CaltechAUTHORS
  A Caltech Library Service

DeepCell Kiosk: Scaling deep learning-enabled cellular image analysis with Kubernetes

Bannon, Dylan and Moen, Erick and Schwartz, Morgan and Borba, Enrico and Kudo, Takamasa and Greenwald, Noah and Vijayakumar, Vibha and Chang, Brian and Pao, Edward and Osterman, Erik and Graf, William and Van Valen, David (2018) DeepCell Kiosk: Scaling deep learning-enabled cellular image analysis with Kubernetes. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20190916-101510993

[img] PDF (Sept. 16, 2020) - Submitted Version
Creative Commons Attribution Non-commercial.

2657Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190916-101510993

Abstract

Deep learning is transforming the analysis of biological images but applying these models to large datasets remains challenging. Here we describe the DeepCell Kiosk, cloud-native software that dynamically scales deep learning workflows to accommodate large imaging datasets. To demonstrate the scalability and affordability of this software, we identified cell nuclei in 10⁶ 1-megapixel images in ~5.5 h for ~$250, with a sub-$100 cost achievable depending on cluster configuration. The DeepCell Kiosk can be downloaded at https://github.com/vanvalenlab/kiosk-console; a persistent deployment is available at https://deepcell.org.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
https://doi.org/10.1101/505032DOIDiscussion Paper
https://github.com/vanvalenlab/kiosk-consoleRelated ItemCode
https://deepcell.orgRelated ItemDeepCell Kiosk
ORCID:
AuthorORCID
Moen, Erick0000-0002-5947-7044
Schwartz, Morgan0000-0002-1449-0026
Kudo, Takamasa0000-0002-9709-5549
Van Valen, David0000-0001-7534-7621
Alternate Title:Dynamic allocation of computational resources for deep learning-enabled cellular image analysis with Kubernetes
Additional Information:The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-NC 4.0 International license. bioRxiv preprint first posted online Dec. 22, 2018. This version posted September 16, 2020. We thank numerous colleagues including Anima Anandkumar, Michael Angelo, Justin Bois, Ian Brown, Andrea Butkovic, Long Cai, Isabella Camplisson, Markus Covert, Michael Elowitz, Jeremy Freeman, Christopher Frick, Lea Geontoro, Andrew Ho, Kevin Huang, KC Huang, Greg Johnson, Leeat Keren, Daniel Litovitz, Derek Macklin, Uri Manor, Shivam Patel, Arjun Raj, Nicolas Pelaez Restrepo, Cole Pavelchek, Sheel Shah, and Matt Thomson for helpful discussions and contributing data. We gratefully acknowledge support from the Shurl and Kay Curci Foundation, the Rita Allen Foundation, the Paul Allen Family Foundation through the Allen Discovery Center at Stanford University, The Rosen Center for Bioengineering at Caltech, Google Research Cloud, Figure 8’s AI For Everyone award, and a subaward from NIH U24CA224309-01. Author Contributions: DB, WG, and DVV conceived the project; DB, WG, EO, and DVV designed the software architecture; DB, EO, and WG wrote the core components of the software; DB, EM, MS, EB, VV, BC, EO, WG, and DVV contributed to the code base; TK and EP collected data for annotation; EM, MS, NG, DB, WG, and DVV wrote documentation; DB, EM, WG, and DVV wrote the paper; DVV supervised the project. Competing Interests: The authors have filed a provisional patent for the described work; the software described here is available under a modified Apache license and is free for non-commercial uses.
Group:Rosen Bioengineering Center
Funders:
Funding AgencyGrant Number
Shurl and Kay Curci FoundationUNSPECIFIED
Rita Allen FoundationUNSPECIFIED
Paul Allen Family FoundationUNSPECIFIED
Donna and Benjamin M. Rosen Bioengineering CenterUNSPECIFIED
Google Research CloudUNSPECIFIED
Figure 8’s AI for EveryoneUNSPECIFIED
NIHU24CA224309-01
Record Number:CaltechAUTHORS:20190916-101510993
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190916-101510993
Official Citation:DeepCell Kiosk: Scaling deep learning-enabled cellular image analysis with Kubernetes. Dylan Bannon, Erick Moen, Morgan Schwartz, Enrico Borba, Takamasa Kudo, Noah Greenwald, Vibha Vijayakumar, Brian Chang, Edward Pao, Erik Osterman, William Graf, David Van Valen. bioRxiv 505032; doi: https://doi.org/10.1101/505032
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:98655
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:16 Sep 2019 17:42
Last Modified:22 Sep 2020 16:45

Repository Staff Only: item control page