甲状腺乳头状癌（PTC）是全球甲状腺癌的主要形式，特别是当发生淋巴结转移（LNM）时。由遗传改变和肿瘤微环境成分驱动的分子异质性导致了 PTC 的复杂性。了解这些复杂性对于精确的风险分层和治疗决策至关重要。这项研究对我们医院的 521 名 PTC 患者和来自癌症基因组图谱 (TCGA) 的 499 名患者进行了全面分析。真实世界队列 1 包括 256 名 I-III 期 PTC 患者。通过基于 DNA 的下一代测序分析了 252 名患者的组织，通过单细胞 RNA 测序 (scRNA-seq) 分析了 4 名患者的组织。此外，从 TCGA 收集了 586 个 PTC 病理切片，从真实世界队列 2 收集了 275 个 PTC 病理切片。使用匹配的组织病理学图像、基因组、转录组和免疫细胞数据开发了深度学习多模态模型来预测 LNM 和无病生存期 (DFS)。这项研究总共包括 1,011 名 PTC 患者，其中 256 名患者来自队列 1，275 名患者来自队列 2，499 名患者来自 TCGA。在队列 1 中，我们根据 BRAF、RAS、RET 和其他突变将 PTC 分为四种分子亚型。 BRAF 突变与 LNM 显着相关并影响 DFS。 ScRNA-seq 识别出具有 LNM 的 BRAF 突变 PTC 中不同的 T 细胞亚型并降低了 B 细胞多样性。该研究还探索了与癌症相关的成纤维细胞和巨噬细胞，强调了它们与 LNM 的关联。该深度学习模型使用来自 328 名 PTC 患者的 405 张病理切片和 RNA 序列进行训练，并使用 TCGA 队列中 140 名 PTC 患者的 181 张切片和 RNA 序列进行验证。它实现了很高的准确性，训练队列中的 AUC 为 0.86，验证队列中为 0.84，真实世界队列中为 0.83 2。训练队列中高危患者的 DFS 率显着较低（P<0.001）。 1 年模型 AUC 为 0.91，3 年模型 AUC 为 0.93，5 年模型 AUC 为 0.87。在验证队列中，高风险患者的 DFS 也较低（P<0.001）；第 1 年、第 3 年和第 5 年的 AUC 分别为 0.89、0.87 和 0.80。我们利用 GradCAM 算法从基于病理学的深度学习模型生成热图，直观地突出显示 PTC 患者的高风险肿瘤区域。这增强了临床医生对模型预测的理解并提高了诊断准确性，特别是在淋巴结转移的病例中。基于人工智能的分析揭示了对 PTC 分子异质性的重要见解，强调了 BRAF 突变的影响。集成的深度学习模型在预测转移方面显示出前景，为改进诊断和治疗策略提供了宝贵的贡献。版权所有 © 2024 作者。由 Wolters Kluwer Health, Inc. 出版

Papillary thyroid carcinoma (PTC) is the predominant form of thyroid cancer globally, especially when lymph node metastasis (LNM) occurs. Molecular heterogeneity, driven by genetic alterations and tumor microenvironment components, contributes to the complexity of PTC. Understanding these complexities is essential for precise risk stratification and therapeutic decisions.This study involved a comprehensive analysis of 521 patients with PTC from our hospital and 499 patients from The Cancer Genome Atlas (TCGA). The real-world cohort 1 comprised 256 patients with stage I-III PTC. Tissues from 252 patients were analyzed by DNA-based next-generation sequencing, and tissues from four patients were analyzed by single-cell RNA sequencing (scRNA-seq). Additionally, 586 PTC pathological sections were collected from TCGA, and 275 PTC pathological sections were collected from the real-world cohort 2. A deep learning multimodal model was developed using matched histopathology images, genomic, transcriptomic, and immune cell data to predict LNM and disease-free survival (DFS).This study included a total of 1,011 PTC patients, comprising 256 patients from cohort 1, 275 patients from cohort 2, and 499 patients from TCGA. In cohort 1, we categorized PTC into four molecular subtypes based on BRAF, RAS, RET, and other mutations. BRAF mutations were significantly associated with LNM and impacted DFS. ScRNA-seq identified distinct T cell subtypes and reduced B cell diversity in BRAF-mutated PTC with LNM. The study also explored cancer-associated fibroblasts and macrophages, highlighting their associations with LNM. The deep learning model was trained using 405 pathology slides and RNA sequences from 328 PTC patients and validated with 181 slides and RNA sequences from 140 PTC patients in the TCGA cohort. It achieved high accuracy, with an AUC of 0.86 in the training cohort, 0.84 in the validation cohort, and 0.83 in the real-world cohort 2. High-risk patients in the training cohort had significantly lower DFS rates (P<0.001). Model AUCs were 0.91 at 1 year, 0.93 at 3 years, and 0.87 at 5 years. In the validation cohort, high-risk patients also had lower DFS (P<0.001); the AUCs were 0.89, 0.87, and 0.80 at 1, 3, and 5 years. We utilized the GradCAM algorithm to generate heatmaps from pathology-based deep learning models, which visually highlighted high-risk tumor areas in PTC patients. This enhanced clinicians' understanding of the model's predictions and improved diagnostic accuracy, especially in cases with lymph node metastasis.The AI-based analysis uncovered vital insights into PTC molecular heterogeneity, emphasizing BRAF mutations' impact. The integrated deep learning model shows promise in predicting metastasis, offering valuable contributions to improved diagnostic and therapeutic strategies.Copyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc.