Department of Diagnostic Pathology and Cytology, Kuma Hospital, Kobe, Japan.
Institute for Datability Science, Osaka University, Suita, Japan.
Cancer Cytopathol. 2023 Apr;131(4):217-225. doi: 10.1002/cncy.22669. Epub 2022 Dec 16.
Several studies have used artificial intelligence (AI) to analyze cytology images, but AI has yet to be adopted in clinical practice. The objective of this study was to demonstrate the accuracy of AI-based image analysis for thyroid fine-needle aspiration cytology (FNAC) and to propose its application in clinical practice.
In total, 148,395 microscopic images of FNAC were obtained from 393 thyroid nodules to train and validate the data, and EfficientNetV2-L was used as the image-classification model. The 35 nodules that were classified as atypia of undetermined significance (AUS) were predicted using AI training.
The precision-recall area under the curve (PR AUC) was >0.95, except for poorly differentiated thyroid carcinoma (PR AUC = 0.49) and medullary thyroid carcinoma (PR AUC = 0.91). Poorly differentiated thyroid carcinoma had the lowest recall (35.4%) and was difficult to distinguish from papillary thyroid carcinoma, medullary thyroid carcinoma, and follicular thyroid carcinoma. Follicular adenomas and follicular thyroid carcinomas were distinguished from each other by 86.7% and 93.9% recall, respectively. For two-dimensional mapping of the data using t-distributed stochastic neighbor embedding, the lymphomas, follicular adenomas, and anaplastic thyroid carcinomas were divided into three, two, and two groups, respectively. Analysis of the AUS nodules showed 94.7% sensitivity, 14.4% specificity, 56.3% positive predictive value, and 66.7% negative predictive value.
The authors developed an AI-based approach to analyze thyroid FNAC cases encountered in routine practice. This analysis could be useful for the clinical management of AUS and follicular neoplasm nodules (e.g., an online AI platform for thyroid cytology consultations).
已有多项研究使用人工智能（AI）分析细胞学图像，但 AI 尚未在临床实践中得到应用。本研究旨在证明基于 AI 的甲状腺细针抽吸细胞学（FNAC）图像分析的准确性，并提出其在临床实践中的应用。
共纳入 393 个甲状腺结节的 148395 个 FNAC 显微镜图像用于训练和验证数据，使用 EfficientNetV2-L 作为图像分类模型。使用 AI 训练预测 35 个被归类为意义未明的不典型病变（AUS）的结节。
除低分化甲状腺癌（PR AUC=0.49）和髓样甲状腺癌（PR AUC=0.91）外，精度-召回率曲线下面积（PR AUC）均>0.95。低分化甲状腺癌的召回率最低（35.4%），难以与甲状腺乳头状癌、髓样甲状腺癌和滤泡状甲状腺癌相区分。滤泡性腺瘤和滤泡状甲状腺癌的召回率分别为 86.7%和 93.9%。使用 t 分布随机邻域嵌入对数据进行二维映射，将淋巴瘤、滤泡性腺瘤和间变性甲状腺癌分别分为三组、两组和两组。对 AUS 结节的分析显示，敏感性为 94.7%，特异性为 14.4%，阳性预测值为 56.3%，阴性预测值为 66.7%。
作者开发了一种基于 AI 的方法来分析常规实践中遇到的甲状腺 FNAC 病例。该分析可用于 AUS 和滤泡性肿瘤结节的临床管理（例如，甲状腺细胞学咨询的在线 AI 平台）。
