Cargando…

Annotations, Ontologies, and Whole Slide Images – Development of an Annotated Ontology-Driven Whole Slide Image Library of Normal and Abnormal Human Tissue

OBJECTIVE: Digital pathology is today a widely used technology, and the digitalization of microscopic slides into whole slide images (WSIs) allows the use of machine learning algorithms as a tool in the diagnostic process. In recent years, “deep learning” algorithms for image analysis have been appl...

Descripción completa

Detalles Bibliográficos
Autores principales: Lindman, Karin, Rose, Jerómino F., Lindvall, Martin, Lundström, Claes, Treanor, Darren
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Wolters Kluwer - Medknow 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6669998/
https://www.ncbi.nlm.nih.gov/pubmed/31523480
http://dx.doi.org/10.4103/jpi.jpi_81_18
_version_ 1783440484807475200
author Lindman, Karin
Rose, Jerómino F.
Lindvall, Martin
Lundström, Claes
Treanor, Darren
author_facet Lindman, Karin
Rose, Jerómino F.
Lindvall, Martin
Lundström, Claes
Treanor, Darren
author_sort Lindman, Karin
collection PubMed
description OBJECTIVE: Digital pathology is today a widely used technology, and the digitalization of microscopic slides into whole slide images (WSIs) allows the use of machine learning algorithms as a tool in the diagnostic process. In recent years, “deep learning” algorithms for image analysis have been applied to digital pathology with great success. The training of these algorithms requires a large volume of high-quality images and image annotations. These large image collections are a potent source of information, and to use and share the information, standardization of the content through a consistent terminology is essential. The aim of this project was to develop a pilot dataset of exhaustive annotated WSI of normal and abnormal human tissue and link the annotations to appropriate ontological information. MATERIALS AND METHODS: Several biomedical ontologies and controlled vocabularies were investigated with the aim of selecting the most suitable ontology for this project. The selection criteria required an ontology that covered anatomical locations, histological subcompartments, histopathologic diagnoses, histopathologic terms, and generic terms such as normal, abnormal, and artifact. WSIs of normal and abnormal tissue from 50 colon resections and 69 skin excisions, diagnosed 2015-2016 at the Department of Clinical Pathology in Linköping, were randomly collected. These images were manually and exhaustively annotated at the level of major subcompartments, including normal or abnormal findings and artifacts. RESULTS: Systemized nomenclature of medicine clinical terms (SNOMED CT) was chosen, and the annotations were linked to its codes and terms. Two hundred WSI were collected and annotated, resulting in 17,497 annotations, covering a total area of 302.19 cm(2), equivalent to 107,7 gigapixels. Ninety-five unique SNOMED CT codes were used. The time taken to annotate a WSI varied from 45 s to over 360 min, a total time of approximately 360 h. CONCLUSION: This work resulted in a dataset of 200 exhaustive annotated WSIs of normal and abnormal tissue from the colon and skin, and it has informed plans to build a comprehensive library of annotated WSIs. SNOMED CT was found to be the best ontology for annotation labeling. This project also demonstrates the need for future development of annotation tools in order to make the annotation process more efficient.
format Online
Article
Text
id pubmed-6669998
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Wolters Kluwer - Medknow
record_format MEDLINE/PubMed
spelling pubmed-66699982019-09-13 Annotations, Ontologies, and Whole Slide Images – Development of an Annotated Ontology-Driven Whole Slide Image Library of Normal and Abnormal Human Tissue Lindman, Karin Rose, Jerómino F. Lindvall, Martin Lundström, Claes Treanor, Darren J Pathol Inform Research Article OBJECTIVE: Digital pathology is today a widely used technology, and the digitalization of microscopic slides into whole slide images (WSIs) allows the use of machine learning algorithms as a tool in the diagnostic process. In recent years, “deep learning” algorithms for image analysis have been applied to digital pathology with great success. The training of these algorithms requires a large volume of high-quality images and image annotations. These large image collections are a potent source of information, and to use and share the information, standardization of the content through a consistent terminology is essential. The aim of this project was to develop a pilot dataset of exhaustive annotated WSI of normal and abnormal human tissue and link the annotations to appropriate ontological information. MATERIALS AND METHODS: Several biomedical ontologies and controlled vocabularies were investigated with the aim of selecting the most suitable ontology for this project. The selection criteria required an ontology that covered anatomical locations, histological subcompartments, histopathologic diagnoses, histopathologic terms, and generic terms such as normal, abnormal, and artifact. WSIs of normal and abnormal tissue from 50 colon resections and 69 skin excisions, diagnosed 2015-2016 at the Department of Clinical Pathology in Linköping, were randomly collected. These images were manually and exhaustively annotated at the level of major subcompartments, including normal or abnormal findings and artifacts. RESULTS: Systemized nomenclature of medicine clinical terms (SNOMED CT) was chosen, and the annotations were linked to its codes and terms. Two hundred WSI were collected and annotated, resulting in 17,497 annotations, covering a total area of 302.19 cm(2), equivalent to 107,7 gigapixels. Ninety-five unique SNOMED CT codes were used. The time taken to annotate a WSI varied from 45 s to over 360 min, a total time of approximately 360 h. CONCLUSION: This work resulted in a dataset of 200 exhaustive annotated WSIs of normal and abnormal tissue from the colon and skin, and it has informed plans to build a comprehensive library of annotated WSIs. SNOMED CT was found to be the best ontology for annotation labeling. This project also demonstrates the need for future development of annotation tools in order to make the annotation process more efficient. Wolters Kluwer - Medknow 2019-07-23 /pmc/articles/PMC6669998/ /pubmed/31523480 http://dx.doi.org/10.4103/jpi.jpi_81_18 Text en Copyright: © 2019 Journal of Pathology Informatics http://creativecommons.org/licenses/by-nc-sa/4.0 This is an open access journal, and articles are distributed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License, which allows others to remix, tweak, and build upon the work non-commercially, as long as appropriate credit is given and the new creations are licensed under the identical terms.
spellingShingle Research Article
Lindman, Karin
Rose, Jerómino F.
Lindvall, Martin
Lundström, Claes
Treanor, Darren
Annotations, Ontologies, and Whole Slide Images – Development of an Annotated Ontology-Driven Whole Slide Image Library of Normal and Abnormal Human Tissue
title Annotations, Ontologies, and Whole Slide Images – Development of an Annotated Ontology-Driven Whole Slide Image Library of Normal and Abnormal Human Tissue
title_full Annotations, Ontologies, and Whole Slide Images – Development of an Annotated Ontology-Driven Whole Slide Image Library of Normal and Abnormal Human Tissue
title_fullStr Annotations, Ontologies, and Whole Slide Images – Development of an Annotated Ontology-Driven Whole Slide Image Library of Normal and Abnormal Human Tissue
title_full_unstemmed Annotations, Ontologies, and Whole Slide Images – Development of an Annotated Ontology-Driven Whole Slide Image Library of Normal and Abnormal Human Tissue
title_short Annotations, Ontologies, and Whole Slide Images – Development of an Annotated Ontology-Driven Whole Slide Image Library of Normal and Abnormal Human Tissue
title_sort annotations, ontologies, and whole slide images – development of an annotated ontology-driven whole slide image library of normal and abnormal human tissue
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6669998/
https://www.ncbi.nlm.nih.gov/pubmed/31523480
http://dx.doi.org/10.4103/jpi.jpi_81_18
work_keys_str_mv AT lindmankarin annotationsontologiesandwholeslideimagesdevelopmentofanannotatedontologydrivenwholeslideimagelibraryofnormalandabnormalhumantissue
AT rosejerominof annotationsontologiesandwholeslideimagesdevelopmentofanannotatedontologydrivenwholeslideimagelibraryofnormalandabnormalhumantissue
AT lindvallmartin annotationsontologiesandwholeslideimagesdevelopmentofanannotatedontologydrivenwholeslideimagelibraryofnormalandabnormalhumantissue
AT lundstromclaes annotationsontologiesandwholeslideimagesdevelopmentofanannotatedontologydrivenwholeslideimagelibraryofnormalandabnormalhumantissue
AT treanordarren annotationsontologiesandwholeslideimagesdevelopmentofanannotatedontologydrivenwholeslideimagelibraryofnormalandabnormalhumantissue