Yao Siqiong, Shen Pengcheng, Dai Fang, Deng Luojia, Qiu Xiangjun, Zhao Yanna, Gao Ming, Zhang Huan, Zheng Xiangqian, Yu Xiaoqiang, Bao Hongjing, Wang Maofeng, Wang Yun, Yi Dandan, Wang Xiaolei, Zhang Yuening, Sang Jianfeng, Fei Jian, Zhang Weituo, Qian Biyun, Lu Hui
State Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic and Developmental Sciences, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China.
SJTU-Yale Joint Center of Biostatistics and Data Science, National Center for Translational Medicine, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai 200240, China.
Research (Wash D C). 2024 Aug 20;7:0432. doi: 10.34133/research.0432. eCollection 2024.
Due to the absence of definitive diagnostic criteria, there remains a lack of consensus regarding the risk assessment of central lymph node metastasis (CLNM) and the necessity for prophylactic lymph node surgery in ultrasound-diagnosed thyroid cancer. The localization of thyroid nodules is a recognized predictor of CLNM; however, quantifying this relationship is challenging due to variable measurements. In this study, we developed a differential isomorphism-based alignment method combined with a graph transformer to accurately extract localization and morphological information of thyroid nodules, thereby predicting CLNM. We collected 88,796 ultrasound images from 48,969 patients who underwent central lymph node (CLN) surgery and utilized these images to train our predictive model, ACE-Net. Furthermore, we employed an interpretable methodology to explore the factors influencing CLNM and generated a risk heatmap to visually represent the distribution of CLNM risk across different thyroid regions. ACE-Net demonstrated superior performance in 6 external multicenter tests (AUC = 0.826), surpassing the predictive accuracy of human experts (accuracy = 0.561). The risk heatmap enabled the identification of high-risk areas for CLNM, likely correlating with lymphatic metastatic pathways. Additionally, it was observed that the likelihood of metastasis exceeded 80% when the nodal margin's minimum distance from the thyroid capsule was less than 1.25 mm. ACE-Net's capacity to effectively predict CLNM and provide interpretable disease-related insights can importantly reduce unnecessary lymph node dissections by 37.9%, without missing positive cases, thus offering a valuable tool for clinical decision-making.
由于缺乏明确的诊断标准，对于超声诊断的甲状腺癌中央淋巴结转移（CLNM）的风险评估以及预防性淋巴结手术的必要性，目前仍未达成共识。甲状腺结节的定位是公认的CLNM预测指标；然而，由于测量方法的差异，量化这种关系具有挑战性。在本研究中，我们开发了一种基于差分同构的对齐方法，并结合图变换器，以准确提取甲状腺结节的定位和形态信息，从而预测CLNM。我们收集了48,969例接受中央淋巴结（CLN）手术患者的88,796张超声图像，并利用这些图像训练我们的预测模型ACE-Net。此外，我们采用了一种可解释的方法来探索影响CLNM的因素，并生成了一个风险热图，以直观地展示不同甲状腺区域CLNM风险的分布。ACE-Net在6次外部多中心测试中表现出色（AUC = 0.826），超过了人类专家的预测准确性（准确率 = 0.561）。风险热图能够识别CLNM的高危区域，这可能与淋巴转移途径相关。此外，还观察到当淋巴结边缘与甲状腺包膜的最小距离小于1.25 mm时，转移的可能性超过80%。ACE-Net有效预测CLNM并提供可解释的疾病相关见解的能力，可显著减少37.9%的不必要淋巴结清扫，且不会遗漏阳性病例，从而为临床决策提供了一个有价值的工具。
