Relationship between a deep learning model and liquid‐based cytological processing techniques
Relationship between a deep learning model and liquid‐based cytological processing techniques
复制标题
深度学习模型与液基细胞学处理技术之间的关系
DOI：
10.1111/cyt.13235
复制
发表时间：
2023
期刊：
影响因子：
1.3
通讯作者：
Nagata Kohzo
中科院分区：
文献类型：
--
作者：
Ikeda Katsuhide;Sakabe Nanako;Maruyama Sayumi;Ito Chihiro;Shimoyama Yuka;Oboshi Wataru;Komene Tetsuya;Yamaguchi Yoshitaka;Sato Shouichi;Nagata Kohzo
使用深度学习进行的基于人工智能（AI）的细胞病理学研究使细胞检测和分类成为可能。液基细胞学（LBC）促进了标本制备的标准化;然而，细胞形态学根据所使用的LBC处理技术而变化。在这项研究中，我们阐明了两个LBC技术和细胞检测和分类之间的关系，使用深度学习model.MethodsCytological标本制备使用ThinPrep和SurePath方法。细胞检测和细胞分类的准确性进行了检查，使用一个和五个细胞模型，分别与一个和五个细胞类型进行训练，results.ResultsWhen相同的LBC处理技术用于训练和检测准备，细胞检测和分类率很高。在ThinPrep准备上训练的模型比在SurePath上训练的模型更准确。当用于训练和检测的制剂类型不同时，细胞检测和分类的准确性显著降低（P< 0.01）。在ThinPrep和SurePath制剂上训练的模型显示出细胞检测和分类率略有降低，但非常准确。ConclusionsFor the two LBC processing techniques，cytomorphology根据细胞类型而变化;这种差异影响了深度学习的细胞检测和分类的准确性。因此，为了使用AI进行高精度的细胞检测和分类，必须对训练和检测使用相同的处理技术。我们的评估还表明，应该使用通过各种处理技术制备的样本来构建深度学习模型，以构建全球适用的AI模型。
ObjectiveArtificial intelligence (AI)–based cytopathology studies conducted using deep learning have enabled cell detection and classification. Liquid‐based cytology (LBC) has facilitated the standardisation of specimen preparation; however, cytomorphology varies according to the LBC processing technique used. In this study, we elucidated the relationship between two LBC techniques and cell detection and classification using a deep learning model.MethodsCytological specimens were prepared using the ThinPrep and SurePath methods. The accuracy of cell detection and cell classification was examined using the one‐ and five‐cell models, which were trained with one and five cell types, respectively.ResultsWhen the same LBC processing techniques were used for the training and detection preparations, the cell detection and classification rates were high. The model trained on ThinPrep preparations was more accurate than that trained on SurePath. When the preparation types used for training and detection were different, the accuracy of cell detection and classification was significantly reduced (P< 0.01). The model trained on both ThinPrep and SurePath preparations exhibited slightly reduced cell detection and classification rates but was highly accurate.ConclusionsFor the two LBC processing techniques, cytomorphology varied according to cell type; this difference affects the accuracy of cell detection and classification by deep learning. Therefore, for highly accurate cell detection and classification using AI, the same processing technique must be used for both training and detection. Our assessment also suggests that a deep learning model should be constructed using specimens prepared via a variety of processing techniques to construct a globally applicable AI model.
登录
查看更多内容
使用液基细胞学表征处理技术和溶液类型对细胞形态学的影响
影响因子：
1.8
作者：
Ikeda Katsuhide;Oboshi Wataru;Hashimoto Yusuke;Komene Tetsuya;Yamaguchi Yoshitaka;Sato Shouichi;Maruyama Sayumi;Furukawa Nozomi;Sakabe Nanako;Nagata Kohzo
通讯作者：
Nagata Kohzo
液基细胞学保存液与人工智能的关系：利用YOLOv5深度卷积神经网络进行液基细胞学标本细胞检测
影响因子：
1.8
作者：
Ikeda Katsuhide;Sakabe Nanako;Maruyama Sayumi;Ito Chihiro;Shimoyama Yuka;Sato Shouichi;Nagata Kohzo
通讯作者：
Nagata Kohzo
影响因子：
1.3
作者：
Michael, CW;McConnel, J;Al-Khafaji, B
通讯作者：
Al-Khafaji, B
影响因子：
1.3
作者：
Belsley, Nicole A.;Tambouret, Rosemary H.;Wilbur, David C.
通讯作者：
Wilbur, David C.
甲状旁腺病变细针抽吸液基细胞学检查：与传统涂片、ThinPrep 和 SurePath 的比较研究。
影响因子：
1.4
作者：
G. Park;Sung Hak Lee;S. Jung;C. Jung
通讯作者：
C. Jung