Machine learning in biomedical images to study infection and disease


Machine learning in biomedical images to study infection and disease

Yakimovich, A.

Recent advances in Machine Learning (ML) and Deep Learning (DL) are revolutionizing our abilities to analyze biomedical images and deepen our understanding of infection and disease. Among other host-pathogen interactions may be readily deciphered from microscopy data using convolutional neural networks (CNN). ML/DL algorithms may allow unambiguous scoring of virus-infected and uninfected cells in absence of specific labeling. Furthermore, accompanied by interpretability approaches, the ability of CNNs to learn representations, without explicit feature engineering, may allow uncovering yet unknown phenotypes in microscopy. One such example is our recent tandem segmentation-classification algorithm aimed to uncover morphological markers of Caenorhabditis elegans lifespan and motility. Taken together these novel approaches may facilitate novel discoveries in Infection and Disease Biology.

Keywords: deep learning; machine learning; bioimage analysis; host-pathogen interactions

  • Lecture (others)
    Big data analytical methods for complex systems, 06.-07.10.2022, Wroclaw, Poland
  • Lecture (others)
    CASUSCON, 11.-15.07.2022, Wroclaw, Poland
  • Lecture (others)
    Professor James Malone-Lee Christmas Lectures, 15.12.2022, Royal Free Hospital Campus, UCL, United Kingdom

Downloads

Permalink: https://www.hzdr.de/publications/Publ-35787
Publ.-Id: 35787