Published March 11, 2021 | Version 1.0.0

NaroNet: Objective-based learning of the tumor microenvironment from highly multiplexed immunostained images

  • 1. Solid Tumors and Biomarkers Program, IDISNA, and Ciberonc, Center for Applied Medical Research, University of Navarra, 31008, Pamplona, Spain
  • 2. Biological Systems and Engineering Division, Lawrence Berkeley National Laboratory, CA, 94720, Berkeley, USA
  • 3. Department of Pathology, Hospital Universitari Arnau de Vilanova, University of Lleida, IRBLleida, Lleida, 25198, Spain
  • 4. Department of Pathology, IDISNA, Ciberonc, Clínica Universidad de Navarra, University of Navarra, 31008, Pamplona, Spain

Description

All data supporting the findings of the publication "NaroNet: Objective-based learning of the tumor microenvironment from highly multiplexed immunostained images", including multiplex images, ground-truth masks, and patient data. The code used to produce the results of this study is available at https://github.com/djimenezsanchez/NaroNet

Synthetic_experiments.zip. contains synthetic patient cohorts generated from the synthetic tissue simulator called Synplex. Synplex tissue generator is thoroughly described in the arxiv preprint https://arxiv.org/abs/2103.04617 

Endometrial_High_grade_cancer.zip contains tiff stacks and patient data for the endometrial high-grade cancer cohort. Note that the endometrial high-grade cancer images provided are already unmixed.

Files

Endometrial_High_grade_cancer.zip

Files (27.8 GB)

Name Size
md5:1e638c740368c6bd2597a02505b53dd7
17.4 GB Preview Download
md5:4af3de8285ff61d187010bc02be64206
722.7 MB Preview Download
md5:eab3cb69e430a1cc8082df6a9dc3be89
9.8 GB Download

Additional details

Related works

Cites
Preprint: arXiv:2103.04617 (arXiv)
Is cited by
Preprint: arXiv:2103.05385 (arXiv)