Cargando…

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

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 morphol...

Descripción completa

Detalles Bibliográficos
Autores principales: Zormpas-Petridis, Konstantinos, Noguera, Rosa, Ivankovic, Daniela Kolarevic, Roxanis, Ioannis, Jamin, Yann, Yuan, Yinyin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7855703/
https://www.ncbi.nlm.nih.gov/pubmed/33552964
http://dx.doi.org/10.3389/fonc.2020.586292
_version_ 1783646197971419136
author Zormpas-Petridis, Konstantinos
Noguera, Rosa
Ivankovic, Daniela Kolarevic
Roxanis, Ioannis
Jamin, Yann
Yuan, Yinyin
author_facet Zormpas-Petridis, Konstantinos
Noguera, Rosa
Ivankovic, Daniela Kolarevic
Roxanis, Ioannis
Jamin, Yann
Yuan, Yinyin
author_sort Zormpas-Petridis, Konstantinos
collection PubMed
description 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.
format Online
Article
Text
id pubmed-7855703
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-78557032021-02-04 SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images Zormpas-Petridis, Konstantinos Noguera, Rosa Ivankovic, Daniela Kolarevic Roxanis, Ioannis Jamin, Yann Yuan, Yinyin Front Oncol Oncology 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. Frontiers Media S.A. 2021-01-20 /pmc/articles/PMC7855703/ /pubmed/33552964 http://dx.doi.org/10.3389/fonc.2020.586292 Text en Copyright © 2021 Zormpas-Petridis, Noguera, Ivankovic, Roxanis, Jamin and Yuan http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Zormpas-Petridis, Konstantinos
Noguera, Rosa
Ivankovic, Daniela Kolarevic
Roxanis, Ioannis
Jamin, Yann
Yuan, Yinyin
SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images
title SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images
title_full SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images
title_fullStr SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images
title_full_unstemmed SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images
title_short SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images
title_sort superhistopath: a deep learning pipeline for mapping tumor heterogeneity on low-resolution whole-slide digital histopathology images
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7855703/
https://www.ncbi.nlm.nih.gov/pubmed/33552964
http://dx.doi.org/10.3389/fonc.2020.586292
work_keys_str_mv AT zormpaspetridiskonstantinos superhistopathadeeplearningpipelineformappingtumorheterogeneityonlowresolutionwholeslidedigitalhistopathologyimages
AT noguerarosa superhistopathadeeplearningpipelineformappingtumorheterogeneityonlowresolutionwholeslidedigitalhistopathologyimages
AT ivankovicdanielakolarevic superhistopathadeeplearningpipelineformappingtumorheterogeneityonlowresolutionwholeslidedigitalhistopathologyimages
AT roxanisioannis superhistopathadeeplearningpipelineformappingtumorheterogeneityonlowresolutionwholeslidedigitalhistopathologyimages
AT jaminyann superhistopathadeeplearningpipelineformappingtumorheterogeneityonlowresolutionwholeslidedigitalhistopathologyimages
AT yuanyinyin superhistopathadeeplearningpipelineformappingtumorheterogeneityonlowresolutionwholeslidedigitalhistopathologyimages