Seminar: Deep learning techniques in bioimaging

When

March 28, 2024    
1:00 pm - 2:00 pm
Seminar: Deep learning techniques in bioimaging

March 28th at 13:00-14:00
On-site event
Auditorium Biochemistry, Biocity 3rd floor

Estibaliz Gómez de Mariscal, Instituto Gulbenkian de Ciência, Portugal
Deep learning enabled image-driven scientific discovery

Host: Guillaumen Jacquemet (guillaume.jacquemet@abo.fi)

 

Esti is currently a postdoctoral researcher in Prof. Ricardo Henriques’ group at Instituto Gulbenkian de Ciência in Portugal and is visiting us for a few weeks.

Recent advancements in bioimage analysis, particularly leveraging deep learning techniques, are revolutionising image-driven scientific discovery by enhancing the speed, accuracy and capacity to extract valuable insights and relationships from biological images. Their ability to uncover intricate patterns and seamlessly adapting to the increasing volume of experimental data holds promise for heuristic approaches in research. In this seminar, I will introduce our methodological contributions within the realm of 3D cancer cell migration and phototoxicity assessment.
Our journey will begin with a discussion on how automated segmentation and tracking methodologies provided us better with a better understanding of dendritic protrusions’ role in mesenchymal 3D cell migration and have let us quantify diverse migration patterns. Furthermore, I will discuss our research concerning the quantitative evaluation of cell photodamage in the context of live-cell imaging acquisitions.
Lastly, I will briefly introduce the different tools developed together with colleagues to foster the accessibility and reproducibility of deep learning approaches. These collaborative efforts include tools to deploy trained deep learning models (deepImageJ), easily train and evaluate them ensuring their long-term reproducibility (DL4MicEverywhere), and openly share them in a documented manner (BioImage Model Zoo).

Selected Publications

DL4MicEverywhere: Deep learning for microscopy made flexible, shareable, and reproducible. Iván Hidalgo-Cenalmor, Joanna W Pylvänäinen, Mariana G Ferreira, Craig T Russell, Ignacio Arganda-Carreras, AI4Life Consortium, Guillaume Jacquemet, Ricardo Henriques, Estibaliz Gómez-de-Mariscal. bioRxiv 2023.11.19.567606; doi: https://doi.org/10.1101/2023.11.19.567606

BioImage Model Zoo: A Community-Driven Resource for Accessible Deep Learning in BioImage Analysis. Wei Ouyang, Fynn Beuttenmueller, Estibaliz Gómez-de-Mariscal, Constantin Pape, Tom Burke, Carlos Garcia-López-de-Haro, Craig Russell, Lucía Moya-Sans, Cristina de-la-Torre-Gutiérrez, Deborah Schmidt, Dominik Kutra, Maksim Novikov, Martin Weigert, Uwe Schmidt, Peter Bankhead, Guillaume Jacquemet, Daniel Sage, Ricardo Henriques, Arrate Muñoz-Barrutia, Emma Lundberg, Florian Jug, Anna Kreshuk. bioRxiv 2022.06.07.495102; doi: https://doi.org/10.1101/2022.06.07.495102

A user-friendly environment to run deep learning models in Image. Gómez-de-Mariscal, E., García-López-de-Haro, C., Ouyang, W. et al. DeepImageJ: J. Nat Methods 18, 1192–1195 (2021). https://doi.org/10.1038/s41592-021-01262-9