Cargando…

Comparison of a machine and deep learning model for automated tumor annotation on digitized whole slide prostate cancer histology

One in eight men will be affected by prostate cancer (PCa) in their lives. While the current clinical standard prognostic marker for PCa is the Gleason score, it is subject to inter-reviewer variability. This study compares two machine learning methods for discriminating between cancerous regions on...

Descripción completa

Detalles Bibliográficos
Autores principales: Duenweg, Savannah R., Brehler, Michael, Bobholz, Samuel A., Lowman, Allison K., Winiarz, Aleksandra, Kyereme, Fitzgerald, Nencka, Andrew, Iczkowski, Kenneth A., LaViolette, Peter S.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10019669/
https://www.ncbi.nlm.nih.gov/pubmed/36928230
http://dx.doi.org/10.1371/journal.pone.0278084
_version_ 1784908074139516928
author Duenweg, Savannah R.
Brehler, Michael
Bobholz, Samuel A.
Lowman, Allison K.
Winiarz, Aleksandra
Kyereme, Fitzgerald
Nencka, Andrew
Iczkowski, Kenneth A.
LaViolette, Peter S.
author_facet Duenweg, Savannah R.
Brehler, Michael
Bobholz, Samuel A.
Lowman, Allison K.
Winiarz, Aleksandra
Kyereme, Fitzgerald
Nencka, Andrew
Iczkowski, Kenneth A.
LaViolette, Peter S.
author_sort Duenweg, Savannah R.
collection PubMed
description One in eight men will be affected by prostate cancer (PCa) in their lives. While the current clinical standard prognostic marker for PCa is the Gleason score, it is subject to inter-reviewer variability. This study compares two machine learning methods for discriminating between cancerous regions on digitized histology from 47 PCa patients. Whole-slide images were annotated by a GU fellowship-trained pathologist for each Gleason pattern. High-resolution tiles were extracted from annotated and unlabeled tissue. Patients were separated into a training set of 31 patients (Cohort A, n = 9345 tiles) and a testing cohort of 16 patients (Cohort B, n = 4375 tiles). Tiles from Cohort A were used to train a ResNet model, and glands from these tiles were segmented to calculate pathomic features to train a bagged ensemble model to discriminate tumors as (1) cancer and noncancer, (2) high- and low-grade cancer from noncancer, and (3) all Gleason patterns. The outputs of these models were compared to ground-truth pathologist annotations. The ensemble and ResNet models had overall accuracies of 89% and 88%, respectively, at predicting cancer from noncancer. The ResNet model was additionally able to differentiate Gleason patterns on data from Cohort B while the ensemble model was not. Our results suggest that quantitative pathomic features calculated from PCa histology can distinguish regions of cancer; however, texture features captured by deep learning frameworks better differentiate unique Gleason patterns.
format Online
Article
Text
id pubmed-10019669
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-100196692023-03-17 Comparison of a machine and deep learning model for automated tumor annotation on digitized whole slide prostate cancer histology Duenweg, Savannah R. Brehler, Michael Bobholz, Samuel A. Lowman, Allison K. Winiarz, Aleksandra Kyereme, Fitzgerald Nencka, Andrew Iczkowski, Kenneth A. LaViolette, Peter S. PLoS One Research Article One in eight men will be affected by prostate cancer (PCa) in their lives. While the current clinical standard prognostic marker for PCa is the Gleason score, it is subject to inter-reviewer variability. This study compares two machine learning methods for discriminating between cancerous regions on digitized histology from 47 PCa patients. Whole-slide images were annotated by a GU fellowship-trained pathologist for each Gleason pattern. High-resolution tiles were extracted from annotated and unlabeled tissue. Patients were separated into a training set of 31 patients (Cohort A, n = 9345 tiles) and a testing cohort of 16 patients (Cohort B, n = 4375 tiles). Tiles from Cohort A were used to train a ResNet model, and glands from these tiles were segmented to calculate pathomic features to train a bagged ensemble model to discriminate tumors as (1) cancer and noncancer, (2) high- and low-grade cancer from noncancer, and (3) all Gleason patterns. The outputs of these models were compared to ground-truth pathologist annotations. The ensemble and ResNet models had overall accuracies of 89% and 88%, respectively, at predicting cancer from noncancer. The ResNet model was additionally able to differentiate Gleason patterns on data from Cohort B while the ensemble model was not. Our results suggest that quantitative pathomic features calculated from PCa histology can distinguish regions of cancer; however, texture features captured by deep learning frameworks better differentiate unique Gleason patterns. Public Library of Science 2023-03-16 /pmc/articles/PMC10019669/ /pubmed/36928230 http://dx.doi.org/10.1371/journal.pone.0278084 Text en © 2023 Duenweg et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://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
Duenweg, Savannah R.
Brehler, Michael
Bobholz, Samuel A.
Lowman, Allison K.
Winiarz, Aleksandra
Kyereme, Fitzgerald
Nencka, Andrew
Iczkowski, Kenneth A.
LaViolette, Peter S.
Comparison of a machine and deep learning model for automated tumor annotation on digitized whole slide prostate cancer histology
title Comparison of a machine and deep learning model for automated tumor annotation on digitized whole slide prostate cancer histology
title_full Comparison of a machine and deep learning model for automated tumor annotation on digitized whole slide prostate cancer histology
title_fullStr Comparison of a machine and deep learning model for automated tumor annotation on digitized whole slide prostate cancer histology
title_full_unstemmed Comparison of a machine and deep learning model for automated tumor annotation on digitized whole slide prostate cancer histology
title_short Comparison of a machine and deep learning model for automated tumor annotation on digitized whole slide prostate cancer histology
title_sort comparison of a machine and deep learning model for automated tumor annotation on digitized whole slide prostate cancer histology
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10019669/
https://www.ncbi.nlm.nih.gov/pubmed/36928230
http://dx.doi.org/10.1371/journal.pone.0278084
work_keys_str_mv AT duenwegsavannahr comparisonofamachineanddeeplearningmodelforautomatedtumorannotationondigitizedwholeslideprostatecancerhistology
AT brehlermichael comparisonofamachineanddeeplearningmodelforautomatedtumorannotationondigitizedwholeslideprostatecancerhistology
AT bobholzsamuela comparisonofamachineanddeeplearningmodelforautomatedtumorannotationondigitizedwholeslideprostatecancerhistology
AT lowmanallisonk comparisonofamachineanddeeplearningmodelforautomatedtumorannotationondigitizedwholeslideprostatecancerhistology
AT winiarzaleksandra comparisonofamachineanddeeplearningmodelforautomatedtumorannotationondigitizedwholeslideprostatecancerhistology
AT kyeremefitzgerald comparisonofamachineanddeeplearningmodelforautomatedtumorannotationondigitizedwholeslideprostatecancerhistology
AT nenckaandrew comparisonofamachineanddeeplearningmodelforautomatedtumorannotationondigitizedwholeslideprostatecancerhistology
AT iczkowskikennetha comparisonofamachineanddeeplearningmodelforautomatedtumorannotationondigitizedwholeslideprostatecancerhistology
AT laviolettepeters comparisonofamachineanddeeplearningmodelforautomatedtumorannotationondigitizedwholeslideprostatecancerhistology