diagnostic system that will incorporate classical demographic data (age, sex), clinical phenotype (anatomical location of every lesion and skin phototype), genotype (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 combination of all this personalised information will result in an accurate, detailed and structured assessment of the pigmented skin lesions of the patient.

The project is aimed at all stakeholders involved with melanoma.

Specific objectives

  • Develop a novel skin scanner to enable an integrative diagnosis platform.
  • Detect and diagnose relevant changes over time in pigmented skin lesions.
  • Integrate all required data sources and clinician’s knowledge for accurate diagnosis through an AI cognitive assistant.
  • Achieve a highly personalised diagnosis of melanoma and offer clinicians understandable AI support (avoid black box).
  • Acquire a comprehensive and representative dataset of skin lesions with ground truth.
  • Organise two challenges for skin lesion analysis.
  • Facilitate the daily use of the Cognitive Assistant through the design of an intelligent Human-Computer Interface.
  • Validate the technology in the target clinical scenario (Barcelona, Trieste and Brisbane).