School of Clinical Medicine, Weifang Medical University, Weifang, Shandong, 261042, People's Republic of China.
Department of Otorhinolaryngology, Head and Neck Surgery, Yantai Yuhuangding Hospital, Qingdao University, Yantai, Shandong, 264000, People's Republic of China.
Eur Radiol. 2023 Oct;33(10):6828-6840. doi: 10.1007/s00330-023-09700-2. Epub 2023 May 13.
To develop an artificial intelligence (AI) system for predicting cervical lymph node metastasis (CLNM) preoperatively in patients with papillary thyroid cancer (PTC) based on CT images.
This multicenter retrospective study included the preoperative CT of PTC patients who were divided into the development, internal, and external test sets. The region of interest of the primary tumor was outlined manually on the CT images by a radiologist who has eight years of experience. With the use of the CT images and lesions masks, the deep learning (DL) signature was developed by the DenseNet combined with convolutional block attention module. One-way analysis of variance and least absolute shrinkage and selection operator were used to select features, and a support vector machine was used to construct the radiomics signature. Random forest was used to combine the DL, radiomics, and clinical signature to perform the final prediction. The receiver operating characteristic curve, sensitivity, specificity, and accuracy were used by two radiologists (R1 and R2) to evaluate and compare the AI system.
For the internal and external test set, the AI system achieved excellent performance with AUCs of 0.84 and 0.81, higher than the DL (p = .03, .82), radiomics (p < .001, .04), and clinical model (p < .001, .006). With the aid of the AI system, the specificities of radiologists were improved by 9% and 15% for R1 and 13% and 9% for R2, respectively.
The AI system can help predict CLNM in patients with PTC, and the radiologists' performance improved with AI assistance.
This study developed an AI system for preoperative prediction of CLNM in PTC patients based on CT images, and the radiologists' performance improved with AI assistance, which could improve the effectiveness of individual clinical decision-making.
• This multicenter retrospective study showed that the preoperative CT image-based AI system has the potential for predicting the CLNM of PTC. • The AI system was superior to the radiomics and clinical model in predicting the CLNM of PTC. • The radiologists' diagnostic performance improved when they received the AI system assistance.
基于 CT 图像，开发一种人工智能（AI）系统，用于预测甲状腺乳头状癌（PTC）患者术前的颈部淋巴结转移（CLNM）。
这项多中心回顾性研究纳入了 PTC 患者的术前 CT，这些患者被分为开发、内部和外部测试集。由一名具有八年经验的放射科医生手动在 CT 图像上勾画原发肿瘤的感兴趣区域。使用 CT 图像和病变掩模，通过 DenseNet 结合卷积块注意力模块开发深度学习（DL）特征。采用单因素方差分析和最小绝对收缩和选择算子（LASSO）选择特征，采用支持向量机构建放射组学特征。随机森林用于结合 DL、放射组学和临床特征进行最终预测。两名放射科医生（R1 和 R2）使用接收者操作特征曲线、敏感度、特异度和准确率来评估和比较 AI 系统。
对于内部和外部测试集，AI 系统的 AUC 分别为 0.84 和 0.81，表现出色，优于 DL（p=0.03，0.82）、放射组学（p<0.001，0.04）和临床模型（p<0.001，0.006）。借助 AI 系统，R1 的特异性提高了 9%和 15%，R2 的特异性提高了 13%和 9%。
AI 系统可帮助预测 PTC 患者的 CLNM，并且 AI 辅助可提高放射科医生的性能。
本研究基于 CT 图像开发了一种用于预测 PTC 患者 CLNM 的 AI 系统，并且 AI 辅助提高了放射科医生的性能，这可能会提高个体临床决策的有效性。
这项多中心回顾性研究表明，基于术前 CT 图像的 AI 系统具有预测 PTC 患者 CLNM 的潜力。
AI 系统在预测 PTC 患者的 CLNM 方面优于放射组学和临床模型。
当放射科医生获得 AI 系统的辅助时，他们的诊断性能得到提高。
