现代仪器与医疗

基于TabPFN模型的CT影像组学联合临床影像特征对亚实性肺腺癌浸润性的术前预测研究

PDF下载

洪森 ¹ , 漆万银 ² , 周颖俊 ³ , 罗圣杰 ¹

现代仪器与医疗 | 临床研究 2025,31(6): 26-35

收起

现代仪器与医疗 |临床研究 2025 , 31 (6) : 26 -35

基于TabPFN模型的CT影像组学联合临床影像特征对亚实性肺腺癌浸润性的术前预测研究

全屏

洪森¹, 漆万银², 周颖俊³, 罗圣杰¹

作者信息

^1.广州医科大学附属妇女儿童医疗中心放射科，广州　510623

^2.西南医科大学附属医院放射科，泸州　646000

^3.湘潭市中心医院放射科，湘潭　411100

作者简介:

洪森，男，硕士研究生，住院医师，研究方向：影像诊断及影像组学研究

Preoperative prediction of invasiveness in part-solid lung adenocarcinoma using CT radiomics combined with clinical-radiological features based on the TabPFN model

Sen Hong¹, Wanyin Qi², Yingjun Zhou³, Shengjie Luo¹

Affiliations

^1.Department of Radiology, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou 510623, China

^2.Department of Radiology, the Affiliated Hospital of Southwest Medical University, Luzhou 646000, China

^3.Department of Radiology, Xiangtan Central Hospital, Xiangtan 411100, China

出版时间: 2025-12-10 doi: 10.11876/mimt202506005

文章导航

摘要

收起

目的

构建基于表格先验数据拟合网络（tabular prior-data fitted network，TabPFN）模型的CT影像组学联合临床影像特征预测体系，提升亚实性肺腺癌浸润性的术前预测精度。

方法

回顾性纳入2019年1月至2023年1月于多中心接受手术治疗、术后病理确诊为亚实性肺腺癌的330例患者，按7∶3的比例随机分为训练集（n=231）与验证集（n=99）。对术前薄层高分辨率CT图像进行病灶分割，提取1 239个定量影像组学特征；通过“批量t检验筛选差异特征→Pearson相关性分析剔除冗余特征（|r|≥0.9）→LASSO回归构建影像组学评分（Radscore）”的特征工程流程优化特征。同时提取患者年龄、性别、结节大小、实性成分占比（consolidation-to-tunor ratio，CTR）、病变位置、形态学征象等临床影像特征。分别构建TabPFN模型、随机森林（rondom forest，RF）、极端梯度提升（extreme gradient boosting，XGBoost）、轻量级梯度提升（light gradient boosting machine，LightGBM）等机器学习模型，以“Radscore+临床影像特征”为输入进行二分类任务构建模型，采用受试者工作特征（receiver operating characteristic，ROC）曲线下面积（area under curve，AUC）、准确率、精确率、召回率、F1值评估模型效能。

结果

纳入的330例患者中，病理确诊非浸润性肺腺癌101例（30.61%）、浸润性肺腺癌229例（69.39%）；TabPFN模型表现最优，AUC为0.839，准确率为0.798，精确率为0.853，召回率为0.877，F1值为0.865。基于SHAP分析对模型的解释显示，Radscore与CTR为TabPFN模型中预测亚实性肺腺癌浸润性的最稳健特征。

结论

基于TabPFN模型的CT影像组学联合临床影像特征分析，可有效实现亚实性肺腺癌浸润性的术前预测，为临床选择肺叶切除或亚肺叶切除等个体化手术方案提供客观参考依据，具有重要临床应用价值。

关键词

TabPFN模型 / 影像组学 / 亚实性肺腺癌 / 临床影像特征 / 术前预测

Abstract

收起

Objective

To construct a CT radiomics model combined with clinical-imaging features based on the tabular prior-data fitted network (TabPFN) algorithm to enhance the preoperative prediction accuracy for the invasiveness of subsolid lung adenocarcinoma.

Methods

This retrospective study enrolled 330 patients with postoperative pathologically confirmed subsolid lung adenocarcinoma who underwent surgical treatment at multiple centers between January 2019 and January 2023. Patients were randomly divided into a training set (n=231) and a validation set (n=99) at a 7:3 ratio. Preoperative thin-slice high-resolution CT images were segmented to extract 1,239 quantitative radiomics features. A feature engineering pipeline was applied to optimize the feature set, involving: batch t-test for screening differential features, Pearson correlation analysis to remove redundant features (|r|≥0.9), and LASSO regression to construct a radiomics score (Radscore). Clinical-imaging features including patient age, sex, nodule size, consolidation-to-tumor ratio (CTR), lesion location, and morphological signs were also extracted. Multiple machine learning models were built for the binary classification task using “Radscore + clinical-imaging features” as input, including TabPFN, random forest (RF), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and F1 score.

Results

Among the 330 patients, pathology confirmed 101 cases (30.61%) as non-invasive adenocarcinoma and 229 cases (69.39%) as invasive adenocarcinoma. The TabPFN model demonstrated the best performance, achieving an AUC of 0.839, accuracy of 0.798, precision of 0.853, recall of 0.877, and an F1 score of 0.865. The interpretation of the model based on SHAP analysis indicated that Radscore and CTR are the most reliable features for predicting the invasiveness of subsolid lung adenocarcinoma in the TabPFN model.

Conclusion

The analysis combining CT radiomics and clinical-imaging features based on the TabPFN model can effectively achieve preoperative prediction of invasiveness in subsolid lung adenocarcinoma. This provides an objective reference for clinical decision-making regarding individualized surgical strategies, such as lobectomy versus sublobar resection, and holds significant clinical application value.

Key words

TabPFN model / Radiomics / Subsolid lung adenocarcinoma / Clinical-imaging features / Preoperative prediction

引用本文

洪森, 漆万银, 周颖俊, 罗圣杰. 基于TabPFN模型的CT影像组学联合临床影像特征对亚实性肺腺癌浸润性的术前预测研究. 现代仪器与医疗, 2025 , 31 (6) : 26 -35 . DOI: 10.11876/mimt202506005

Sen Hong, Wanyin Qi, Yingjun Zhou, Shengjie Luo. Preoperative prediction of invasiveness in part-solid lung adenocarcinoma using CT radiomics combined with clinical-radiological features based on the TabPFN model[J]. Modern Instruments & Medical Treatment, 2025 , 31 (6) : 26 -35 . DOI: 10.11876/mimt202506005

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

Zuo Z C, Wang L D, Peng K, et al. Development and validation of a nomogram for predicting the 1-, 3-, and 5-year survival in patients with acinar-predominant lung adenocarcinoma[J]. Curr Med Sci, 2022, 42(6): 1178-1185.

[2]

Zuo Z, Zhang G, Song P, et al. Survival nomogram for stage IB non-small-cell lung cancer patients, based on the SEER database and an external validation cohort[J]. Ann Surg Oncol, 2021, 28(7): 3941-3950.

[3]

Bertolaccini L, Tralongo A C, Del Re M, et al. Segmentectomy vs. lobectomy in stage IA non-small cell lung cancer: a systematic review and meta-analysis of perioperative and survival outcomes[J]. Lung Cancer, 2024, 197: 107990.

[4]

Zuo Z, Wang P, Zeng W, et al. Measuring pure ground-glass nodules on computed tomography: assessing agreement between a commercially available deep learning algorithm and radiologists' readings[J]. Acta Radiol, 2023, 64(4): 1422-1430.

[5]

Ye T, Deng L, Wang S, et al. Lung adenocarcinomas manifesting as radiological part-solid nodules define a special clinical subtype[J]. J Thorac Oncol, 2019, 14(4): 617-627.

[6]

Liu M, Yang L, Sun X, et al. Evaluation of prognosis in patients with lung adenocarcinoma with atypical solid nodules on thin-section CT images[J]. Radiol Cardiothorac Imaging, 2024, 6(1): e220234.

[7]

Okamoto T, Miyawaki M, Toyokawa G, et al. Clinical significance of part-solid lung cancer in the eighth edition TNM staging system[J]. Interact Cardiovasc Thorac Surg, 2022, 34(2): 219-226.

[8]

Yotsukura M, Asamura H, Motoi N, et al. Long-term prognosis of patients with resected adenocarcinoma in situ and minimally invasive adenocarcinoma of the lung[J]. J Thorac Oncol, 2021, 16(8): 1312-1320.

[9]

Watanabe Y, Hattori A, Nojiri S, et al. Clinical impact of a small component of ground-glass opacity in solid-dominant clinical stage IA non-small cell lung cancer[J]. J Thorac Cardiovasc Surg, 2022, 163(3): 791-801.

[10]

Shi Y, Wu S, Ma S, et al. Comparison between wedge resection and lobectomy/segmentectomy for early-stage non-small cell lung cancer: a bayesian meta-analysis and systematic review[J]. Ann Surg Oncol, 2022, 29(3): 1868-1879.

[11]

Dolan D, Swanson S J, Gill R, et al. Survival and recurrence following wedge resection versus lobectomy for early-stage non-small cell lung cancer[J]. Semin Thorac Cardiovasc Surg, 2022, 34(2): 712-723.

[12]

Zuo Z, Deng J, Ge W, et al. Quantifying intratumoral heterogeneity within sub-regions to predict high-grade patterns in clinical stage I solid lung adenocarcinoma[J]. BMC Cancer, 2025, 25(1): 51.

[13]

Zuo Z, Zhang G, Lin S, et al. Radiomics nomogram based on optimal volume of interest derived from high-resolution CT for preoperative prediction of IASLC grading in clinical IA lung adenocarcinomas: a multi-center, large-population study[J]. Technol Cancer Res Treat, 2024, 23: 15330338241300734.

[14]

Qi H, Zuo Z, Lin S, et al. Assessment of intratumor heterogeneity for preoperatively predicting the invasiveness of pulmonary adenocarcinomas manifesting as pure ground-glass nodules[J]. Quant Imaging Med Surg, 2025, 15(1): 272-286.

[15]

Zuo Z, Zhang G, Chen J, et al. CT radiomic nomogram using optimal volume of interest for preoperatively predicting invasive mucinous adenocarcinomas in patients with incidental pulmonary nodules: a multicenter, large-scale study[J]. Technol Cancer Res Treat, 2024, 23: 15330338241308307.

[16]

Zuo Z, Zeng Y, Deng J, et al. Intratumoral heterogeneity score enhances invasiveness prediction in pulmonary ground-glass nodules via stacking ensemble machine learning[J]. Insights Imaging, 2025, 16(1): 209.

[17]

Zuo Z, Zeng W, Peng K, et al. Development of a novel combined nomogram integrating deep-learning-assisted CT texture and clinical-radiological features to predict the invasiveness of clinical stage IA part-solid lung adenocarcinoma: a multicentre study[J]. Clin Radiol, 2023, 78(10): e698-e706.

[18]

Li Y, Ding J, Wu K, et al. Ensemble machine learning classifiers combining CT radiomics and clinical-radiological features for preoperative prediction of pathological invasiveness in lung adenocarcinoma presenting as partsolid nodules: a multicenter retrospective study[J]. Technol Cancer Res Treat, 2025, 24: 15330338251351365.

[19]

Weng Q, Zhou L, Wang H, et al. A radiomics model for determining the invasiveness of solitary pulmonary nodules that manifest as part-solid nodules[J]. Clin Radiol, 2019, 74(12): 933-943.

[20]

Wu G, Woodruff H C, Shen J, et al. Diagnosis of invasive lung adenocarcinoma based on chest CT radiomic features of partsolid pulmonary nodules: a multicenter study[J]. Radiology, 2020, 297(2): 451-458.

[21]

Bühlmann P, Hothorn T. Boosting algorithms: regularization, prediction and model fitting[J]. Stat Sci, 2007, 22(4): 477-550.

[22]

Hollmann N, Müller S, Purucker L, et al. Accurate predictions on small data with a tabular foundation model[J]. Nature, 2025, 637: 319-326.

[23]

Li Y, Yang J, Xiao P, et al. MRI delta-radiomics and morphological feature-driven TabPFN model for preoperative prediction of lymphovascular invasion in invasive breast cancer[J]. Technol Cancer Res Treat, 2025, 24: 15330338251362050.

[24]

Zheng H, Chen W, Qi W, et al. Enhancing the prediction of the invasiveness of pulmonary adenocarcinomas presenting as pure ground-glass nodules: integrating intratumor heterogeneity score with clinical-radiological features via machine learning in a multicenter study[J]. Digit Health, 2024, 10: 20552076241289181.

[25]

Ling T, Zuo Z, Wu L, et al. Predicting neoadjuvant chemotherapy response in locally advanced gastric cancer using a machine learning model combining radiomics and clinical biomarkers[J]. Digit Health, 2025, 11: 20552076251341740.

[26]

Ling T, Zuo Z, Huang M, et al. Prediction of mucinous adenocarcinoma in colorectal cancer with mucinous components detected in preoperative biopsy diagnosis[J]. Abdom Radiol (NY), 2025, 50(7): 2794-2805.

2025年第31卷第6期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.11876/mimt202506005

首发时间：2026-10-23
出版时间：2025-12-10

补充材料

相关文章

文章信息

作者

出版历史

基金

作者信息

^1.广州医科大学附属妇女儿童医疗中心放射科，广州　510623

^2.西南医科大学附属医院放射科，泸州　646000

^3.湘潭市中心医院放射科，湘潭　411100

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/xdyqyyl/CN/10.11876/mimt202506005

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT