Department of Pathology, All India Institute of Medical Sciences, New Delhi, India.
Department of Pathology, All India Institute of Medical Sciences, New Delhi, India.
J Thorac Oncol. 2022 Jun;17(6):793-805. doi: 10.1016/j.jtho.2022.02.013. Epub 2022 Mar 22.
Accurate subtyping of NSCLC into lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) is the cornerstone of NSCLC diagnosis. Cytology samples reveal higher rates of classification failures, that is, subtyping as non-small cell carcinoma-not otherwise specified (NSCC-NOS), as compared with histology specimens. This study aims to identify specific algorithms on the basis of known cytomorphologic features that aid accurate and successful subtyping of NSCLC on cytology.
A total of 13 expert cytopathologists participated anonymously in an online survey to subtype 119 NSCLC cytology cases (gold standard diagnoses being LUAD in 80 and LUSC in 39) enriched for nonkeratinizing LUSC. They selected from 23 predefined cytomorphologic features that they used in subtyping. Data were analyzed using machine learning algorithms on the basis of random forest method and regression trees.
From 1474 responses recorded, concordant cytology typing was achieved in 53.7% (792 of 1474) responses. NSCC-NOS rates on cytology were similar among gold standard LUAD (36%) and LUSC (38%) cases. Misclassification rates were higher in gold standard LUSC (17.6%) than gold standard LUAD (5.5%; p < 0.0001). Keratinization, when present, recognized LUSC with high accuracy. In its absence, the machine learning algorithms developed on the basis of experts' choices were unable to reduce cytology NSCC-NOS rates without increasing misclassification rates.
Suboptimal recognition of LUSC in the absence of keratinization remains the major hurdle in improving cytology subtyping accuracy with such cases either failing classification (NSCC-NOS) or misclassifying as LUAD. NSCC-NOS seems to be an inevitable morphologic diagnosis emphasizing that ancillary immunochemistry is necessary to achieve accurate subtyping on cytology.
准确地将 NSCLC 分为肺腺癌 (LUAD) 和肺鳞状细胞癌 (LUSC) 是 NSCLC 诊断的基石。与组织学标本相比,细胞学样本显示出更高的分类失败率,即分类为非小细胞癌-非特指型 (NSCC-NOS)。本研究旨在根据已知的细胞形态学特征,确定特定的算法,以帮助准确、成功地对细胞学标本进行 NSCLC 分型。
共有 13 位细胞病理专家匿名参与了一项在线调查,对 119 例 NSCLC 细胞学病例进行亚型分类(80 例为 LUAD,39 例为 LUSC),这些病例富含非角化性 LUSC。他们从 23 个预先定义的细胞形态学特征中选择用于分类的特征。数据使用随机森林方法和回归树的机器学习算法进行分析。
在记录的 1474 次应答中,53.7%(792/1474)的应答达到了一致的细胞学分型。金标准 LUAD(36%)和 LUSC(38%)病例的细胞学 NSCC-NOS 发生率相似。金标准 LUSC (17.6%)的误诊率高于金标准 LUAD(5.5%;p<0.0001)。角化存在时,可准确识别 LUSC。角化不存在时,基于专家选择开发的机器学习算法无法在不增加误诊率的情况下降低细胞学 NSCC-NOS 率。
在缺乏角化的情况下,对 LUSC 的识别不理想仍然是提高细胞学分型准确性的主要障碍,这些病例要么分类失败(NSCC-NOS),要么误诊为 LUAD。NSCC-NOS 似乎是一种不可避免的形态学诊断,强调需要辅助免疫化学来实现细胞学的准确分型。