Relationship between Liquid-Based Cytology Preservative Solutions and Artificial Intelligence: Liquid-Based Cytology Specimen Cell Detection Using YOLOv5 Deep Convolutional Neural Network
Relationship between Liquid-Based Cytology Preservative Solutions and Artificial Intelligence: Liquid-Based Cytology Specimen Cell Detection Using YOLOv5 Deep Convolutional Neural Network
复制标题
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
DOI：
10.1159/000526098
复制
发表时间：
2022
期刊：
影响因子：
1.8
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;Sato Shouichi;Nagata Kohzo
深度学习是机器学习的一个子集，它为特征提取和图像分类带来了重大变化，并在细胞病理学领域得到了积极的研究和发展。液基细胞学（LBC）可以实现标准化的细胞学制备，也可应用于人工智能（AI）研究，但细胞学特征因LBC防腐液类型而异。在这项研究中，细胞检测AI和类型的保存液used.MethodsThe标本制备从五个保存液LBC和染色使用巴氏法之间的关系。使用YOLOv5深度卷积神经网络算法为每个标本创建深度学习模型，并创建了来自五个标本的BRCPT模型。每个模型进行了比较，用于detection.ResultsAmong的6个模型，约25%的检测率的差异被观察到取决于检测的标本，和标本内，约20%的检测率的差异被观察到取决于模型。BRCPT模型的检测率的变化很小，取决于类型的检测speciments.ConclusionsThe相同的细胞用不同的保存液处理，细胞学特征是不同的，AI澄清的差异，细胞学特征取决于类型的解决方案。用于训练和检测的保存溶液的类型对使用AI的细胞检测具有极端影响。虽然深度学习模型的准确性很重要，但有必要了解细胞形态因保存液的类型而异，这是影响AI检测率的一个因素。
IntroductionDeep learning is a subset of machine learning that has contributed to significant changes in feature extraction and image classification and is being actively researched and developed in the field of cytopathology. Liquid-based cytology (LBC) enables standardized cytological preparation and is also applied to artificial intelligence (AI) research, but cytological features differ depending on the LBC preservative solution types. In this study, the relationship between cell detection by AI and the type of preservative solution used was examined.MethodsThe specimens were prepared from five preservative solutions of LBC and stained using the Papanicolaou method. The YOLOv5 deep convolutional neural network algorithm was used to create a deep learning model for each specimen, and a BRCPT model from five specimens was also created. Each model was compared to the specimen types used for detection.ResultsAmong the six models, a difference in the detection rate of approximately 25% was observed depending on the detected specimen, and within specimens, a difference in the detection rate of approximately 20% was observed depending on the model. The BRCPT model had little variation in the detection rate depending on the type of the detected specimen.ConclusionsThe same cells were treated with different preservative solutions, the cytologic features were different, and AI clarified the difference in cytologic features depending on the type of solution. The type of preservative solution used for training and detection had an extreme influence on cell detection using AI. Although the accuracy of the deep learning model is important, it is necessary to understand that cell morphology differs depending on the type of preservative solution, which is a factor affecting the detection rate of AI.
登录
查看更多内容
改进的归约-最近邻分类
DOI：
--
发表时间：
2012
期刊：
Proc. IEEE/ACIS Int. Conf. on Comp. And Information Science Comp. Soc
影响因子：
--
作者：
Naohiro Ishii;Ippei Torii;Yonngguang Bao;Hidekazu Tanaka
通讯作者：
Hidekazu Tanaka
影响因子：
6.3
作者：
Jubayer F;Soeb JA;Mojumder AN;Paul MK;Barua P;Kayshar S;Akter SS;Rahman M;Islam A
通讯作者：
Islam A
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
影响因子：
1.3
作者：
Okuda, Chihiro;Kyotake, Aiko;Ohsaki, Hiroyuki
通讯作者：
Ohsaki, Hiroyuki
影响因子：
1.3
作者：
Michael, CW;McConnel, J;Al-Khafaji, B
通讯作者：
Al-Khafaji, B