Cargando…

Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images

Deep learning technology has been used in the medical field to produce devices for clinical practice. Deep learning methods in cytology offer the potential to enhance cancer screening while also providing quantitative, objective, and highly reproducible testing. However, constructing high-accuracy d...

Descripción completa

Detalles Bibliográficos
Autores principales: Kurita, Yuki, Meguro, Shiori, Tsuyama, Naoko, Kosugi, Isao, Enomoto, Yasunori, Kawasaki, Hideya, Uemura, Takashi, Kimura, Michio, Iwashita, Toshihide
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10194854/
https://www.ncbi.nlm.nih.gov/pubmed/37200281
http://dx.doi.org/10.1371/journal.pone.0285996
_version_ 1785044102658654208
author Kurita, Yuki
Meguro, Shiori
Tsuyama, Naoko
Kosugi, Isao
Enomoto, Yasunori
Kawasaki, Hideya
Uemura, Takashi
Kimura, Michio
Iwashita, Toshihide
author_facet Kurita, Yuki
Meguro, Shiori
Tsuyama, Naoko
Kosugi, Isao
Enomoto, Yasunori
Kawasaki, Hideya
Uemura, Takashi
Kimura, Michio
Iwashita, Toshihide
author_sort Kurita, Yuki
collection PubMed
description Deep learning technology has been used in the medical field to produce devices for clinical practice. Deep learning methods in cytology offer the potential to enhance cancer screening while also providing quantitative, objective, and highly reproducible testing. However, constructing high-accuracy deep learning models necessitates a significant amount of manually labeled data, which takes time. To address this issue, we used the Noisy Student Training technique to create a binary classification deep learning model for cervical cytology screening, which reduces the quantity of labeled data necessary. We used 140 whole-slide images from liquid-based cytology specimens, 50 of which were low-grade squamous intraepithelial lesions, 50 were high-grade squamous intraepithelial lesions, and 40 were negative samples. We extracted 56,996 images from the slides and then used them to train and test the model. We trained the EfficientNet using 2,600 manually labeled images to generate additional pseudo labels for the unlabeled data and then self-trained it within a student-teacher framework. Based on the presence or absence of abnormal cells, the created model was used to classify the images as normal or abnormal. The Grad-CAM approach was used to visualize the image components that contributed to the classification. The model achieved an area under the curve of 0.908, accuracy of 0.873, and F1-score of 0.833 with our test data. We also explored the optimal confidence threshold score and optimal augmentation approaches for low-magnification images. Our model efficiently classified normal and abnormal images at low magnification with high reliability, making it a promising screening tool for cervical cytology.
format Online
Article
Text
id pubmed-10194854
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-101948542023-05-19 Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images Kurita, Yuki Meguro, Shiori Tsuyama, Naoko Kosugi, Isao Enomoto, Yasunori Kawasaki, Hideya Uemura, Takashi Kimura, Michio Iwashita, Toshihide PLoS One Research Article Deep learning technology has been used in the medical field to produce devices for clinical practice. Deep learning methods in cytology offer the potential to enhance cancer screening while also providing quantitative, objective, and highly reproducible testing. However, constructing high-accuracy deep learning models necessitates a significant amount of manually labeled data, which takes time. To address this issue, we used the Noisy Student Training technique to create a binary classification deep learning model for cervical cytology screening, which reduces the quantity of labeled data necessary. We used 140 whole-slide images from liquid-based cytology specimens, 50 of which were low-grade squamous intraepithelial lesions, 50 were high-grade squamous intraepithelial lesions, and 40 were negative samples. We extracted 56,996 images from the slides and then used them to train and test the model. We trained the EfficientNet using 2,600 manually labeled images to generate additional pseudo labels for the unlabeled data and then self-trained it within a student-teacher framework. Based on the presence or absence of abnormal cells, the created model was used to classify the images as normal or abnormal. The Grad-CAM approach was used to visualize the image components that contributed to the classification. The model achieved an area under the curve of 0.908, accuracy of 0.873, and F1-score of 0.833 with our test data. We also explored the optimal confidence threshold score and optimal augmentation approaches for low-magnification images. Our model efficiently classified normal and abnormal images at low magnification with high reliability, making it a promising screening tool for cervical cytology. Public Library of Science 2023-05-18 /pmc/articles/PMC10194854/ /pubmed/37200281 http://dx.doi.org/10.1371/journal.pone.0285996 Text en © 2023 Kurita 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
Kurita, Yuki
Meguro, Shiori
Tsuyama, Naoko
Kosugi, Isao
Enomoto, Yasunori
Kawasaki, Hideya
Uemura, Takashi
Kimura, Michio
Iwashita, Toshihide
Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images
title Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images
title_full Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images
title_fullStr Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images
title_full_unstemmed Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images
title_short Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images
title_sort accurate deep learning model using semi-supervised learning and noisy student for cervical cancer screening in low magnification images
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10194854/
https://www.ncbi.nlm.nih.gov/pubmed/37200281
http://dx.doi.org/10.1371/journal.pone.0285996
work_keys_str_mv AT kuritayuki accuratedeeplearningmodelusingsemisupervisedlearningandnoisystudentforcervicalcancerscreeninginlowmagnificationimages
AT meguroshiori accuratedeeplearningmodelusingsemisupervisedlearningandnoisystudentforcervicalcancerscreeninginlowmagnificationimages
AT tsuyamanaoko accuratedeeplearningmodelusingsemisupervisedlearningandnoisystudentforcervicalcancerscreeninginlowmagnificationimages
AT kosugiisao accuratedeeplearningmodelusingsemisupervisedlearningandnoisystudentforcervicalcancerscreeninginlowmagnificationimages
AT enomotoyasunori accuratedeeplearningmodelusingsemisupervisedlearningandnoisystudentforcervicalcancerscreeninginlowmagnificationimages
AT kawasakihideya accuratedeeplearningmodelusingsemisupervisedlearningandnoisystudentforcervicalcancerscreeninginlowmagnificationimages
AT uemuratakashi accuratedeeplearningmodelusingsemisupervisedlearningandnoisystudentforcervicalcancerscreeninginlowmagnificationimages
AT kimuramichio accuratedeeplearningmodelusingsemisupervisedlearningandnoisystudentforcervicalcancerscreeninginlowmagnificationimages
AT iwashitatoshihide accuratedeeplearningmodelusingsemisupervisedlearningandnoisystudentforcervicalcancerscreeninginlowmagnificationimages