Cargando…
Cancer diagnosis through a tandem of classifiers for digitized histopathological slides
The current research study is concerned with the automated differentiation between histopathological slides from colon tissues with respect to four classes (healthy tissue and cancerous of grades 1, 2 or 3) through an optimized ensemble of predictors. Six distinct classifiers with prediction accurac...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6334911/ https://www.ncbi.nlm.nih.gov/pubmed/30650087 http://dx.doi.org/10.1371/journal.pone.0209274 |
_version_ | 1783387807825264640 |
---|---|
author | Lichtblau, Daniel Stoean, Catalin |
author_facet | Lichtblau, Daniel Stoean, Catalin |
author_sort | Lichtblau, Daniel |
collection | PubMed |
description | The current research study is concerned with the automated differentiation between histopathological slides from colon tissues with respect to four classes (healthy tissue and cancerous of grades 1, 2 or 3) through an optimized ensemble of predictors. Six distinct classifiers with prediction accuracies ranging from 87% to 95% are considered for the task. The proposed method of combining them takes into account the probabilities of the individual classifiers for each sample to be assigned to any of the four classes, optimizes weights for each technique by differential evolution and attains an accuracy that is significantly better than the individual results. Moreover, a degree of confidence is defined that would allow the pathologists to separate the data into two distinct sets, one that is correctly classified with a high level of confidence and the rest that would need their further attention. The tandem is also validated on other benchmark data sets. The proposed methodology proves to be efficient in improving the classification accuracy of each algorithm taken separately and performs reasonably well on other data sets, even with default weights. In addition, by establishing a degree of confidence the method becomes more viable for use by actual practitioners. |
format | Online Article Text |
id | pubmed-6334911 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-63349112019-01-31 Cancer diagnosis through a tandem of classifiers for digitized histopathological slides Lichtblau, Daniel Stoean, Catalin PLoS One Research Article The current research study is concerned with the automated differentiation between histopathological slides from colon tissues with respect to four classes (healthy tissue and cancerous of grades 1, 2 or 3) through an optimized ensemble of predictors. Six distinct classifiers with prediction accuracies ranging from 87% to 95% are considered for the task. The proposed method of combining them takes into account the probabilities of the individual classifiers for each sample to be assigned to any of the four classes, optimizes weights for each technique by differential evolution and attains an accuracy that is significantly better than the individual results. Moreover, a degree of confidence is defined that would allow the pathologists to separate the data into two distinct sets, one that is correctly classified with a high level of confidence and the rest that would need their further attention. The tandem is also validated on other benchmark data sets. The proposed methodology proves to be efficient in improving the classification accuracy of each algorithm taken separately and performs reasonably well on other data sets, even with default weights. In addition, by establishing a degree of confidence the method becomes more viable for use by actual practitioners. Public Library of Science 2019-01-16 /pmc/articles/PMC6334911/ /pubmed/30650087 http://dx.doi.org/10.1371/journal.pone.0209274 Text en © 2019 Lichtblau, Stoean http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Lichtblau, Daniel Stoean, Catalin Cancer diagnosis through a tandem of classifiers for digitized histopathological slides |
title | Cancer diagnosis through a tandem of classifiers for digitized histopathological slides |
title_full | Cancer diagnosis through a tandem of classifiers for digitized histopathological slides |
title_fullStr | Cancer diagnosis through a tandem of classifiers for digitized histopathological slides |
title_full_unstemmed | Cancer diagnosis through a tandem of classifiers for digitized histopathological slides |
title_short | Cancer diagnosis through a tandem of classifiers for digitized histopathological slides |
title_sort | cancer diagnosis through a tandem of classifiers for digitized histopathological slides |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6334911/ https://www.ncbi.nlm.nih.gov/pubmed/30650087 http://dx.doi.org/10.1371/journal.pone.0209274 |
work_keys_str_mv | AT lichtblaudaniel cancerdiagnosisthroughatandemofclassifiersfordigitizedhistopathologicalslides AT stoeancatalin cancerdiagnosisthroughatandemofclassifiersfordigitizedhistopathologicalslides |