Purpose: 8-28% of Papillary thyroid carcinoma (PTC) experience recurrence, complicating risk stratification and treatment. We previously identified an inflammatory molecular subtype of PTC associated with poor prognosis. Based on this subtype, we aimed to develop and validate a noninvasive radiomic signature to predict prognosis and treatment response in PTC patients. Experimental Design: We collected preoperative ultrasound images from two large independent centers (n=2506) to develop and validate a Deep Learning Radiomics signature of Inflammation (DLRI) for predicting the inflammatory subtype of PTC, including its correlation with prognosis and anti-inflammatory traditional Chinese medicine (TCM) treatment. Training set 1 (n=64) and internal validation set 2 (n=1108) were from Tianjin Medical University Cancer Institute and Hospital. External validation set 1 (n=76) and 2 (n=1258) were from Fudan University Shanghai Cancer Center. Results: We developed DLRI to accurately predict PTC's inflammatory subtype (AUC=0.97 in the training set 1 and AUC=0.82 in the external validation set 1). High-risk DLRI was significantly associated with poor disease-free survival in the first cohort (HR=16.49, 95% CI: 7.92-34.35, P<0.001) and second cohort (HR=5.42, 95%: 3.67-8.02, P<0.001). DLRI independently predicted disease-free survival, irrespective of clinicopathological variables (P<0.001 for all). Furthermore, patients with high-risk DLRI were likely to benefit from anti-inflammatory TCM treatment (HR=0.19, 95% CI: 0.06-0.55, P=0.002), whereas those in low-risk DLRI did not. Conclusions: DLRI is a reliable noninvasive tool for evaluating prognosis and guiding anti-inflammatory TCM treatment in PTC patients. Prospective studies are needed to confirm these findings.

中文翻译：

---

一种 AI 驱动的术前影像组学亚型，用于预测甲状腺状癌患者的预后和治疗反应


目的：8-28% 的甲状腺状癌 （PTC） 会复发，使风险分层和治疗复杂化。我们之前确定了与不良预后相关的 PTC 炎症分子亚型。基于该亚型，我们旨在开发和验证一种无创放射组学特征，以预测 PTC 患者的预后和治疗反应。实验设计： 我们从两个大型独立中心 （n=2506） 收集术前超声图像，以开发和验证用于预测 PTC 炎症亚型的深度学习放射组学特征 （DLRI），包括其与预后和抗炎中医 （TCM） 治疗的相关性。训练集 1 （n=64） 和内部验证集 2 （n=1108） 来自天津医科大学肿瘤研究所和医院。外部验证集 1 （n=76） 和 2 （n=1258） 来自复旦大学附属肿瘤医院。结果：我们开发了 DLRI 来准确预测 PTC 的炎症亚型 （训练集 1 中的 AUC=0.97 和外部验证集 1 中的 AUC=0.82）。高危 DLRI 与第一队列 （HR=16.49,95% CI： 7.92-34.35， P<0.001） 和第二队列 （HR=5.42， 95%： 3.67-8.02， P<0.001） 的无病生存率差显著相关。DLRI 独立预测无病生存期，与临床病理变量无关 （P<0.001）。此外，高危 DLRI 患者可能受益于中药消炎治疗 （HR=0.19,95% CI： 0.06-0.55，P=0.002），而低危 DLRI 患者则没有。结论： DLRI 是一种可靠的无创工具，用于评估 PTC 患者的预后和指导中药消炎治疗。需要前瞻性研究来证实这些发现。