Author:
Bremer Jan P.,Baumdick Martin E.,Knorr Marius S.,Wegner Lucy H.M.,Wesche Jasmin,Jordan-Paiz Ana,Jung Johannes M.,Highton Andrew J.,Jäger Julia,Hinrichs Ole,Brias Sebastien,Niersch Jennifer,Müller Luisa,Schreurs Renée R.C.E.,Koyro Tobias,Löbl Sebastian,Mensching Leonore,Konczalla Leonie,Niehrs Annika,Vondran Florian W. R.,Schramm Christoph,Hölzemer Angelique,Oldhafer Karl,Königs Ingo,Kluge Stefan,Perez Daniel,Reinshagen Konrad,Pals Steven T.,Gagliani Nicola,Joosten Sander P.,Topf Maya,Altfeld Marcus,Bunders Madeleine J.
Abstract
AbstractOrganoids have emerged as a powerful technology to investigate human development, model diseases and for drug discovery. However, analysis tools to rapidly and reproducibly quantify organoid parameters from microscopy images are lacking. We developed a deep-learning based generalized organoid annotation tool (GOAT) using instance segmentation with pixel-level identification of organoids to quantify advanced organoid features. Using a multicentric dataset, including multiple organoid systems (e.g. liver, intestine, tumor, lung), we demonstrate generalization of the tool to annotate a diverse range of organoids generated in different laboratories and high performance in comparison to previously published methods. In sum, GOAT provides fast and unbiased quantification of organoid experiments to accelerate organoid research and facilitates novel high-throughput applications.
Publisher
Cold Spring Harbor Laboratory
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献