Department of Thoracic Surgery, Tokyo Medical University, Tokyo, Japan.
Department of Radiology, Tokyo Medical University, Tokyo, Japan.
Ann Surg Oncol. 2022 Dec;29(13):8185-8193. doi: 10.1245/s10434-022-12516-x. Epub 2022 Sep 7.
We seek to explore the ability of computed tomography (CT)-based radiomics coupled with artificial intelligence (AI) to predict early recurrence (< 2 years after surgery) in patients with clinical stage 0-IA non-small cell lung cancer (c-stage 0-IA NSCLC).
Data of 642 patients were collected for early recurrence and assigned to the derivation and validation cohorts at a ratio of 2:1. Using the AI software Beta Version (Fujifilm Corporation, Japan), 39 AI imaging factors, including 17 factors from the AI ground-glass nodule analysis and 22 radiomic features from nodule characterization analysis, were extracted.
Multivariate analysis showed that male sex (p = 0.016), solid part size (p < 0.001), CT value standard deviation (p = 0.038), solid part volume ratio (p = 0.016), and bronchus translucency (p = 0.007) were associated with recurrence-free survival (RFS). Receiver operating characteristics analysis showed that the area under the curve and optimal cutoff values relevant to recurrence were 0.707 and 1.49 cm for solid part size, and 0.710 and 22.9% for solid part volume ratio, respectively. The 5-year RFS rates for patients in the validation set with solid part size ≤ 1.49 cm and > 1.49 cm were 92.2% and 70.4% (p < 0.001), whereas those for patients with solid part volume ratios ≤ 22.9% and > 22.9% were 97.8% and 71.7% (p < 0.001), respectively.
CT-based radiomics coupled with AI contributes to the noninvasive prediction of early recurrence in patients with c-stage 0-IA NSCLC.
我们旨在探索基于计算机断层扫描（CT）的放射组学与人工智能（AI）相结合，预测临床分期 0-IA 期非小细胞肺癌（c 分期 0-IA NSCLC）患者的早期复发（术后<2 年）。
收集了 642 例患者的早期复发数据，并按照 2:1 的比例将其分配到推导和验证队列中。使用 AI 软件 Beta Version（富士胶片公司，日本）提取了 39 个 AI 成像因素，包括 AI 磨玻璃结节分析的 17 个因素和结节特征分析的 22 个放射组学特征。
多变量分析表明，男性（p=0.016）、实性部分大小（p<0.001）、CT 值标准差（p=0.038）、实性部分体积比（p=0.016）和支气管透明度（p=0.007）与无复发生存率（RFS）相关。受试者工作特征分析显示，与复发相关的曲线下面积和最佳截断值分别为 1.49cm 时的实性部分大小为 0.707，实性部分体积比为 0.710 和 22.9%。验证队列中实性部分大小≤1.49cm 和>1.49cm 的患者 5 年 RFS 率分别为 92.2%和 70.4%（p<0.001），而实性部分体积比≤22.9%和>22.9%的患者 5 年 RFS 率分别为 97.8%和 71.7%（p<0.001）。
基于 CT 的放射组学与 AI 相结合有助于预测 c 分期 0-IA NSCLC 患者的早期复发。
