Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022, China.
Department of Gastroenterology, The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, China.
J Gastroenterol Hepatol. 2023 Jun;38(6):883-887. doi: 10.1111/jgh.16073. Epub 2023 Jan 23.
During endoscopic ultrasound-guided fine needle aspiration (EUS-FNA), cytopathology with rapid on-site evaluation (ROSE) can improve diagnostic yield and accuracy. However, ROSE is unavailable in most Asian and European institutions because of the shortage of cytopathologists. Therefore, developing computer-assisted diagnostic tools to replace manual ROSE is crucial. Herein, we reported the validation of an artificial intelligence (AI)-based model (ROSE-AI model) to substitute manual ROSE during EUS-FNA.
A total of 467 digitized images from Diff-Quik (D&F)-stained EUS-FNA slides were divided into training (3642 tiles from 367 images) and internal validation (916 tiles from 100 images) datasets. The ROSE-AI model was trained and validated using training and internal validation datasets, respectively. The specificity was emphasized while developing the model. Then, we evaluated the AI model on a 693-image external dataset. We assessed the performance of the AI model to detect cancer cells (CCs) regarding the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).
The ROSE-AI model achieved an accuracy of 83.4% in the internal validation dataset and 88.7% in the external test dataset. The sensitivity and PPV were 79.1% and 71.7% in internal validation dataset and 78.0% and 60.7% in external test dataset, respectively.
We provided a proof of concept that AI can be used to replace manual ROSE during EUS-FNA. The ROSE-AI model can address the shortage of cytopathologists and make ROSE available in more institutes.
在超声内镜引导下细针抽吸（EUS-FNA）过程中，细胞学快速现场评估（ROSE）可以提高诊断的检出率和准确性。然而，由于细胞病理学家的短缺，ROSE 在大多数亚洲和欧洲机构中无法使用。因此，开发计算机辅助诊断工具来替代手动 ROSE 至关重要。在此，我们报告了一种基于人工智能（AI）的模型（ROSE-AI 模型）在 EUS-FNA 中替代手动 ROSE 的验证结果。
共对 467 张 Diff-Quik（D&F）染色的 EUS-FNA 切片的数字化图像进行了分析，将其分为训练集（来自 367 张图像的 3642 个图块）和内部验证集（来自 100 张图像的 916 个图块）。使用训练集和内部验证集分别对 ROSE-AI 模型进行训练和验证。在开发模型时强调了特异性。然后，我们在 693 张图像的外部数据集上评估了 AI 模型。我们评估了 AI 模型在检测癌细胞（CC）时的准确性、敏感性、特异性、阳性预测值（PPV）和阴性预测值（NPV）。
ROSE-AI 模型在内部验证数据集中的准确率为 83.4%，在外部测试数据集中的准确率为 88.7%。在内部验证数据集中，敏感性和 PPV 分别为 79.1%和 71.7%，在外部测试数据集中，敏感性和 PPV 分别为 78.0%和 60.7%。
我们提供了一个概念验证，证明人工智能可以用于替代 EUS-FNA 中的手动 ROSE。ROSE-AI 模型可以解决细胞病理学家短缺的问题，并使 ROSE 在更多的机构中得到应用。
