Department of Surgery, Division of Otolaryngology Head and Neck Surgery, University of New Mexico Health Sciences Center, Albuquerque, NM, USA.
Department of Pathology, University of New Mexico Health Sciences Center, Albuquerque, NM, USA.
Ann Otol Rhinol Laryngol. 2023 Nov;132(11):1373-1379. doi: 10.1177/00034894231158464. Epub 2023 Mar 10.
The presence of nodal metastases in patients with papillary thyroid carcinoma (PTC) has both staging and treatment implications. However, lymph nodes are often not removed during thyroidectomy. Prior work has demonstrated the capability of artificial intelligence (AI) to predict the presence of nodal metastases in PTC based on the primary tumor histopathology alone. This study aimed to replicate these results with multi-institutional data.
Cases of conventional PTC were identified from the records of 2 large academic institutions. Only patients with complete pathology data, including at least 3 sampled lymph nodes, were included in the study. Tumors were designated "positive" if they had at least 5 positive lymph node metastases. First, algorithms were trained separately on each institution's data and tested independently on the other institution's data. Then, the data sets were combined and new algorithms were developed and tested. The primary tumors were randomized into 2 groups, one to train the algorithm and another to test it. A low level of supervision was used to train the algorithm. Board-certified pathologists annotated the slides. HALO-AI convolutional neural network and image software was used to perform training and testing. Receiver operator characteristic curves and the Youden J statistic were used for primary analysis.
There were 420 cases used in analyses, 45% of which were negative. The best performing single institution algorithm had an area under the curve (AUC) of 0.64 with a sensitivity and specificity of 65% and 61% respectively, when tested on the other institution's data. The best performing combined institution algorithm had an AUC of 0.84 with a sensitivity and specificity of 68% and 91% respectively.
A convolutional neural network can produce an accurate and robust algorithm that is capable of predicting nodal metastases from primary PTC histopathology alone even in the setting of multi-institutional data.
甲状腺乳头状癌（PTC）患者的淋巴结转移情况具有分期和治疗意义。然而，甲状腺切除术通常不切除淋巴结。先前的工作已经证明，人工智能（AI）能够仅根据原发肿瘤组织病理学预测 PTC 中淋巴结转移的存在。本研究旨在使用多机构数据复制这些结果。
从 2 家大型学术机构的记录中确定了常规 PTC 病例。只有具有完整病理数据（包括至少 3 个取样淋巴结）的患者才包括在研究中。如果肿瘤至少有 5 个阳性淋巴结转移，则将其指定为“阳性”。首先，在每个机构的数据上分别训练算法，并在另一个机构的数据上独立测试。然后，合并数据集并开发和测试新算法。将原发肿瘤随机分为 2 组，一组用于训练算法，另一组用于测试算法。使用低水平的监督来训练算法。认证病理学家对幻灯片进行注释。HALO-AI 卷积神经网络和图像软件用于进行训练和测试。使用接收器操作特征曲线和 Youden J 统计量进行主要分析。
有 420 例病例用于分析，其中 45%为阴性。在对另一机构的数据进行测试时，表现最佳的单一机构算法的曲线下面积（AUC）为 0.64，灵敏度和特异性分别为 65%和 61%。表现最佳的联合机构算法的 AUC 为 0.84，灵敏度和特异性分别为 68%和 91%。
卷积神经网络可以生成一种准确且稳健的算法，即使在多机构数据的情况下，该算法也能够仅根据原发 PTC 组织病理学预测淋巴结转移。
