Center for Computational Imaging and Personalized Diagnostics, Case Western Reserve University, Cleveland, Ohio.
Computer Imaging and Medical Applications Laboratory, Universidad Nacional de Colombia, Bogotá, Colombia.
Clin Cancer Res. 2019 Mar 1;25(5):1526-1534. doi: 10.1158/1078-0432.CCR-18-2013. Epub 2018 Sep 10.
The presence of a high degree of tumor-infiltrating lymphocytes (TIL) has been proven to be associated with outcome in patients with non-small cell lung cancer (NSCLC). However, recent evidence indicates that tissue architecture is also prognostic of disease-specific survival and recurrence. We show a set of descriptors (spatial TIL, SpaTIL) that capture density, and spatial colocalization of TILs and tumor cells across digital images that can predict likelihood of recurrence in early-stage NSCLC.
The association between recurrence in early-stage NSCLC and SpaTIL features was explored on 301 patients across four different cohorts. Cohort D ( = 70) was used to identify the most prognostic SpaTIL features and to train a classifier to predict the likelihood of recurrence. The classifier performance was evaluated in cohorts D ( = 119), D ( = 112), and D ( = 112). Two pathologists graded each sample of D and D; intraobserver agreement and association between manual grading and likelihood of recurrence were analyzed.
SpaTIL was associated with likelihood of recurrence in all test sets (log-rank < 0.02). A multivariate Cox proportional hazards analysis revealed an HR of 3.08 (95% confidence interval, 2.1-4.5, = 7.3 × 10). In contrast, agreement among expert pathologists using tumor grade was moderate (Kappa = 0.5), and the manual TIL grading was only prognostic for one reader in D ( = 8.0 × 10).
A set of features related to density and spatial architecture of TILs was found to be associated with a likelihood of recurrence of early-stage NSCLC. This information could potentially be used for helping in treatment planning and management of early-stage NSCLC..
大量肿瘤浸润淋巴细胞（TIL）的存在已被证明与非小细胞肺癌（NSCLC）患者的预后相关。然而，最近的证据表明，组织结构也是疾病特异性生存和复发的预后因素。我们展示了一组描述符（空间 TIL，SpaTIL），这些描述符可以捕获数字图像中 TIL 和肿瘤细胞的密度和空间共定位，从而预测早期 NSCLC 复发的可能性。
在四个不同队列的 301 名患者中，探讨了早期 NSCLC 复发与 SpaTIL 特征之间的关系。队列 D（=70）用于确定最具预后意义的 SpaTIL 特征，并训练分类器来预测复发的可能性。在队列 D（=119）、D（=112）和 D（=112）中评估了分类器的性能。两位病理学家对 D 和 D 的每个样本进行了分级；分析了内部观察者的一致性以及手动分级与复发可能性之间的关系。
SpaTIL 与所有测试集的复发可能性相关（对数秩检验<0.02）。多变量 Cox 比例风险分析显示，风险比为 3.08（95%置信区间，2.1-4.5，=7.3×10）。相比之下，使用肿瘤分级的专家病理学家之间的一致性为中等（Kappa=0.5），并且手动 TIL 分级仅在 D 中对一位读者具有预后意义（=8.0×10）。
发现一组与 TIL 密度和空间结构相关的特征与早期 NSCLC 复发的可能性相关。这些信息可能有助于早期 NSCLC 的治疗计划和管理。
