About this item:

21 Views | 10 Downloads

Author Notes:

Rajarsi.Gupta@stonybrookmedicine.edu

Author Contributions: Conceptualization, J.S, T.K, R.G, H.L, A.L.V.D, D.S, D.F, T.Z, R.B; Methodology, J.S, T.K, H.L, L.H, S.A, D.S;

Data Curation, R.G; Running Experiments, H.L, S.A; Writing – Original Draft, H.L, R.G, T.K, J.S.A, A.S; Writing – Review & Editing, H.L, R.G, T.K, J.S, A.L.V.D;

Formal Analysis, J.S, R.G, A.L.V.D; Training Convolutional Neural Networks R.G, H.L; Supervision, J.S, T.K, D.S; Visualization, H.L, J.S.A, E.B; Software, E.B, J.S.A, A.S.

Competing interests: The author(s) declare no competing interests.

Subjects:

Research Funding:

This work was supported in part by 1U24CA180924-01A1, 3U24CA215109-02, and 1UG3CA225021-01 from the National Cancer Institute, R01LM011119-01 and R01LM009239 from the U.S. National Library of Medicine.

This work used the Extreme Science and Engineering Discovery Environment (XSEDE), which is supported by National Science Foundation grant number ACI-1548562.

Specifically, it used the Bridges system, which is supported by NSF award number ACI-1445606, at the Pittsburgh Supercomputing Center (PSC).

NCI Surveillance Research Program overseeing the Virtual Tissue Repository (VTR) Pilot Program, from which participating SEER cancer registries (Greater California, Connecticut, Hawaii, Iowa, Kentucky, and Louisiana) supplied the whole slide images utilized in algorithm development and testing.

The SEER VTR Pilot Program is supported by the Division of Cancer Control and Population Sciences at the National Cancer Institute of the National Institutes of Health.

Keywords:

  • eess.IV
  • eess.IV
  • cs.CV

Utilizing Automated Breast Cancer Detection to Identify Spatial Distributions of Tumor Infiltrating Lymphocytes in Invasive Breast Cancer

Show all authors Show less authors

Tools:

Journal Title:

arXiv preprint arXiv:1905.10841

Publisher:

Type of Work:

Article | Final Publisher PDF

Abstract:

Quantitative assessment of Tumor-TIL spatial relationships is increasingly important in both basic science and clinical aspects of breast cancer research. We have developed and evaluated convolutional neural network (CNN) analysis pipelines to generate combined maps of cancer regions and tumor infiltrating lymphocytes (TILs) in routine diagnostic breast cancer whole slide tissue images (WSIs). We produce interactive whole slide maps that provide 1) insight about the structural patterns and spatial distribution of lymphocytic infiltrates and 2) facilitate improved quantification of TILs. We evaluated both tumor and TIL analyses using three CNN networks - Resnet-34, VGG16 and Inception v4, and demonstrated that the results compared favorably to those obtained by what believe are the best published methods. We have produced open-source tools and generated a public dataset consisting of tumor/TIL maps for 1,015 TCGA breast cancer images. We also present a customized web-based interface that enables easy visualization and interactive exploration of high-resolution combined Tumor-TIL maps for 1,015TCGA invasive breast cancer cases that can be downloaded for further downstream analyses.

Copyright information:

This is an Open Access work distributed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (http://creativecommons.org/licenses/by-nc-sa/4.0/).

Creative Commons License

Export to EndNote