Deep Learning Enables Individual Xenograft Cell Classification in Histological Images by Analysis of Contextual Features.

"the slide images are publicly available on zenodo 2 . the training data is publicly available on the github of scc. data availability archived images as at time of publication: https://doi"

"scc is released as an open-source plugin in imagej/fiji available at the following link: https://github com/biomedical-imaging-group/singlecellclassifier .; scc is supplied as a publicly available plugin in imagej/fiji [ ] and can be downloaded at the following link: https://github com/biomedical-imaging-group/singlecellclassifier .; the training data is publicly available on the github of scc. supplementary file 1 (pdf 3 15 mb) supplementary file 2(pdf 16 2 mb) supplementary file 3(pdf 1 8 mb) supplementary file 4(pdf 7 7 mb) supplementary file 5(pdf 8 6 mb) supplementary file 6(pdf 26 0 mb) supplementary file 7(pdf 0 96 mb) abbreviations scc singe cell clasifier h&e haematoxylin and eosin hbecs human breast epithelial cells hr hormone receptor mind mouse intraductal pdx patient-derived xenograft 1 https://github com/qupath/qupath-bioformats-extension 2 https://zenodo org/record/3960270 3 https://github com/biomedical-imaging-group/singlecellclassifier publisher's note springer nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations."

"Declarations Confic of Interest/Competing InterestThe authors declare that they have no conflict of interest. Ethical ApprovalAnimal experiments were performed in accordance with protocol approved by the Service de la Consommation et des Affaires vtrinaires of Canton de Vaud (VD 1541.4 and VD 1865.3). NOD.Cg-Prkdcscid Il2rgtm1Wjl/SzJ mice (NSG) breeders were purchased from Jackson Laboratories Consent to participateThe cantonal ethics committee approved the study on patient samples (183/10). Informed consent was obtained from all subjects. Confic of Interest/Competing Interest The authors declare that they have no conflict of interest."

"Funding Information Open Access funding provided by EPFL Lausanne. This work was supported by the EPFL Open Science Fund “Reproducible and Reusable Imaging Workflows” from the Imaging@EPFL initiative and the Swiss Data Science Center (SDSC). Q.J. was supported by the EPFL Center for Imaging under the fund OSF RENKU 563229. F.D.M. was supported by SNF (310030_179163/1 Exploring key steps of the metastatic cascade in estrogen receptor positive breast cancer in vivo). M.W. was supported by a generous donor represented by CARIGEST SA."