18/05/2020: ThS. Nguyễn Thúy Nga (Univ. Toulouse, France), Automatic detection and classification of a skin cancer lesion by machine learning: From research result to a startup company

Skin cancer is the most common cancer with two to three millions new cases per year worldwide, according to WHO. Skin Cancer Foundation Statistics stated that one in every five persons will get skin cancer in their lifetime in the US. More than 2 people die of skin cancer in the U.S every hour (see more fact in Skin cancer facts ). The cost of treatment of skin cancer is high and increases quickly. In 2011, the US spent 8.1 billion USD on skin cancer which has increased 126.2% (www.ncbi.nlm.nih.gov ). However, if it is caught in early state, it can be treated. 5-year survival rate for melanoma one type of skin cancer drops from over 99% to about 14% if it is detected at terminal stage. The huge problem is that many people have skin cancer without knowing it because of the lack of dermatologists. According to the article “Lure of cosmetic procedures compounds a shortage of dermatologists” in Star Tribune, this causes huge problem that is large delays in diagnosis and treatment. This talk is about the work our team at Torus Actions did last year which won the second prize of ISIC 2019, (challenge2019.isic-archive.com ) the international competition in detection and classification of skin cancer. The aim of this work is to detect and classify a skin cancer lesion automatically by machine learning.

Speaker: ThS. Nguyễn Thúy Nga, Univ. Toulouse

Time: 15:30, Monday, May 18, 2020

Venue: Webinar – Microsoft Teams