Multiple Tumor-related autoantibodies test enhances CT-based deep learning performance in diagnosing lung cancer with diameters < 70 mm: a prospective study in China

Abstract Background Deep learning (DL) demonstrates high sensitivity but low specificity in lung cancer (LC) detection during CT screening, and the seven Tumor-associated antigens autoantibodies (7-TAAbs), known for its high specificity in LC, was employed to improve the DL’s specificity for the eff...

Full description

Saved in:
Bibliographic Details
Main Authors: Qingcheng Meng, Pengfei Ren, Lanwei Guo, Pengrui Gao, Tong Liu, Wenda Chen, Wentao Liu, Hui Peng, Mengjia Fang, Shuo Meng, Hong Ge, Meng Li, Xuejun Chen
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Pulmonary Medicine
Subjects:
Online Access:https://doi.org/10.1186/s12890-025-03807-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849344627883114496
author Qingcheng Meng
Pengfei Ren
Lanwei Guo
Pengrui Gao
Tong Liu
Wenda Chen
Wentao Liu
Hui Peng
Mengjia Fang
Shuo Meng
Hong Ge
Meng Li
Xuejun Chen
author_facet Qingcheng Meng
Pengfei Ren
Lanwei Guo
Pengrui Gao
Tong Liu
Wenda Chen
Wentao Liu
Hui Peng
Mengjia Fang
Shuo Meng
Hong Ge
Meng Li
Xuejun Chen
author_sort Qingcheng Meng
collection DOAJ
description Abstract Background Deep learning (DL) demonstrates high sensitivity but low specificity in lung cancer (LC) detection during CT screening, and the seven Tumor-associated antigens autoantibodies (7-TAAbs), known for its high specificity in LC, was employed to improve the DL’s specificity for the efficiency of LC screening in China. Purpose To develop and evaluate a risk model combining 7-TAAbs test and DL scores for diagnosing LC with pulmonary lesions < 70 mm. Materials and methods Four hundreds and six patients with 406 lesions were enrolled and assigned into training set (n = 313) and test set (n = 93) randomly. The malignant lesions were defined as those lesions with high malignant risks by DL or those with positive expression of 7-TAAbs panel. Model performance was assessed using the area under the receiver operating characteristic curves (AUC). Results In the training set, the AUCs for DL, 7-TAAbs, combined model (DL and 7-TAAbs) and combined model (DL or 7-TAAbs) were 0.771, 0.638, 0.606, 0.809 seperately. In the test set, the combined model (DL or 7-TAAbs) achieved achieved the highest sensitivity (82.6%), NPV (81.8%) and accuracy (79.6%) among four models, and the AUCs of DL model, 7-TAAbs model, combined model (DL and 7-TAAbs), and combined model (DL or 7-TAAbs) were 0.731, 0.679, 0.574, and 0.794, respectively. Conclusion The 7-TAAbs test significantly enhances DL performance in predicting LC with pulmonary leisons < 70 mm in China.
format Article
id doaj-art-490b6f6af9664e89b30d3268c8a1194f
institution Kabale University
issn 1471-2466
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Pulmonary Medicine
spelling doaj-art-490b6f6af9664e89b30d3268c8a1194f2025-08-20T03:42:37ZengBMCBMC Pulmonary Medicine1471-24662025-07-0125111110.1186/s12890-025-03807-6Multiple Tumor-related autoantibodies test enhances CT-based deep learning performance in diagnosing lung cancer with diameters < 70 mm: a prospective study in ChinaQingcheng Meng0Pengfei Ren1Lanwei Guo2Pengrui Gao3Tong Liu4Wenda Chen5Wentao Liu6Hui Peng7Mengjia Fang8Shuo Meng9Hong Ge10Meng Li11Xuejun Chen12Department of Radiology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalDepartment of Molecular Pathology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalDepartment of Clinical Research Management, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalDepartment of Radiology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalDepartment of Radiology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalDepartment of Radiology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalDepartment of Radiology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalDepartment of Radiology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalDepartment of Radiology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalDepartment of Mechanical and Electrical Engineering, Beijing University of Chemical TechnologyDepartment of Radiotherapy, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalDepartment of Radiology, National Clinical Research Center for Cancer/Cancer Hospital, National Cancer Center, Chinese Academy of Medical Sciences, Peking Union Medical CollegeDepartment of Radiology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalAbstract Background Deep learning (DL) demonstrates high sensitivity but low specificity in lung cancer (LC) detection during CT screening, and the seven Tumor-associated antigens autoantibodies (7-TAAbs), known for its high specificity in LC, was employed to improve the DL’s specificity for the efficiency of LC screening in China. Purpose To develop and evaluate a risk model combining 7-TAAbs test and DL scores for diagnosing LC with pulmonary lesions < 70 mm. Materials and methods Four hundreds and six patients with 406 lesions were enrolled and assigned into training set (n = 313) and test set (n = 93) randomly. The malignant lesions were defined as those lesions with high malignant risks by DL or those with positive expression of 7-TAAbs panel. Model performance was assessed using the area under the receiver operating characteristic curves (AUC). Results In the training set, the AUCs for DL, 7-TAAbs, combined model (DL and 7-TAAbs) and combined model (DL or 7-TAAbs) were 0.771, 0.638, 0.606, 0.809 seperately. In the test set, the combined model (DL or 7-TAAbs) achieved achieved the highest sensitivity (82.6%), NPV (81.8%) and accuracy (79.6%) among four models, and the AUCs of DL model, 7-TAAbs model, combined model (DL and 7-TAAbs), and combined model (DL or 7-TAAbs) were 0.731, 0.679, 0.574, and 0.794, respectively. Conclusion The 7-TAAbs test significantly enhances DL performance in predicting LC with pulmonary leisons < 70 mm in China.https://doi.org/10.1186/s12890-025-03807-6X-ray computed tomographyTumor biomarkersDeep learningNeoplasm, pulmonary lesions
spellingShingle Qingcheng Meng
Pengfei Ren
Lanwei Guo
Pengrui Gao
Tong Liu
Wenda Chen
Wentao Liu
Hui Peng
Mengjia Fang
Shuo Meng
Hong Ge
Meng Li
Xuejun Chen
Multiple Tumor-related autoantibodies test enhances CT-based deep learning performance in diagnosing lung cancer with diameters < 70 mm: a prospective study in China
BMC Pulmonary Medicine
X-ray computed tomography
Tumor biomarkers
Deep learning
Neoplasm, pulmonary lesions
title Multiple Tumor-related autoantibodies test enhances CT-based deep learning performance in diagnosing lung cancer with diameters < 70 mm: a prospective study in China
title_full Multiple Tumor-related autoantibodies test enhances CT-based deep learning performance in diagnosing lung cancer with diameters < 70 mm: a prospective study in China
title_fullStr Multiple Tumor-related autoantibodies test enhances CT-based deep learning performance in diagnosing lung cancer with diameters < 70 mm: a prospective study in China
title_full_unstemmed Multiple Tumor-related autoantibodies test enhances CT-based deep learning performance in diagnosing lung cancer with diameters < 70 mm: a prospective study in China
title_short Multiple Tumor-related autoantibodies test enhances CT-based deep learning performance in diagnosing lung cancer with diameters < 70 mm: a prospective study in China
title_sort multiple tumor related autoantibodies test enhances ct based deep learning performance in diagnosing lung cancer with diameters 70 mm a prospective study in china
topic X-ray computed tomography
Tumor biomarkers
Deep learning
Neoplasm, pulmonary lesions
url https://doi.org/10.1186/s12890-025-03807-6
work_keys_str_mv AT qingchengmeng multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT pengfeiren multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT lanweiguo multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT pengruigao multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT tongliu multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT wendachen multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT wentaoliu multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT huipeng multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT mengjiafang multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT shuomeng multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT hongge multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT mengli multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina
AT xuejunchen multipletumorrelatedautoantibodiestestenhancesctbaseddeeplearningperformanceindiagnosinglungcancerwithdiameters70mmaprospectivestudyinchina