Journal article
Spatial Organization and Molecular Correlation of Tumor-Infiltrating Lymphocytes Using Deep Learning on Pathology Images
Cell reports (Cambridge), Vol.23(1), pp.181-193.e7
04/03/2018
DOI: 10.1016/j.celrep.2018.03.086
PMCID: PMC5943714
PMID: 29617659
Abstract
Beyond sample curation and basic pathologic characterization, the digitized H&E-stained images of TCGA samples remain underutilized. To highlight this resource, we present mappings of tumor-infiltrating lymphocytes (TILs) based on H&E images from 13 TCGA tumor types. These TIL maps are derived through computational staining using a convolutional neural network trained to classify patches of images. Affinity propagation revealed local spatial structure in TIL patterns and correlation with overall survival. TIL map structural patterns were grouped using standard histopathological parameters. These patterns are enriched in particular T cell subpopulations derived from molecular measures. TIL densities and spatial structure were differentially enriched among tumor types, immune subtypes, and tumor molecular subtypes, implying that spatial infiltrate state could reflect particular tumor cell aberration states. Obtaining spatial lymphocytic patterns linked to the rich genomic characterization of TCGA samples demonstrates one use for the TCGA image archives with insights into the tumor-immune microenvironment.
Details
- Title: Subtitle
- Spatial Organization and Molecular Correlation of Tumor-Infiltrating Lymphocytes Using Deep Learning on Pathology Images
- Creators
- Joel Saltz - Stony Brook UniversityRajarsi Gupta - Stony Brook UniversityLe Hou - Stony Brook UniversityTahsin Kurc - Stony Brook UniversityPankaj Singh - The University of Texas MD Anderson Cancer CenterVu Nguyen - Stony Brook UniversityDimitris Samaras - Stony Brook UniversityKenneth R Shroyer - Stony Brook UniversityTianhao Zhao - Stony Brook UniversityRebecca Batiste - Stony Brook UniversityJohn Van Arnam - University of PennsylvaniaIlya Shmulevich - Institute for Systems BiologyArvind U K Rao - Department of Bioinformatics and Computational Biology, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USAAlexander J Lazar - The University of Texas MD Anderson Cancer CenterAshish Sharma - Emory UniversityVésteinn Thorsson - Institute for Systems Biology
- Contributors
- Cancer Genome Atlas Research Network (Contributor)Deqin Ma (Contributor) - University of Iowa, PathologyMohammed M Milhem (Contributor) - University of Iowa, Internal MedicineAaron D Bossler (Contributor) - University of Iowa, Pathology
- Resource Type
- Journal article
- Publication Details
- Cell reports (Cambridge), Vol.23(1), pp.181-193.e7
- DOI
- 10.1016/j.celrep.2018.03.086
- PMID
- 29617659
- PMCID
- PMC5943714
- ISSN
- 2211-1247
- eISSN
- 2211-1247
- Grant note
- R37 CA214955 / NCI NIH HHS U24 CA143843 / NCI NIH HHS U24 CA180924 / NCI NIH HHS U24 CA199461 / NCI NIH HHS U24 CA210957 / NCI NIH HHS R01 LM009239 / NLM NIH HHS U54 HG003079 / NHGRI NIH HHS U24 CA143883 / NCI NIH HHS HHSN261201400007C / NCI NIH HHS U24 CA210990 / NCI NIH HHS U24 CA143799 / NCI NIH HHS R50 CA221675 / NCI NIH HHS U24 CA143867 / NCI NIH HHS U24 CA143858 / NCI NIH HHS U24 CA143882 / NCI NIH HHS U24 CA215109 / NCI NIH HHS U54 HG003067 / NHGRI NIH HHS U24 CA143845 / NCI NIH HHS U24 CA143835 / NCI NIH HHS U54 HG003273 / NHGRI NIH HHS U24 CA143840 / NCI NIH HHS U24 CA144025 / NCI NIH HHS U24 CA210950 / NCI NIH HHS U24 CA143866 / NCI NIH HHS U24 CA210949 / NCI NIH HHS R01 CA163722 / NCI NIH HHS U24 CA143848 / NCI NIH HHS
- Language
- English
- Date published
- 04/03/2018
- Academic Unit
- Hematology, Oncology, and Blood & Marrow Transplantation; Pathology; Internal Medicine
- Record Identifier
- 9984185274402771
Metrics
14 Record Views