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}
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.
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.