deepOrganoid: A brightfield cell viability model for screening matrix-embedded organoids.

Autor:	Powell RT; Center for Translational Cancer Research, Texas A&M University, 2121 W. Holcombe Blvd. Rm 911, Houston, TX 77030, United States. Electronic address: repowell@tamu.edu., Moussalli MJ; Department of Gastrointestinal Medical Oncology, UT MDACC, Houston, TX, United States., Guo L; Center for Translational Cancer Research, Texas A&M University, 2121 W. Holcombe Blvd. Rm 911, Houston, TX 77030, United States., Bae G; Center for Translational Cancer Research, Texas A&M University, 2121 W. Holcombe Blvd. Rm 911, Houston, TX 77030, United States., Singh P; Center for Translational Cancer Research, Texas A&M University, 2121 W. Holcombe Blvd. Rm 911, Houston, TX 77030, United States., Stephan C; Center for Translational Cancer Research, Texas A&M University, 2121 W. Holcombe Blvd. Rm 911, Houston, TX 77030, United States., Shureiqi I; Department of Gastrointestinal Medical Oncology, UT MDACC, Houston, TX, United States., Davies PJ; Center for Translational Cancer Research, Texas A&M University, 2121 W. Holcombe Blvd. Rm 911, Houston, TX 77030, United States.
Jazyk:	angličtina
Zdroj:	SLAS discovery : advancing life sciences R & D [SLAS Discov] 2022 Apr; Vol. 27 (3), pp. 175-184. Date of Electronic Publication: 2022 Mar 18.
DOI:	10.1016/j.slasd.2022.03.004
Abstrakt:	High-throughput viability screens are commonly used in the identification and development of chemotherapeutic drugs. These systems rely on the fidelity of the cellular model systems to recapitulate the drug response that occurs in vivo. In recent years, there has been an expansion in the utilization of patient-derived materials as well as advanced cell culture techniques, such as multi-cellular tumor organoids, to further enhance the translational relevance of cellular model systems. Simple quantitative analysis remains a challenge, primarily due to the difficulties of robust image segmentation in heterogenous 3D cultures. However, explicit segmentation is not required with the advancement of deep learning, and it can be used for both continuous (regression) or categorical classification problems. Deep learning approaches are additionally benefited by being fully data-driven and highly automatable, thus they can be established and run with minimal to no user-defined parameters. In this article, we describe the development and implementation of a regressive deep learning model trained on brightfield images of patient-derived organoids and use the terminal viability readout (CellTiter-Glo) as training labels. Ultimately, this has led to the generation of a non-invasive and label-free tool to evaluate changes in organoid viability. Competing Interests: Declaration of Competing Interest RTP had a non-financial collaboration with DeepCognition, the sole proprietors of Deep Learning Studios. All other authors have no conflicts of interest to report. This article is being reproduced in print post-publication in a sponsored print collection for distribution. The company sponsoring the print collection was not involved in the editorial selection or review of this article. (Copyright © 2022. Published by Elsevier Inc.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu