肿瘤细胞治疗研究
英文原题：Deep learning-based quantification of tumor-infiltrating lymphocytes as a prognostic indicator in nasopharyngeal carcinoma: multicohort findings.
Deep learning-based quantification of tumor-infiltrating lymphocytes as a prognostic indicator in nasopharyngeal carcinoma: multicohort findings.
源自 H&E 染色的 WSIs 的 TIL DL 百分比可有效对非转移性 NPC 进行风险分层，并可能作为接受 ICB 治疗的转移性 NPC 中的生物标志物，有助于个体化治疗的患者选择。
鼻咽癌（NPC）具有富含TIL（肿瘤浸润淋巴细胞）（TILs）的肿瘤免疫微环境，这对预后很重要，但量化起来劳动强度大。本研究评估了一种深度学习模型，用于量化鼻咽癌苏木精-伊红（H&E）染色全切片图像（WSIs）中的 TILs（TIL DL），并探讨 TIL DL 百分比与患者结局及对免疫检查点阻断（ICB）反应之间的关联。
我们回顾性分析了来自两个中心的435例非转移性NPC患者，分为训练队列（n = 220）和验证队列（n = 215）。另外纳入了一个接受ICB治疗的初治转移性NPC患者队列（n = 63）。深度学习模型从H&E染色的WSI中计算TIL DL百分比。评估了TIL DL百分比与免疫组织化学（IHC）来源的TIL密度之间的相关性。生存分析评估了其预后意义。
TIL DL 百分比与 IHC 得出的 TIL 密度呈强相关（CD3+ T 细胞 R = 0.46，CD8+ T 细胞 R = 0.33，CD20+ B 细胞 R = 0.57；均 P < 0.001）。较高的 TIL DL 百分比（中位 45.7%）与更好的 5 年无病生存（DFS）和总生存（OS）相关，在训练队列（DFS：80.6% 对 62.5%，P = 0.016；OS：84.4% 对 71.8%，P = 0.025）和验证队列（DFS：87.3% 对 74.3%，P = 0.016；OS：93.7% 对 82.6%，P = 0.010）中均是如此。在接受 ICB 治疗的转移性队列中，较高的 TIL DL 百分比预示更好的 3 年无进展生存（PFS：40.5% 对 25.0%，P = 0.022）。多因素分析证实，TIL DL 百分比在两种情况下均为独立预后因素。
BACKGROUND: Nasopharyngeal carcinoma (NPC) features a tumor-immune microenvironment rich in tumor-infiltrating lymphocytes (TILs), important for prognosis but labor-intensive to quantify. This study evaluates a deep learning model to quantify TILs (TIL DL ) in hematoxylin and eosin (H&E)-stained whole-slide images (WSIs) of NPC and explores the association of TIL DL percentage with patient outcomes and response to immune checkpoint blockade (ICB). METHODS: We retrospectively analyzed 435 nonmetastatic NPC patients from two centers, divided into a training cohort (n = 220) and a validation cohort (n = 215). An additional cohort of de novo metastatic NPC patients receiving ICB therapy (n = 63) was included. The deep learning model calculated TIL DL percentages from H&E-stained WSIs. Correlations between TIL DL percentages and immunohistochemistry (IHC)-derived TIL densities were assessed. Survival analyses evaluated their prognostic significance. RESULTS: TIL DL percentages showed strong correlations with IHC-derived TIL densities (CD3+ T cells R = 0.46, CD8+ T cells R = 0.33, CD20+ B cells R = 0.57; all P < 0.001). Higher TIL DL percentages (median 45.7%) were associated with better 5-year disease-free survival (DFS) and overall survival (OS) in both training (DFS: 80.6% versus 62.5%, P = 0.016; OS: 84.4% versus 71.8%, P = 0.025) and validation cohorts (DFS: 87.3% versus 74.3%, P = 0.016; OS: 93.7% versus 82.6%, P = 0.010). In the ICB-treated metastatic cohort, higher TIL DL percentages predicted better 3-year progression-free survival (PFS: 40.5% versus 25.0%, P = 0.022). Multivariate analyses confirmed TIL DL percentage as an independent prognostic factor in both settings. CONCLUSIONS: The TIL DL percentage derived from H&E-stained WSIs effectively stratifies risk in nonmetastatic NPC and may serve as a biomarker in metastatic NPC treated with ICB, aiding in patient selection for individualized treatment.
MEMBER ACCOUNT
登录成功会直接打开下一页。
