• Advanced Institute of Engineering and Technology (AVITECH)

  • Seminars

    May 18, 2020: Ms. Nguyen Thuy 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: Ms. Nguyen Thuy Nga, Univ. Toulouse

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

    Venue: Webinar – Microsoft Teams


    Nguyen Thuy Nga graduated from the Hanoi National University of Education (Hanoi, Vietnam) in 2014. Then she worked at the Institute of Mathematics, Vietnam Academy of Science and Technology (VAST) as a junior researcher from 2014-2017. In 2017, she got a Master degree in Applied Mathematics at Paul Sabatier University. She is now a third-year PhD student at LAAS-CNRS, in SARA team, in Toulouse, France. Her PhD research is funded by Continental Digital Services in France (CDSF). She is a co-founder of Torus Actions Company. At Torus, she is the team leader of SkinCancerAI project. Her main research concentrates on Stochastic Modeling, Reinforcement Learning and Convex Optimization for scheduling for moving-user systems. She also interested in Machine Learning for Computer Vision.


    February 2, 2024: Dr. Khoa D. Doan (Vin Univeristy) Toward Reliable and Practical Machine Learning Applications

    While Machine Learning (ML) has rapidly transformed several domains and applications with incredible successes, there are also important areas where the progress is significantly slower. Specifically, there exists a widened complexity gap between the methods currently investigated in research and those used in practice in these areas. One reason is that many algorithms, despite achieving […]

    February 2, 2024: Prof. Heng Ji (University of Illinois at Urbana-Champaign), Combating with Misinformation and Cancer: A Unified Multimodal AI Approach to Healthy and Happy Life

    A research overview of ongoing research projects, especially focusing on two that are most related to the VinUni-UIUC Smart Health Center: (1) Misinformation Detection and Trustworthy Large Language Models; (2) Joint Natural Language and Molecule Learning for Drug Discovery. Unsurprisingly these two seemingly different research problems can be tackled with a unified approach based on […]

    January 11, 2024: Dr. Le Duc Trong (FIT-UET) Resilient Multimodal Learning for Multimodal Emotion Recognition in the Presence of Incomplete Modalities

    Multimodal Emotion Recognition in Conversation (Multimodal ERC) is a critical area of research for interpreting human communication in diverse applications. Nevertheless, the persistent issue of uncertain missing modalities poses a major hurdle, hampering the development of robust Multimodal ERC models. Existing approaches face limitations in effectively leveraging a fusion of diverse data modalities encompassing audio, […]