A deep convolutional neural network for segmentation of whole-slide pathology images identifies novel tumour cell-perivascular niche interactions that are associated with poor survival in glioblastoma

Amin Zadeh Shirazi; Mark D McDonnell; Eric Fornaciari; Narjes Sadat Bagherian; Kaitlin G Scheer; Michael S Samuel; Mahdi Yaghoobi; Rebecca J Ormsby; Santosh Poonnoose; Damon J Tumes; Guillermo A Gomez

doi:10.1038/s41416-021-01394-x

A deep convolutional neural network for segmentation of whole-slide pathology images identifies novel tumour cell-perivascular niche interactions that are associated with poor survival in glioblastoma

Br J Cancer. 2021 Aug;125(3):337-350. doi: 10.1038/s41416-021-01394-x. Epub 2021 Apr 29.

Authors

Amin Zadeh Shirazi^#^{1

2}, Mark D McDonnell^#², Eric Fornaciari^#³, Narjes Sadat Bagherian⁴, Kaitlin G Scheer¹, Michael S Samuel^{1

5}, Mahdi Yaghoobi⁶, Rebecca J Ormsby⁷, Santosh Poonnoose^{7

8}, Damon J Tumes¹, Guillermo A Gomez^#⁹

Affiliations

¹ Centre for Cancer Biology, SA Pathology and University of South Australia, Adelaide, SA, Australia.
² Computational Learning Systems Laboratory, UniSA STEM, University of South Australia, Mawson Lakes, SA, Australia.
³ Department of Mathematics of Computation, University of California, Los Angeles (UCLA), CA, USA.
⁴ Mashhad University of Medical Sciences, Mashhad, Iran.
⁵ Adelaide Medical School, University of Adelaide, Adelaide, SA, Australia.
⁶ Electrical and Computer Engineering Department, Department of Artificial Intelligence, Islamic Azad University, Mashhad Branch, Mashhad, Iran.
⁷ Flinders Health and Medical Research Institute, College of Medicine & Public Health, Flinders University, Adelaide, SA, Australia.
⁸ Department of Neurosurgery, Flinders Medical Centre, Bedford Park, SA, Australia.
⁹ Centre for Cancer Biology, SA Pathology and University of South Australia, Adelaide, SA, Australia. Guillermo.Gomez@unisa.edu.au.

^# Contributed equally.

Abstract

Background: Glioblastoma is the most aggressive type of brain cancer with high-levels of intra- and inter-tumour heterogeneity that contribute to its rapid growth and invasion within the brain. However, a spatial characterisation of gene signatures and the cell types expressing these in different tumour locations is still lacking.

Methods: We have used a deep convolutional neural network (DCNN) as a semantic segmentation model to segment seven different tumour regions including leading edge (LE), infiltrating tumour (IT), cellular tumour (CT), cellular tumour microvascular proliferation (CTmvp), cellular tumour pseudopalisading region around necrosis (CTpan), cellular tumour perinecrotic zones (CTpnz) and cellular tumour necrosis (CTne) in digitised glioblastoma histopathological slides from The Cancer Genome Atlas (TCGA). Correlation analysis between segmentation results from tumour images together with matched RNA expression data was performed to identify genetic signatures that are specific to different tumour regions.

Results: We found that spatially resolved gene signatures were strongly correlated with survival in patients with defined genetic mutations. Further in silico cell ontology analysis along with single-cell RNA sequencing data from resected glioblastoma tissue samples showed that these tumour regions had different gene signatures, whose expression was driven by different cell types in the regional tumour microenvironment. Our results further pointed to a key role for interactions between microglia/pericytes/monocytes and tumour cells that occur in the IT and CTmvp regions, which may contribute to poor patient survival.

Conclusions: This work identified key histopathological features that correlate with patient survival and detected spatially associated genetic signatures that contribute to tumour-stroma interactions and which should be investigated as new targets in glioblastoma. The source codes and datasets used are available in GitHub: https://github.com/amin20/GBM_WSSM .

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Brain Neoplasms / diagnostic imaging*
Brain Neoplasms / genetics
Deep Learning
Gene Expression Profiling / methods*
Gene Expression Regulation, Neoplastic
Gene Regulatory Networks*
Glioblastoma / diagnostic imaging*
Glioblastoma / genetics
Humans
Neural Networks, Computer
Radiographic Image Interpretation, Computer-Assisted / methods*
Single-Cell Analysis
Stem Cell Niche
Survival Analysis
Tumor Microenvironment