BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN BEGIN:VEVENT UID:601@biocityturku.fi DTSTART;TZID=Europe/Helsinki:20240328T130000 DTEND;TZID=Europe/Helsinki:20240328T140000 DTSTAMP:20240319T110341Z URL:https://biocityturku.fi/events/seminar-deep-learning-techniques-in-bio imaging/ SUMMARY:Seminar: Deep learning techniques in bioimaging DESCRIPTION:March 28th at 13:00-14:00\nOn-site event\nAuditorium Biochemist ry\, Biocity 3rd floor\n\nEstibaliz Gómez de Mariscal\, Instituto Gulbenk ian de Ciência\, Portugal\nDeep learning enabled image-driven scientific discovery\n\nHost: Guillaumen Jacquemet (guillaume.jacquemet@abo.fi)\n\n&n bsp\;\n\nEsti is currently a postdoctoral researcher in Prof. Ricardo Henr iques' group at Instituto Gulbenkian de Ciência in Portugal and is visiti ng us for a few weeks.\n\nRecent advancements in bioimage analysis\, parti cularly leveraging deep learning techniques\, are revolutionising image-dr iven scientific discovery by enhancing the speed\, accuracy and capacity t o extract valuable insights and relationships from biological images. Thei r ability to uncover intricate patterns and seamlessly adapting to the inc reasing volume of experimental data holds promise for heuristic approaches in research. In this seminar\, I will introduce our methodological contri butions within the realm of 3D cancer cell migration and phototoxicity ass essment.\nOur journey will begin with a discussion on how automated segmen tation and tracking methodologies provided us better with a better underst anding of dendritic protrusions’ role in mesenchymal 3D cell migration a nd have let us quantify diverse migration patterns. Furthermore\, I will d iscuss our research concerning the quantitative evaluation of cell photoda mage in the context of live-cell imaging acquisitions.\nLastly\, I will br iefly 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-t erm reproducibility (DL4MicEverywhere)\, and openly share them in a docume nted manner (BioImage Model Zoo).\n\n\nSelected Publications\n\nDL4MicEver ywhere: Deep learning for microscopy made flexible\, shareable\, and repro ducible. Iván Hidalgo-Cenalmor\, Joanna W Pylvänäinen\, Mariana G Ferre ira\, Craig T Russell\, Ignacio Arganda-Carreras\, AI4Life Consortium\, Gu illaume Jacquemet\, Ricardo Henriques\, Estibaliz Gómez-de-Mariscal. bioR xiv 2023.11.19.567606\; doi: https://doi.org/10.1101/2023.11.19.567606\n\n BioImage Model Zoo: A Community-Driven Resource for Accessible Deep Learni ng in BioImage Analysis. Wei Ouyang\, Fynn Beuttenmueller\, Estibaliz Góm ez-de-Mariscal\, Constantin Pape\, Tom Burke\, Carlos Garcia-López-de-Har o\, Craig Russell\, Lucía Moya-Sans\, Cristina de-la-Torre-Gutiérrez\, D eborah Schmidt\, Dominik Kutra\, Maksim Novikov\, Martin Weigert\, Uwe Sch midt\, Peter Bankhead\, Guillaume Jacquemet\, Daniel Sage\, Ricardo Henriq ues\, Arrate Muñoz-Barrutia\, Emma Lundberg\, Florian Jug\, Anna Kreshuk. bioRxiv 2022.06.07.495102\; doi: https://doi.org/10.1101/2022.06.07.49510 2\n\nA user-friendly environment to run deep learning models in Image. Gó mez-de-Mariscal\, E.\, García-López-de-Haro\, C.\, Ouyang\, W. et al. De epImageJ: J. Nat Methods 18\, 1192–1195 (2021). https://doi.org/10.1038/ s41592-021-01262-9\n\n \;\n\n \; ATTACH;FMTTYPE=image/jpeg:https://biocityturku.fi/wp-content/uploads/AAU-t humbnail.jpg CATEGORIES:Other events END:VEVENT BEGIN:VTIMEZONE TZID:Europe/Helsinki X-LIC-LOCATION:Europe/Helsinki BEGIN:STANDARD DTSTART:20231029T030000 TZOFFSETFROM:+0300 TZOFFSETTO:+0200 TZNAME:EET END:STANDARD END:VTIMEZONE END:VCALENDAR