Skin cancer, AI detection of melanoma and 100+ other types of skin tumors 

Skin cancer is one of the most common cancers in the world. In the US alone, between 3 to 5 million new cases are reported each year, with treatment costs of approximately $9 billion.

In the UK, on the other hand, about 147,000 new cases of non-melanoma skin cancer are diagnosed per year. In France, over 100,000 cases of skin cancer are reported every year, most of which are basal cell carcinomas, a type of non-melanoma skin cancer. 

The rate of skin cancer (both melanoma and non-melanoma cancer) increased 5-fold since the 1970s, and continues to rise in many places. Due to the lack of dermatologists and frequent misdiagnosis, many people may have skin cancer without knowing it. Late stage skin cancers spreads to internal organs and become fatal. Early stage skin cancer can be cured with a high survival rate (98%), while the 5-year survival rate for skin cancer is extremely low (15%). 

iToBoS project, funded by European Research Council Horizon 2020 research and innovation programme under grant agreement No 965221, is one of the biggest European project dedicated to fight skin cancer. The goal of the project is to build a full-body 3D scanner that can be used in hospitals for early detection of melanoma and other types of skin cancer. The project has a duration of 48 months (1 April 2021-31 March 2025) and a total Budget of 12 million Euro, with 19 members, including universities and hospital (Barcelona, Trieste, Hannover, among others); big companies (IBM, BOSCH, etc.); NGOs (European Melanoma Patient Network, etc.), and small companies (Coronis Computing, Trilateral Research, Torus Actions and others). 

Supported by ITOBOS project, Torus Actions has created Skin Cancer AI, an intelligence solution for early detection of skin cancer. It provides a very detailed diagnosis of both melanoma and non-melanoma skin cancer, as well as other types of skin lesions. For instance, Torus Actions Skin Cancer AI can detect up to 12 types of melanoma, 38 types of non-melanoma skin cancer, in addition to over 70 types of other pre-cancer or benign skin lesions. 

Skin Cancer AI developed by Torus Actions is highly accurate, efficient  and easy to use. Patients can upload either a dermoscopic or a clinical  image of their lesions and instantly obtain diagnosis. This specifies  the level of cancer risk and preferential diagnosis, and it includes a  differential diagnosis of their lesions. Skin experts and researchers  can upload a folder of images and download a detailed diagnostic CSV  file as well as a statistical report PDF file within seconds. 

This article was produced with the support of Torus Actions, an iToBoS partner specialized in AI solutions for skin care.