利用液基细胞学图像区分非小细胞肺癌恶性程度和组织学类型的人工智能识别模型

IF 3.5 4区 医学 Q3 CELL BIOLOGY
Pathobiology Pub Date : 2024-08-28 DOI:10.1159/000541148
Ryota Tanaka, Yukihiro Tsuboshita, Mitsuaki Okodo, Rei Settsu, Kohei Hashimoto, Keisei Tachibana, Kazumasa Tanabe, Koji Kishimoto, Masachika Fujiwara, Junji Shibahara
{"title":"利用液基细胞学图像区分非小细胞肺癌恶性程度和组织学类型的人工智能识别模型","authors":"Ryota Tanaka, Yukihiro Tsuboshita, Mitsuaki Okodo, Rei Settsu, Kohei Hashimoto, Keisei Tachibana, Kazumasa Tanabe, Koji Kishimoto, Masachika Fujiwara, Junji Shibahara","doi":"10.1159/000541148","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Artificial intelligence image recognition has applications in clinical practice. The purpose of this study was to develop an automated image classification model for lung cancer cytology using a deep learning convolutional neural network (DCNN).</p><p><strong>Methods: </strong>Liquid-based cytology samples from 8 normal parenchymal (N), 22 adenocarcinoma (ADC), and 15 squamous cell carcinoma (SQCC) surgical specimens were prepared, and 45 Papanicolaou-stained slides were scanned using whole-slide imaging. The final dataset of 9,141 patches consisted of 2,737 N, 4,756 ADC, and 1,648 SQCC samples. Densenet-121 was used as the DCNN to classify N versus malignant (ADC+SQCC) and ADC versus SQCC images. AdamW optimizer and 5-fold cross-validation were used in the training.</p><p><strong>Results: </strong>For malignancy prediction, the sensitivity, specificity, and accuracy were 0.97, 0.85, and 0.94, respectively, in the patch-level classification, and 0.92, 0.88, and 0.91, respectively, in the case-level classification. For SQCC prediction, the sensitivity, specificity, and accuracy were 0.86, 0.91, and 0.90, respectively, in the patch-level classification and 0.73, 0.82, and 0.78, respectively, in the case-level classification.</p><p><strong>Conclusion: </strong>The DCNN model performed excellently in predicting malignancy and histological types of lung cancer. This model may be useful for predicting cytopathological diagnosis in clinical situations by reinforcing training.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":null,"pages":null},"PeriodicalIF":3.5000,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Artificial Intelligence Recognition Model Using Liquid-Based Cytology Images to Discriminate Malignancy and Histological Types of Non-Small-Cell Lung Cancer.\",\"authors\":\"Ryota Tanaka, Yukihiro Tsuboshita, Mitsuaki Okodo, Rei Settsu, Kohei Hashimoto, Keisei Tachibana, Kazumasa Tanabe, Koji Kishimoto, Masachika Fujiwara, Junji Shibahara\",\"doi\":\"10.1159/000541148\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>Artificial intelligence image recognition has applications in clinical practice. The purpose of this study was to develop an automated image classification model for lung cancer cytology using a deep learning convolutional neural network (DCNN).</p><p><strong>Methods: </strong>Liquid-based cytology samples from 8 normal parenchymal (N), 22 adenocarcinoma (ADC), and 15 squamous cell carcinoma (SQCC) surgical specimens were prepared, and 45 Papanicolaou-stained slides were scanned using whole-slide imaging. The final dataset of 9,141 patches consisted of 2,737 N, 4,756 ADC, and 1,648 SQCC samples. Densenet-121 was used as the DCNN to classify N versus malignant (ADC+SQCC) and ADC versus SQCC images. AdamW optimizer and 5-fold cross-validation were used in the training.</p><p><strong>Results: </strong>For malignancy prediction, the sensitivity, specificity, and accuracy were 0.97, 0.85, and 0.94, respectively, in the patch-level classification, and 0.92, 0.88, and 0.91, respectively, in the case-level classification. For SQCC prediction, the sensitivity, specificity, and accuracy were 0.86, 0.91, and 0.90, respectively, in the patch-level classification and 0.73, 0.82, and 0.78, respectively, in the case-level classification.</p><p><strong>Conclusion: </strong>The DCNN model performed excellently in predicting malignancy and histological types of lung cancer. This model may be useful for predicting cytopathological diagnosis in clinical situations by reinforcing training.</p>\",\"PeriodicalId\":19805,\"journal\":{\"name\":\"Pathobiology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2024-08-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Pathobiology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1159/000541148\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CELL BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pathobiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1159/000541148","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CELL BIOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

引言人工智能图像识别可应用于临床实践。本研究的目的是利用深度学习卷积神经网络(DCNN)开发肺癌细胞学自动图像分类模型:方法:准备了来自 8 例正常实质细胞(N)、22 例腺癌(ADC)和 15 例鳞状细胞癌(SQCC)手术标本的液基细胞学样本,并使用全玻片成像技术扫描了 45 张巴氏染色玻片。最终的 9141 个数据集包括 2737 个 N、4756 个 ADC 和 1648 个 SQCC 样本。Densenet-121 被用作 DCNN 对 N 和恶性(ADC+SQCC)以及 ADC 和 SQCC 图像进行分类。训练中使用了 AdamW 优化器和 5 倍交叉验证:在恶性预测方面,斑块级分类的灵敏度、特异度和准确度分别为 0.97、0.85 和 0.94,病例级分类的灵敏度、特异度和准确度分别为 0.92、0.88 和 0.91。在 SQCC 预测中,斑块级分类的灵敏度、特异度和准确度分别为 0.86、0.91 和 0.90,病例级分类的灵敏度、特异度和准确度分别为 0.73、0.82 和 0.78:结论:DCNN 模型在预测肺癌的恶性程度和组织学类型方面表现出色。结论:DCNN 模型在预测肺癌的恶性程度和组织类型方面表现出色,通过强化训练,该模型可用于预测临床情况下的细胞病理学诊断。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Artificial Intelligence Recognition Model Using Liquid-Based Cytology Images to Discriminate Malignancy and Histological Types of Non-Small-Cell Lung Cancer.

Introduction: Artificial intelligence image recognition has applications in clinical practice. The purpose of this study was to develop an automated image classification model for lung cancer cytology using a deep learning convolutional neural network (DCNN).

Methods: Liquid-based cytology samples from 8 normal parenchymal (N), 22 adenocarcinoma (ADC), and 15 squamous cell carcinoma (SQCC) surgical specimens were prepared, and 45 Papanicolaou-stained slides were scanned using whole-slide imaging. The final dataset of 9,141 patches consisted of 2,737 N, 4,756 ADC, and 1,648 SQCC samples. Densenet-121 was used as the DCNN to classify N versus malignant (ADC+SQCC) and ADC versus SQCC images. AdamW optimizer and 5-fold cross-validation were used in the training.

Results: For malignancy prediction, the sensitivity, specificity, and accuracy were 0.97, 0.85, and 0.94, respectively, in the patch-level classification, and 0.92, 0.88, and 0.91, respectively, in the case-level classification. For SQCC prediction, the sensitivity, specificity, and accuracy were 0.86, 0.91, and 0.90, respectively, in the patch-level classification and 0.73, 0.82, and 0.78, respectively, in the case-level classification.

Conclusion: The DCNN model performed excellently in predicting malignancy and histological types of lung cancer. This model may be useful for predicting cytopathological diagnosis in clinical situations by reinforcing training.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Pathobiology
Pathobiology 医学-病理学
CiteScore
8.50
自引率
0.00%
发文量
47
审稿时长
>12 weeks
期刊介绍: ''Pathobiology'' offers a valuable platform for the publication of high-quality original research into the mechanisms underlying human disease. Aiming to serve as a bridge between basic biomedical research and clinical medicine, the journal welcomes articles from scientific areas such as pathology, oncology, anatomy, virology, internal medicine, surgery, cell and molecular biology, and immunology. Published bimonthly, ''Pathobiology'' features original research papers and reviews on translational research. The journal offers the possibility to publish proceedings of meetings dedicated to one particular topic.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信