%0 Journal Article
%A Klett, Anusha
%A Raith, Dennis
%A Silvestrini, Paula
%A Stingl, Matías
%A Bermeitinger, Jonas
%A Sapre, Avani
%A Condor, Martin
%A Melachrinos, Roman
%A Kusterer, Mira
%A Brand, Alexandra
%A Pisani, Guido
%A Ullrich, Evelyn
%A Follo, Marie
%A Duque-Afonso, Jesús
%A Mertelsmann, Roland
%T Leveraging automated time-lapse microscopy coupled with deep learning to automate colony forming assay.
%J Frontiers in oncology
%V 15
%@ 2234-943X
%C Lausanne
%I Frontiers Media
%M DKFZ-2025-00502
%P 1520972
%D 2025
%X The colony forming assay (CFA) stands as a cornerstone technique for evaluating the clonal expansion ability of single cancer cells and is crucial for assessing drug efficacy. However, traditional CFAs rely on labor-intensive, endpoint manual counting, offering limited insights into the dynamic effects of treatment. To overcome these limitations, we developed an Artificial Intelligence (AI)-assisted automated CFA combining time-lapse microscopy for real-time tracking of colony formation.Using B-acute lymphoblastic leukemia (B-ALL) cells from an E2A-PBX1 mouse model, we cultured them in a collagen-based 3D matrix with cytokines under static conditions in a low volume (60 µl) culture vessel and validated its comparability to methylcellulose-based media. No significant differences in final colony count or plating efficiency were observed. Our automated platform utilizes a deep learning and multi-object tracking approach for colony counting. Brightfield images were used to train a YOLOv8 object detection network, achieving a mAP50 score of 86
%K artificial intelligence (Other)
%K automated colony forming assay (Other)
%K live cell imaging (Other)
%K personalized cancer therapy (Other)
%K primary B-ALL cells (Other)
%K time-lapse microscopy (Other)
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:40046624
%2 pmc:PMC11879803
%R 10.3389/fonc.2025.1520972
%U https://inrepo02.dkfz.de/record/299558