Cargando…

Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma

Identification of pancreatic ductal adenocarcinoma (PDAC) and precursor lesions in histological tissue slides can be challenging and elaborate, especially due to tumor heterogeneity. Thus, supportive tools for the identification of anatomical and pathological tissue structures are desired. Deep lear...

Descripción completa

Detalles Bibliográficos
Autores principales: Kriegsmann, Mark, Kriegsmann, Katharina, Steinbuss, Georg, Zgorzelski, Christiane, Kraft, Anne, Gaida, Matthias M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8160892/
https://www.ncbi.nlm.nih.gov/pubmed/34065423
http://dx.doi.org/10.3390/ijms22105385
_version_ 1783700386597568512
author Kriegsmann, Mark
Kriegsmann, Katharina
Steinbuss, Georg
Zgorzelski, Christiane
Kraft, Anne
Gaida, Matthias M.
author_facet Kriegsmann, Mark
Kriegsmann, Katharina
Steinbuss, Georg
Zgorzelski, Christiane
Kraft, Anne
Gaida, Matthias M.
author_sort Kriegsmann, Mark
collection PubMed
description Identification of pancreatic ductal adenocarcinoma (PDAC) and precursor lesions in histological tissue slides can be challenging and elaborate, especially due to tumor heterogeneity. Thus, supportive tools for the identification of anatomical and pathological tissue structures are desired. Deep learning methods recently emerged, which classify histological structures into image categories with high accuracy. However, to date, only a limited number of classes and patients have been included in histopathological studies. In this study, scanned histopathological tissue slides from tissue microarrays of PDAC patients (n = 201, image patches n = 81.165) were extracted and assigned to a training, validation, and test set. With these patches, we implemented a convolutional neuronal network, established quality control measures and a method to interpret the model, and implemented a workflow for whole tissue slides. An optimized EfficientNet algorithm achieved high accuracies that allowed automatically localizing and quantifying tissue categories including pancreatic intraepithelial neoplasia and PDAC in whole tissue slides. SmoothGrad heatmaps allowed explaining image classification results. This is the first study that utilizes deep learning for automatic identification of different anatomical tissue structures and diseases on histopathological images of pancreatic tissue specimens. The proposed approach is a valuable tool to support routine diagnostic review and pancreatic cancer research.
format Online
Article
Text
id pubmed-8160892
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-81608922021-05-29 Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma Kriegsmann, Mark Kriegsmann, Katharina Steinbuss, Georg Zgorzelski, Christiane Kraft, Anne Gaida, Matthias M. Int J Mol Sci Article Identification of pancreatic ductal adenocarcinoma (PDAC) and precursor lesions in histological tissue slides can be challenging and elaborate, especially due to tumor heterogeneity. Thus, supportive tools for the identification of anatomical and pathological tissue structures are desired. Deep learning methods recently emerged, which classify histological structures into image categories with high accuracy. However, to date, only a limited number of classes and patients have been included in histopathological studies. In this study, scanned histopathological tissue slides from tissue microarrays of PDAC patients (n = 201, image patches n = 81.165) were extracted and assigned to a training, validation, and test set. With these patches, we implemented a convolutional neuronal network, established quality control measures and a method to interpret the model, and implemented a workflow for whole tissue slides. An optimized EfficientNet algorithm achieved high accuracies that allowed automatically localizing and quantifying tissue categories including pancreatic intraepithelial neoplasia and PDAC in whole tissue slides. SmoothGrad heatmaps allowed explaining image classification results. This is the first study that utilizes deep learning for automatic identification of different anatomical tissue structures and diseases on histopathological images of pancreatic tissue specimens. The proposed approach is a valuable tool to support routine diagnostic review and pancreatic cancer research. MDPI 2021-05-20 /pmc/articles/PMC8160892/ /pubmed/34065423 http://dx.doi.org/10.3390/ijms22105385 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kriegsmann, Mark
Kriegsmann, Katharina
Steinbuss, Georg
Zgorzelski, Christiane
Kraft, Anne
Gaida, Matthias M.
Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma
title Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma
title_full Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma
title_fullStr Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma
title_full_unstemmed Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma
title_short Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma
title_sort deep learning in pancreatic tissue: identification of anatomical structures, pancreatic intraepithelial neoplasia, and ductal adenocarcinoma
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8160892/
https://www.ncbi.nlm.nih.gov/pubmed/34065423
http://dx.doi.org/10.3390/ijms22105385
work_keys_str_mv AT kriegsmannmark deeplearninginpancreatictissueidentificationofanatomicalstructurespancreaticintraepithelialneoplasiaandductaladenocarcinoma
AT kriegsmannkatharina deeplearninginpancreatictissueidentificationofanatomicalstructurespancreaticintraepithelialneoplasiaandductaladenocarcinoma
AT steinbussgeorg deeplearninginpancreatictissueidentificationofanatomicalstructurespancreaticintraepithelialneoplasiaandductaladenocarcinoma
AT zgorzelskichristiane deeplearninginpancreatictissueidentificationofanatomicalstructurespancreaticintraepithelialneoplasiaandductaladenocarcinoma
AT kraftanne deeplearninginpancreatictissueidentificationofanatomicalstructurespancreaticintraepithelialneoplasiaandductaladenocarcinoma
AT gaidamatthiasm deeplearninginpancreatictissueidentificationofanatomicalstructurespancreaticintraepithelialneoplasiaandductaladenocarcinoma