print · login   

Vision Transformer Model for Microscopy Images

Project Description

Together with colleagues at the Biomedical Sciences department at Radboudumc, we run an imaging platform for cancer research, based on the so-called "Vectra Polaris" digital microscopy platform. To understand the background of this system, you can watch a brief promotional video (in Dutch, with the popular singer “Do”) about the underlying research here: https://www.youtube.com/watch?v=VHRHWJw6jcA and a more technical video that explains the system is available here: https://app.jove.com/v/65717/author-spotlight-unlocking-insights-into-immune-cell-landscape

Over the years, we have collected several terabytes of human tissue sample images and we would now like to leverage this treasure trove of data to build smarter biomedical computer vision systems for the future. Specifically, when training our existing machine learning pipeline to detect and classify cells in these images (https://doi.org/10.1093/biomethods/bpae094), we have created a hand-curated dataset of almost 200,000 cell annotations. We would now like to use a self-supervised vision transformer model -- perhaps DinoV3 by Meta -- to automatically scale up this annotation dataset by approximately 10-fold. We would then like to use this "10xed" dataset to determine whether it leads to performance improvements for our existing machine learning models or perhaps even enables us to train our own foundation model that is specific for this kind of data.

People

Johannes Textor

Requirements

  • RU student with a Bachelor degree in Computing Science or Artificial Intelligence, or comparable degree
  • Interest in working on systems that are used in practice
  • Interest in image processing and biomedical imaging
  • Some experience with Python and Linux

Overview

  • Preferably a Master’s Thesis; a research internship could be possible for students with pre-existing knowledge in this field
  • Duration: 3 - 6 months.
  • Location: Computational Immunology Group, DAS (https://computational-immunology.org)
  • For further information on the project, please reach out to Johannes Textor (johannes.textor@ru.nl)