基于深度学习影像组学和纵隔脂肪组织的列线图用于非小细胞肺癌术后脑转移风险的术前预测

Deep learning radiomics and mediastinal adipose tissue-based nomogram for preoperative prediction of postoperative‌ brain metastasis risk in non-small cell lung cancer.

作者信息

Niu Ye, Jia Hao-Bo, Li Xue-Meng, Huang Wen-Juan, Liu Ping-Ping, Liu Le, Liu Zeng-Yao, Wang Qiu-Jun, Li Yuan-Zhou, Miao Shi-Di, Wang Rui-Tao, Duan Ze-Xun

机构信息

Department of Internal Medicine, Harbin Medical University Cancer Hospital, Harbin Medical University, NO.150 Haping ST, Nangang District, Harbin, Heilongjiang, 150081, China.

The School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, 611731, China.

出版信息

BMC Cancer. 2025 Jul 1;25(1):1133. doi: 10.1186/s12885-025-14466-5.

DOI:10.1186/s12885-025-14466-5

PMID:40597925

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12219950/

Abstract

BACKGROUND AND OBJECTIVES

Brain metastasis (BM) significantly affects the prognosis of non-small cell lung cancer (NSCLC) patients. Increasing evidence suggests that adipose tissue influences cancer progression and metastasis. This study aimed to develop a predictive nomogram integrating mediastinal fat area (MFA) and deep learning (DL)-derived tumor characteristics to stratify postoperative‌ BM risk in NSCLC patients.

MATERIALS AND METHODS

A retrospective cohort of 585 surgically resected NSCLC patients was analyzed. Preoperative computed tomography (CT) scans were utilized to quantify MFA using ImageJ software (radiologist-validated measurements). Concurrently, a DL algorithm extracted tumor radiomic features, generating a deep learning brain metastasis score (DLBMS). Multivariate logistic regression identified independent BM predictors, which were incorporated into a nomogram. Model performance was assessed via area under the receiver operating characteristic curve (AUC), calibration plots, integrated discrimination improvement (IDI), net reclassification improvement (NRI), and decision curve analysis (DCA).

RESULTS

Multivariate analysis identified N stage, EGFR mutation status, MFA, and DLBMS as independent predictors of BM. The nomogram achieved superior discriminative capacity (AUC: 0.947 in the test set), significantly outperforming conventional models. MFA contributed substantially to predictive accuracy, with IDI and NRI values confirming its incremental utility (IDI: 0.123, < 0.001; NRI: 0.386, = 0.023). Calibration analysis demonstrated strong concordance between predicted and observed BM probabilities, while DCA confirmed clinical net benefit across risk thresholds.

CONCLUSION

This DL-enhanced nomogram, incorporating MFA and tumor radiomics, represents a robust and clinically useful tool for preoperative prediction of postoperative BM risk in NSCLC. The integration of adipose tissue metrics with advanced imaging analytics advances personalized prognostic assessment in NSCLC patients.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1186/s12885-025-14466-5.

摘要

背景与目的

脑转移（BM）显著影响非小细胞肺癌（NSCLC）患者的预后。越来越多的证据表明，脂肪组织会影响癌症进展和转移。本研究旨在开发一种预测列线图，整合纵隔脂肪面积（MFA）和深度学习（DL）衍生的肿瘤特征，以对NSCLC患者术后的BM风险进行分层。

材料与方法

分析了585例接受手术切除的NSCLC患者的回顾性队列。利用术前计算机断层扫描（CT）扫描，通过ImageJ软件（经放射科医生验证的测量）对MFA进行量化。同时，一种DL算法提取肿瘤放射组学特征，生成深度学习脑转移评分（DLBMS）。多因素逻辑回归确定了独立的BM预测因素，并将其纳入列线图。通过受试者操作特征曲线下面积（AUC）、校准图、综合判别改善（IDI）、净重新分类改善（NRI）和决策曲线分析（DCA）评估模型性能。

结果

多因素分析确定N分期、表皮生长因子受体（EGFR）突变状态、MFA和DLBMS为BM的独立预测因素。该列线图具有卓越的判别能力（测试集中AUC为0.947），显著优于传统模型。MFA对预测准确性有很大贡献，IDI和NRI值证实了其增加的效用（IDI：0.123，<0.001；NRI：0.386，=0.023）。校准分析表明预测的和观察到的BM概率之间具有很强的一致性，而DCA证实了跨风险阈值的临床净效益。