SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images.

Fecha de publicación: 20/01/2021 Fecha Ahead of Print: 20/01/2021

Autores de INCLIVA

• 

  Rosa Noguera Salva

  Autor

Participantes ajenos a INCLIVA

• Zormpas-Petridis, K
• Ivankovic, DK
• Roxanis, I
• Jamin, Y
• Yuan, YY

Grupos y Plataformas de I+D+i

• Grupo de Investigación Translacional de Tumores Sólidos Pediátricos

  

  Leading Researcher

  Samuel Navarro Fos

Abstract

High computational cost associated with digital pathology image analysis approaches is a challenge towards their translation in routine pathology clinic. Here, we propose a computationally efficient framework (SuperHistopath), designed to map global context features reflecting the rich tumor morphological heterogeneity. SuperHistopath efficiently combines i) a segmentation approach using the linear iterative clustering (SLIC) superpixels algorithm applied directly on the whole-slide images at low resolution (5x magnification) to adhere to region boundaries and form homogeneous spatial units at tissue-level, followed by ii) classification of superpixels using a convolution neural network (CNN). To demonstrate how versatile SuperHistopath was in accomplishing histopathology tasks, we classified tumor tissue, stroma, necrosis, lymphocytes clusters, differentiating regions, fat, hemorrhage and normal tissue, in 127 melanomas, 23 triple-negative breast cancers, and 73 samples from transgenic mouse models of high-risk childhood neuroblastoma with high accuracy (98.8%, 93.1% and 98.3% respectively). Furthermore, SuperHistopath enabled discovery of significant differences in tumor phenotype of neuroblastoma mouse models emulating genomic variants of high-risk disease, and stratification of melanoma patients (high ratio of lymphocyte-to-tumor superpixels (p = 0.015) and low stroma-to-tumor ratio (p = 0.028) were associated with a favorable prognosis). Finally, SuperHistopath is efficient for annotation of ground-truth datasets (as there is no need of boundary delineation), training and application (~5 min for classifying a whole-slide image and as low as ~30 min for network training). These attributes make SuperHistopath particularly attractive for research in rich datasets and could also facilitate its adoption in the clinic to accelerate pathologist workflow with the quantification of phenotypes, predictive/prognosis markers.

Copyright © 2021 Zormpas-Petridis, Noguera, Ivankovic, Roxanis, Jamin and Yuan.

Keywords

• breast cancer; computational pathology; deep learning; digital pathology; machine learning; melanoma; neuroblastoma; tumor region classification