Cargando…

Deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis

Cervical cancer (CC) is the fourth most common malignant tumor among women worldwide. Constructing a high-accuracy deep convolutional neural network (DCNN) for cervical cancer screening and diagnosis is important for the successful prevention of cervical cancer. In this work, we proposed a robust DC...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Xueguang, Du, Mingyue, Zuo, Shanru, Zhou, Mingqing, Peng, Qiyao, Chen, Ziyao, Zhou, Junhua, He, Quanyuan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10034408/
https://www.ncbi.nlm.nih.gov/pubmed/36969799
http://dx.doi.org/10.3389/fbinf.2023.1101667
_version_ 1784911213641072640
author Li, Xueguang
Du, Mingyue
Zuo, Shanru
Zhou, Mingqing
Peng, Qiyao
Chen, Ziyao
Zhou, Junhua
He, Quanyuan
author_facet Li, Xueguang
Du, Mingyue
Zuo, Shanru
Zhou, Mingqing
Peng, Qiyao
Chen, Ziyao
Zhou, Junhua
He, Quanyuan
author_sort Li, Xueguang
collection PubMed
description Cervical cancer (CC) is the fourth most common malignant tumor among women worldwide. Constructing a high-accuracy deep convolutional neural network (DCNN) for cervical cancer screening and diagnosis is important for the successful prevention of cervical cancer. In this work, we proposed a robust DCNN for cervical cancer screening using whole-slide images (WSI) of ThinPrep cytologic test (TCT) slides from 211 cervical cancer and 189 normal patients. We used an active learning strategy to improve the efficiency and accuracy of image labeling. The sensitivity, specificity, and accuracy of the best model were 96.21%, 98.95%, and 97.5% for CC patient identification respectively. Our results also demonstrated that the active learning strategy was superior to the traditional supervised learning strategy in cost reduction and improvement of image labeling quality. The related data and source code are freely available at https://github.com/hqyone/cancer_rcnn.
format Online
Article
Text
id pubmed-10034408
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-100344082023-03-24 Deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis Li, Xueguang Du, Mingyue Zuo, Shanru Zhou, Mingqing Peng, Qiyao Chen, Ziyao Zhou, Junhua He, Quanyuan Front Bioinform Bioinformatics Cervical cancer (CC) is the fourth most common malignant tumor among women worldwide. Constructing a high-accuracy deep convolutional neural network (DCNN) for cervical cancer screening and diagnosis is important for the successful prevention of cervical cancer. In this work, we proposed a robust DCNN for cervical cancer screening using whole-slide images (WSI) of ThinPrep cytologic test (TCT) slides from 211 cervical cancer and 189 normal patients. We used an active learning strategy to improve the efficiency and accuracy of image labeling. The sensitivity, specificity, and accuracy of the best model were 96.21%, 98.95%, and 97.5% for CC patient identification respectively. Our results also demonstrated that the active learning strategy was superior to the traditional supervised learning strategy in cost reduction and improvement of image labeling quality. The related data and source code are freely available at https://github.com/hqyone/cancer_rcnn. Frontiers Media S.A. 2023-03-09 /pmc/articles/PMC10034408/ /pubmed/36969799 http://dx.doi.org/10.3389/fbinf.2023.1101667 Text en Copyright © 2023 Li, Du, Zuo, Zhou, Peng, Chen, Zhou and He. https://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 Bioinformatics
Li, Xueguang
Du, Mingyue
Zuo, Shanru
Zhou, Mingqing
Peng, Qiyao
Chen, Ziyao
Zhou, Junhua
He, Quanyuan
Deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis
title Deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis
title_full Deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis
title_fullStr Deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis
title_full_unstemmed Deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis
title_short Deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis
title_sort deep convolutional neural networks using an active learning strategy for cervical cancer screening and diagnosis
topic Bioinformatics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10034408/
https://www.ncbi.nlm.nih.gov/pubmed/36969799
http://dx.doi.org/10.3389/fbinf.2023.1101667
work_keys_str_mv AT lixueguang deepconvolutionalneuralnetworksusinganactivelearningstrategyforcervicalcancerscreeninganddiagnosis
AT dumingyue deepconvolutionalneuralnetworksusinganactivelearningstrategyforcervicalcancerscreeninganddiagnosis
AT zuoshanru deepconvolutionalneuralnetworksusinganactivelearningstrategyforcervicalcancerscreeninganddiagnosis
AT zhoumingqing deepconvolutionalneuralnetworksusinganactivelearningstrategyforcervicalcancerscreeninganddiagnosis
AT pengqiyao deepconvolutionalneuralnetworksusinganactivelearningstrategyforcervicalcancerscreeninganddiagnosis
AT chenziyao deepconvolutionalneuralnetworksusinganactivelearningstrategyforcervicalcancerscreeninganddiagnosis
AT zhoujunhua deepconvolutionalneuralnetworksusinganactivelearningstrategyforcervicalcancerscreeninganddiagnosis
AT hequanyuan deepconvolutionalneuralnetworksusinganactivelearningstrategyforcervicalcancerscreeninganddiagnosis