Maruyama Sayumi, Sakabe Nanako, Ito Chihiro, Shimoyama Yuka, Sato Shouichi, Ikeda Katsuhide
Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan.
Clinical Engineering, Faculty of Medical Sciences, Juntendo University, Urayasu, Japan.
Am J Clin Pathol. 2023 May 2;159(5):448-454. doi: 10.1093/ajcp/aqac178.
Cytomorphology is known to differ depending on the processing technique, and these differences pose a problem for automated diagnosis using deep learning. We examined the as-yet unclarified relationship between cell detection or classification using artificial intelligence (AI) and the AutoSmear (Sakura Finetek Japan) and liquid-based cytology (LBC) processing techniques.
The "You Only Look Once" (YOLO), version 5x, algorithm was trained on the AutoSmear and LBC preparations of 4 cell lines: lung cancer (LC), cervical cancer (CC), malignant pleural mesothelioma (MM), and esophageal cancer (EC). Detection and classification rates were used to evaluate the accuracy of cell detection.
When preparations of the same processing technique were used for training and detection in the 1-cell (1C) model, the AutoSmear model had a higher detection rate than the LBC model. When different processing techniques were used for training and detection, detection rates of LC and CC were significantly lower in the 4-cell (4C) model than in the 1C model, and those of MM and EC were approximately 10% lower in the 4C model.
In AI-based cell detection and classification, attention should be paid to cells whose morphologies change significantly depending on the processing technique, further suggesting the creation of a training model.
已知细胞形态学因处理技术而异，这些差异给使用深度学习的自动诊断带来了问题。我们研究了使用人工智能（AI）进行细胞检测或分类与自动涂片法（樱花精技株式会社）和液基细胞学（LBC）处理技术之间尚未阐明的关系。
使用“你只看一次”（YOLO）v5x算法对4种细胞系（肺癌（LC）、宫颈癌（CC）、恶性胸膜间皮瘤（MM）和食管癌（EC））的自动涂片和LBC标本进行训练。检测率和分类率用于评估细胞检测的准确性。
在单细胞（1C）模型中，当使用相同处理技术的标本进行训练和检测时，自动涂片模型的检测率高于LBC模型。当使用不同处理技术进行训练和检测时，在四细胞（4C）模型中，LC和CC的检测率显著低于1C模型，MM和EC的检测率在4C模型中约低10%。
在基于AI的细胞检测和分类中，应关注形态因处理技术而显著变化的细胞，这进一步表明需要创建一个训练模型。
