FIMM High Content Imaging and Analysis (FIMM-HCA) team has been recently published the work on mini-immunofluorescence assay to test for SARS-CoV-2 antibodies in patient blood samples in Cell Report Methods journal: https://doi.org/10.1016/j.crmeth.2023.100565
Researchers from the FIMM High Content Imaging and Analysis (FIMM-HCA) Unit (partner of the Finnish Advanced Microscopy Node) have unveiled a cutting-edge method combining image-based serology and machine learning to detect SARS-CoV-2 antibodies. Led by Lassi Paavolainen, Academy Research Fellow at the Institute for Molecular Medicine Finland, their mini-immunofluorescence assay leverages custom neural network analysis for high-throughput testing in low-biosafety environments.
This breakthrough not only enhances disease detection but also sets a high standard in data accessibility through the BY-COVID project. The entire dataset, including raw images and segmentation masks, is now publicly available on the BioImage Archive, marking a pivotal move towards FAIR (Findable, Accessible, Interoperable, Reusable) data sharing. The metadata for the images is described according to the REMBI guidelines (REcommended Metadata for Biological Images: https://doi.org/10.1038/s41592-021-01166-8).
Isabel Kemmer, FAIR Data Steward at Euro-BioImaging, was in charge of bringing COVID-19 and infectious diseases related image datasets into public repositories. She highlighted the importance of such initiatives in advancing infectious disease research. “This dataset will catalyze future studies and foster innovation in bioimage analysis,” she stated.
For more details, visit the BioImage Archive and explore the comprehensive dataset under project S-BIAD1076: https://www.ebi.ac.uk/biostudies/BioImages/studies/S-BIAD1076
Read full story on Euro-BioImaging webpage: https://www.eurobioimaging.eu/news/combining-image-based-serology-and-machine-learning-to-screen-for-sars-cov-2/
Raw image and cell segmentation masks from S-BIAD1076. Image provided by Lassi Paavolainen
