LE Van Linh

About Me

I finished my Bachelor at University of Dalat in 2011. Then, I obtained my Master degree at PUF-HCM (Pôle Universitaire Francais, Ho Chi Minh City) in 2016. This is a Master program of University of Bordeaux that is deployed at Ho Chi Minh City. My Master's Internship has been done in LaBRI with the topic: "Automatic morphology: landmarks estimation in biological images".

My Ph.D. has been done at LaBRI, University of Bordeaux under supervising of Mrs. Marie BEURTON-AIMAR. The subject is "Automatic landmarking for 2D biological images: image processing with and without deep learning methods". This work took a place in a collaborative project with biologists (DEVMAP) to analyze the interaction between the insect (beetle) and the environment by applying morphometry analysis based on landmarks. In this project, we worked on the methods to automatically predict the coordinates of landmarks by using classical image processing alogrithms and deep learning models, specifically, Convolutional Neural Network.

After the Ph.D., I have joined to MONC team, Inria Bordeaux Sud-Ouest for my first post-doctoral. During this period, I have the opportunity to apply deep learning methods on "radiomics" images (Computed Tomography) in a collaborative project with Sophia Genetics. The objective of this project was to improve the monitoring of Non-Small Cell Lung Cancer patients by offering new quantitative tools for clinical decision helping. My main tasks were to design the models to provide the segmentation of the parenchyma and nodules inside the lung.

I did my second post-doct at the Sciences Biology and Medical Department, University of Bordeaux. The project that I am working on, focused on deep learning methods to study the histological images of cancer patients.

Currently, I work at Insitute Bergonié. My work focuses on applying deep learning models to process pathological images from different types of cancer. The objectives of the projects are to predict the outcome for the patients from the cohorts.

Work Experiences

Data scientist (Research fellow)

Institute Bergonié (05/2023 - present)

Post-doctoral

Sciences Biology and Medical Department, University of Bordeaux (01/2022 - 04/2023)

Post-doctoral

MONC team, INRIA Bordeaux Sud-Ouest (03/2020 - 12/2021)

Temporary Assistant, Lecturer and Research (ATER)

University of Bordeaux. Charge: 96 hours. Duration: 6 months (9/2019 - 2/2020)

Teaching (amendment to doctoral contract)

University of Bordeaux. Charge: 64 hours. Duration: 2/2019 - 6/2019

Ph.D.

LaBRI, University of Bordeaux. Duration: 2016 - 2020

Master Intership

LaBRI, University of Bordeaux (France). Duration: 06/2015 - 12/2015

Lecturer

Faculty of Information Technology. University of Dalat (Vietnam). Duration: 2011 - 2019

Website developer (part-time)

Minh Quan Ltd, But Xanh Ltd (Vietnam). Duration: 2008 - 2010

Projects

Modeling and applying AI to improve cancer monitoring

In this project, we are building mathematical models that are used to describe the course of the disease, and to understand the mechanisms involved in cancer, to help monitor patients. We use AI to integrate parameters or measures that cannot be modeled into these models or to make a diagnosis directly. We use all the available information: imagery, genomic information, clinical data, etc. Ultimately, the objective is to assess the effectiveness of a treatment early. The idea is that the doctor can know, very quickly after the start of treatment, whether it will work or not and that he adapts his therapeutic strategy accordingly.

Analyse d'images de stèles anciennes vietnamiennes

Updating....

DEVMAP Project

This is a collaboration project with INRA - Rennes. The main purpose of the project is to study the complex interactions between the evolution of insect populations and environmental factors affecting their functions. The project focus on Carabidae, one of the most common and beneficial insects in France. The first step is the digital imaging of Carabidae specimens. Then, the images will be studied by applying the analysis methods. The methods which have been used to study are based on the morphometry analysis and deep learning. My Ph.D. thesis took a place in this project.

HERITAGE CLASSIFICATION

From a couple of years, the project Heritage Observatory collects photos, post-cards and any graphical documents about South-East Asia. In order to present the data set in a more friendly, the first step is to classify the images into several domains. From this, the volunteers can choose the types of images that they prefer to annotate. In this collaboration, we propose the Deep Learning method for classify the images in the collection.

AUTOMATISATION OF ASSEMBLING ANCIENT DOCUMENT FRAGMENTS

This project is a collaboration with the archaeologists. In the old Egyptian times, the papyrus was used for administrative tasks. Then, it was used to wrap the mummies. The archaeologists have collected the papyrus as the fragments when they opened the mummies. Studying the papyrus can increase our knowledge about cultural and economic activity in the world areas. Currently, most of working with papyrus are manual. This process of assembling fragmented papyrus is time-consuming and effort. Computer technologies and image processing techniques were applied in order to help archaeologists in this task.