Abstract
Objective
To construct a new pulmonary nodule diagnostic model with high diagnostic efficiency, non-invasive and simple to measure.
Methods
This study included 424 patients with radioactive pulmonary nodules who underwent preoperative 7-autoantibody (7-AAB) panel testing, CT-based AI diagnosis, and pathological diagnosis by surgical resection. The patients were randomly divided into a training set (n = 212) and a validation set (n = 212). The nomogram was developed through forward stepwise logistic regression based on the predictive factors identified by univariate and multivariate analyses in the training set and was verified internally in the verification set.
Results
A diagnostic nomogram was constructed based on the statistically significant variables of age as well as CT-based AI diagnostic, 7-AAB panel, and CEA test results. In the validation set, the sensitivity, specificity, positive predictive value, and AUC were 82.29%, 90.48%, 97.24%, and 0.899 (95%[CI], 0.851–0.936), respectively. The nomogram showed significantly higher sensitivity than the 7-AAB panel test result (82.29% vs. 35.88%, p < 0.001) and CEA (82.29% vs. 18.82%, p < 0.001); it also had a significantly higher specificity than AI diagnosis (90.48% vs. 69.04%, p = 0.022). For lesions with a diameter of ≤ 2 cm, the specificity of the Nomogram was higher than that of the AI diagnostic system (90.00% vs. 67.50%, p = 0.022).
Conclusions
Based on the combination of a 7-AAB panel, an AI diagnostic system, and other clinical features, our Nomogram demonstrated good diagnostic performance in distinguishing lung nodules, especially those with ≤ 2 cm diameters.
Key Points
• A novel diagnostic model of lung nodules was constructed by combining high-specific tumor markers with a high-sensitivity artificial intelligence diagnostic system.
• The diagnostic model has good diagnostic performance in distinguishing malignant and benign pulmonary nodules, especially for nodules smaller than 2 cm.
• The diagnostic model can assist the clinical decision-making of pulmonary nodules, with the advantages of high diagnostic efficiency, noninvasive, and simple measurement.
Similar content being viewed by others
Abbreviations
- 3D:
-
Three-dimensional
- 7-AAB:
-
7-Autoantibody
- AAH:
-
Atypical adenomatous hyperplasia
- AI:
-
Artificial intelligence
- AIS:
-
Adenocarcinoma in situ
- CEA:
-
Carcinoembryonic antigen
- CI:
-
Confidence interval
- DF:
-
Degree of freedom
- DICOM:
-
Digital Imaging and Communications in Medicine
- ELISA:
-
Enzyme-linked immunosorbent assay
- GGO:
-
Ground-glass opacity
- GPPH:
-
Guangdong Provincial People’s Hospital
- IA:
-
Invasive adenocarcinoma
- LDCT:
-
Low-dose computed tomography
- MIA:
-
Minimally invasive adenocarcinoma
- SCC:
-
Squamous cell carcinoma
- SD:
-
Standard deviation
- SE:
-
Standard error
References
Migliore M (2021) Ground glass opacities of the lung before, during and post COVID-19 pandemic. Ann Transl Med 9:1042
Organization. WH (2020) Use of chest imaging in COVID-19:a rapid advice guide. Available at: https://www.who.int/publications/i/item/use-of-chest-imaging-in-covid-19.
National Lung Screening Trial Research T, Aberle DR, Adams AM et al (2011) Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 365:395–409
Boiselle PM (2013) Computed tomography screening for lung cancer. JAMA 309:1163–1170
Aberle DR, DeMello S, Berg CD et al (2013) Results of the two incidence screenings in the National Lung Screening Trial. N Engl J Med 369:920–931
Assessment SCOHT (2003) Computed tomography in screening for lung cancer, Stockholm
Liu B, Chi W, Li X et al (2020) Evolving the pulmonary nodules diagnosis from classical approaches to deep learning-aided decision support: three decades’ development course and future prospect. J Cancer Res Clin Oncol 146:153–185
Gao N, Tian S, Li X et al (2020) Three-dimensional texture feature analysis of pulmonary nodules in CT images: lung cancer predictive models based on support vector machine classifier. J Digit Imaging 33:414–422
Swensen SJ, Jett JR, Hartman TE et al (2005) CT screening for lung cancer: five-year prospective experience. Radiology 235:259–265
Yang K, Liu J, Tang W et al (2020) Identification of benign and malignant pulmonary nodules on chest CT using improved 3D U-Net deep learning framework. Eur J Radiol 129:109013
Vinolas N, Molina R, Galan MC et al (1998) Tumor markers in response monitoring and prognosis of non-small cell lung cancer: preliminary report. Anticancer Res 18:631–634
Trape J, Buxo J, Perez de Olaguer J, Vidal C (2003) Tumor markers as prognostic factors in treated non-small cell lung cancer. Anticancer Res 23:4277–4281
Chu XY, Hou XB, Song WA, Xue ZQ, Wang B, Zhang LB (2011) Diagnostic values of SCC, CEA, Cyfra21-1 and NSE for lung cancer in patients with suspicious pulmonary masses: a single center analysis. Cancer Biol Ther 11:995–1000
Ren S, Zhang S, Jiang T et al (2018) Early detection of lung cancer by using an autoantibody panel in Chinese population. Oncoimmunology 7:e1384108
Travis WD, Brambilla E, Noguchi M et al (2011) International association for the study of Lung Cancer/American Thoracic Society/European Respiratory Society International Multidisciplinary Classification of lung adenocarcinoma. J Thorac Oncol 6:244–285
Huang G, Liu Z, Maaten LVD, Weinberger KQ (2017) Densely connected convolutional NetworksCVPR,
Zhao W, Yang J, Sun Y et al (2018) 3D deep learning from CT scans predicts tumor invasiveness of subcentimeter pulmonary adenocarcinomas. Cancer Res 78:6881–6889
Li Z, Chen Q, Feng L et al (2020) Active case finding with case management: the key to tackling the COVID-19 pandemic. Lancet 396:63–70
Li X, Hu B, Li H, You B (2019) Application of artificial intelligence in the diagnosis of multiple primary lung cancer. Thorac Cancer 10:2168–2174
Ronneberger O, Fischer P, Brox T (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science(), vol 9351. Springer, Cham. https://doi.org/10.1007/978-3-319-24574-4_28
Wender R, Fontham ET, Barrera E Jr et al (2013) American Cancer Society lung cancer screening guidelines. CA Cancer J Clin 63:107–117
Swensen SJ, Jett JR, Hartman TE et al (2003) Lung cancer screening with CT: Mayo Clinic experience. Radiology 226:756–761
Wang W, Zhuang R, Ma H et al (2020) The diagnostic value of a seven-autoantibody panel and a nomogram with a scoring table for predicting the risk of non-small-cell lung cancer. Cancer Sci 111:1699–1710
Du Q, Yan C, Wu SG et al (2018) Development and validation of a novel diagnostic nomogram model based on tumor markers for assessing cancer risk of pulmonary lesions: a multicenter study in Chinese population. Cancer Lett 420:236–241
Baldwin DR, Gustafson J, Pickup L et al (2020) External validation of a convolutional neural network artificial intelligence tool to predict malignancy in pulmonary nodules. Thorax 75:306–312
Kim RY, Oke JL, Pickup LC et al (2022) Artificial intelligence tool for assessment of indeterminate pulmonary nodules detected with CT. Radiology 304:683–691
Venkadesh KV, Setio AAA, Schreuder A et al (2021) Deep learning for malignancy risk estimation of pulmonary nodules detected at low-dose screening CT. Radiology 300:438–447
Zhang C, Sun X, Dang K et al (2019) Toward an expert level of lung cancer detection and classification using a deep convolutional neural network. Oncologist 24:1159–1165
Hua KL, Hsu CH, Hidayati SC, Cheng WH, Chen YJ (2015) Computer-aided classification of lung nodules on computed tomography images via deep learning technique. Onco Targets Ther 8:2015–2022
Zhang J, Chen L (2019) Clustering-based undersampling with random over sampling examples and support vector machine for imbalanced classification of breast cancer diagnosis. Comput Assist Surg 24(sup2):62–72. https://doi.org/10.1080/24699322.2019.1649074
Mu Y, Xie F, Sun T (2020) Clinical value of seven autoantibodies combined detection in the diagnosis of lung cancer. J Clin Lab Anal 34(8). https://doi.org/10.1002/jcla.23349
Zang R, Li Y, Jin R et al (2019) Enhancement of diagnostic performance in lung cancers by combining CEA and CA125 with autoantibodies detection. Oncoimmunology 8:e1625689
Zhong L, Coe SP, Stromberg AJ, Khattar NH, Jett JR, Hirschowitz EA (2006) Profiling tumor-associated antibodies for early detection of non-small cell lung cancer. J Thorac Oncol 1(6):513–519
Sullivan FM, Farmer E, Mair FS et al (2017) Detection in blood of autoantibodies to tumour antigens as a case-finding method in lung cancer using the EarlyCDT(R)-Lung Test (ECLS): study protocol for a randomized controlled trial. BMC Cancer 17:187
Mittal D, Gubin MM, Schreiber RD, Smyth MJ (2014) New insights into cancer immunoediting and its three component phases--elimination, equilibrium and escape. Curr Opin Immunol 27:16–25
Qiu J, Choi G, Li L et al (2008) Occurrence of autoantibodies to annexin I, 14-3-3 theta and LAMR1 in prediagnostic lung cancer sera. J Clin Oncol 26:5060–5066
Boyle P, Chapman CJ, Holdenrieder S et al (2011) Clinical validation of an autoantibody test for lung cancer. Ann Oncol 22:383–389
Saha MN, Qiu L, Chang H (2013) Targeting p53 by small molecules in hematological malignancies. J Hematol Oncol 6:23
Zhang R, Ma L, Li W, Zhou S, Xu S (2019) Diagnostic value of multiple tumor-associated autoantibodies in lung cancer. Onco Targets Ther 12:457–469
Chen SS, Li K, Wu J et al (2021) Stem signatures associated antibodies yield early diagnosis and precise prognosis predication of patients with non-small cell lung cancer. J Cancer Res Clin Oncol 147:223–233
Qin J, Zeng N, Yang T et al (2018) Diagnostic value of autoantibodies in lung cancer: a systematic review and meta-analysis. Cell Physiol Biochem 51:2631–2646
Silvestri GA, Tanner NT, Kearney P et al (2018) Assessment of plasma proteomics biomarker’s ability to distinguish benign from malignant lung nodules: results of the PANOPTIC (Pulmonary Nodule Plasma Proteomic Classifier) Trial. Chest 154:491–500
Balachandran VP, Gonen M, Smith JJ, DeMatteo RP (2015) Nomograms in oncology: more than meets the eye. Lancet Oncol 16:e173–e180
Reid M, Choi HK, Han X et al (2019) Development of a risk prediction model to estimate the probability of malignancy in pulmonary nodules being considered for biopsy. Chest 156:367–375
Wood DE, Kazerooni EA, Baum SL et al (2018) Lung cancer screening, version 3.2018, NCCN clinical practice guidelines in oncology. J Natl Compr Cancer Netw 16:412–441
Xi K, Wang W, Wen Y et al (2019) Combining plasma miRNAs and computed tomography features to differentiate the nature of pulmonary nodules. Front Oncol 9:975
Szpechcinski A, Rudzinski P, Kupis W, Langfort R, Orlowski T, Chorostowska-Wynimko J (2016) Plasma cell-free DNA levels and integrity in patients with chest radiological findings: NSCLC versus benign lung nodules. Cancer Lett 374:202–207
Acknowledgements
We would like to thank Xiaosong Ben, Zihao Zhou, Liang Xie, Jiming Tang, and Haiyu Zhou for their help with the data collection. We would like to thank the Dianei Technology and AME Lung Cancer Collaborative Group for the academic support and to thank the Editage (www.editage. com) for English language edits.
Funding
The authors state that this work has not received any funding.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The scientific guarantor of this publication is Guibin Qiao (MD, Department of Thoracic Surgery, Guangdong Provincial People’s Hospital, Email: guibinqiao@126.com).
Conflict of interest
The authors (Kaiming Kuang and Jiancheng Yang) of this manuscript declare relationships with the following companies: Diannei Technology Co. Ltd (Shanghai, China).
Statistics and biometry
Yu Ding did the statistical analysis. Qiuling Shi has significant statistical expertise.
Informed consent
Written informed consent was obtained from all subjects (patients) in this study.
Ethical approval
Institutional Review Board approval was obtained from the Medical Ethics Committee and Institutional Review Board of Guangdong Provincial People’s Hospital (GPPH).
Methodology
• prospective
• diagnostic or prognostic study
• performed at one institution
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
ESM 1
(DOCX 71 kb)
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ding, Y., Zhang, J., Zhuang, W. et al. Improving the efficiency of identifying malignant pulmonary nodules before surgery via a combination of artificial intelligence CT image recognition and serum autoantibodies. Eur Radiol 33, 3092–3102 (2023). https://doi.org/10.1007/s00330-022-09317-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-022-09317-x