6/27/2023 0 Comments Pixel 3 f1 2019 imagesUnderstanding the structural and functional relationships present in tissues is a challenge at the forefront of basic and translational research. All code, data, and models are released as a community resource. We then adapted Mesmer to harness cell lineage information in highly multiplexed datasets and used this enhanced version to quantify cell morphology changes during human gestation. Mesmer enabled the automated extraction of key cellular features, such as subcellular localization of protein signal, which was challenging with previous approaches. We demonstrated that Mesmer is more accurate than previous methods, generalizes to the full diversity of tissue types and imaging platforms in TissueNet, and achieves human-level performance. We used TissueNet to train Mesmer, a deep learning-enabled segmentation algorithm. To address this problem we constructed TissueNet, a dataset for training segmentation models that contains more than 1 million manually labeled cells, an order of magnitude more than all previously published segmentation training datasets. All authors provided feedback on the manuscript.Ī major challenge in the analysis of tissue imaging data is cell segmentation, the task of identifying the precise boundary of every cell in an image. generated MIBI-TOF data for morphological analyses. performed quality control on the training data. developed the pathologist evaluation software. developed the multiplex image analysis pipeline. developed Mesmer’s deep learning architecture. developed the human-in-the-loop pipeline. conceived the whole-cell segmentation approach. conceived the human-in-the-loop approach. Authorship ContributionsN.F.G., L.K., M.A., and D.V.V.
0 Comments
Leave a Reply. |