Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ASCO Annual Meeting 2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress
Clinical Collections
Advances in Alzheimer’s

2024 ASCO Annual Meeting

Keep up to date with all the top stories and latest evidence with our hub page, including official congress videos and expert takeaways.
ADVANCED SEARCH
Log in
Top
European Radiology
Published in: European Radiology 6/2021

01-06-2021 | Computed Tomography | Nuclear Medicine

Machine learning-based diagnostic method of pre-therapeutic 18F-FDG PET/CT for evaluating mediastinal lymph nodes in non-small cell lung cancer

Authors: Jang Yoo, Miju Cheon, Yong Jin Park, Seung Hyup Hyun, Jae Ill Zo, Sang-Won Um, Hong-Hee Won, Kyung-Han Lee, Byung-Tae Kim, Joon Young Choi

Published in: European Radiology | Issue 6/2021

Login to get access

Abstract

Objectives

We aimed to find the best machine learning (ML) model using 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) for evaluating metastatic mediastinal lymph nodes (MedLNs) in non-small cell lung cancer, and compare the diagnostic results with those of nuclear medicine physicians.

Methods

A total of 1329 MedLNs were reviewed. Boosted decision tree, logistic regression, support vector machine, neural network, and decision forest models were compared. The diagnostic performance of the best ML model was compared with that of physicians. The ML method was divided into ML with quantitative variables only (MLq) and adding clinical information (MLc). We performed an analysis based on the 18F-FDG-avidity of the MedLNs.

Results

The boosted decision tree model obtained higher sensitivity and negative predictive values but lower specificity and positive predictive values than the physicians. There was no significant difference between the accuracy of the physicians and MLq (79.8% vs. 76.8%, p = 0.067). The accuracy of MLc was significantly higher than that of the physicians (81.0% vs. 76.8%, p = 0.009). In MedLNs with low 18F-FDG-avidity, ML had significantly higher accuracy than the physicians (70.0% vs. 63.3%, p = 0.018).

Conclusion

Although there was no significant difference in accuracy between the MLq and physicians, the diagnostic performance of MLc was better than that of MLq or of the physicians. The ML method appeared to be useful for evaluating low metabolic MedLNs. Therefore, adding clinical information to the quantitative variables from 18F-FDG PET/CT can improve the diagnostic results of ML.

Key Points

• Machine learning using two-class boosted decision tree model revealed the highest value of area under curve, and it showed higher sensitivity and negative predictive values but lower specificity and positive predictive values than nuclear medicine physicians.
• The diagnostic results from machine learning method after adding clinical information to the quantitative variables improved accuracy significantly than nuclear medicine physicians.
• Machine learning could improve the diagnostic significance of metastatic mediastinal lymph nodes, especially in mediastinal lymph nodes with low 18F-FDG-avidity.
Appendix
Available only for authorised users
Literature
1.
Detterbeck FC, Postmus PE, Tanoue LT (2013) The stage classification of lung cancer: diagnosis and management of lung cancer, 3rd ed: American College of Chest Physicians evidence-based clinical practice guidelines. Chest 143:e191S–e210SCrossRef
2.
Silvestri GA, Gonzalez AV, Jantz MA et al (2013) Methods for staging non-small cell lung cancer. Chest 143:e211S–e250sCrossRef
3.
Lu P, Sun Y, Sun Y, Yu L (2014) The role of (18)F-FDG PET/CT for evaluation of metastatic mediastinal lymph nodes in patients with lung squamous-cell carcinoma or adenocarcinoma. Lung Cancer 85:53–58CrossRef
4.
Li X, Zhang H, Xing L et al (2012) Mediastinal lymph nodes staging by 18F-FDG PET/CT for early stage non-small cell lung cancer: a multicenter study. Radiother Oncol 102:246–250CrossRef
5.
Darling GE, Maziak DE, Inculet RI et al (2011) Positron emission tomography-computed tomography compared with invasive mediastinal staging in non-small cell lung cancer: results of mediastinal staging in the early lung positron emission tomography trial. J Thorac Oncol 6:1367–1372CrossRef
6.
Ong P, Grosu H, Eapen GA et al (2015) Endobronchial ultrasound-guided transbronchial needle aspiration for systemic nodal staging of lung cancer in patients with N0 disease by computed tomography and integrated positron emission tomography-computed tomography. Ann Am Thorac Soc 12(3):415–419CrossRef
7.
Naur TMH, Konge L, Clementsen PF (2017) Endobronchial ultrasound-guided transbronchial needle aspiration for staging of patients with non-small cell lung cancer without mediastinal involvement at positron emission tomography computed tomography. Respiration 94:279–284CrossRef
8.
Um SW, Kim HK, Jung SH et al (2015) Endobronchial ultrasound versus mediastinoscopy for mediastinal nodal staging of non-small-cell lung cancer. J Thorac Oncol 10:331–337CrossRef
9.
Gu P, Zhao YZ, Jiang LY, Zhang W, Xin Y, Han BH (2009) Endobronchial ultrasound-guided transbronchial needle aspiration for staging of lung cancer: a systematic review and meta-analysis. Eur J Cancer 45:1389–1396
10.
Vincent BD, El-Bayoumi E, Hoffman B et al (2008) Real-time endobronchial ultrasound-guided transbronchial lymph node aspiration. Ann Thorc Surg 85:224–230CrossRef
11.
Choi H (2018) Deep learning in nuclear medicine and molecular imaging: Current perspectives and future directions. Nucl Med Mol Imaging 52:109–118CrossRef
12.
Katako A, Shelton P, Goertzen AL et al (2018) Machine learning identified an Alzheimer’s disease-related FDG-PET pattern which is also expressed in Lewy body dementia and Parkinson’s disease dementia. Sci Rep 8:13236CrossRef
13.
Lu S, Xia Y, Cai W, Fulham M, Feng DD, Alzheimer’s Disease Neuroimaging Initiative (2017) Early identification of mild cognitive impairment using incomplete random forest-robust support vector machine and FDG-PET imaging. Comput Med Imaging Graph 60:35–41
14.
Dukart J, Mueller K, Barthel H et al (2013) Meta-analysis based SVM classification enables accurate detection of Alzheimer’s disease across different clinical centers using FDG-PET and MRI. Psychiatry Res 212:230–236CrossRef
15.
Wang H, Zhou Z, Li Y et al (2017) Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images. EJNMMI Res 7(1):11CrossRef
16.
Wnuk P, Kowalewski M, Malkowski B, et al (2014) PET-CT derived artificial neural network can predict mediastinal lymph nodes metastases in non-small cell lung cancer patients. Preliminary report and scoring model. Q J Nucl Med Mol Imaging 2014 Oct 7. Online ahead of print
17.
Gao X, Chu C, Li Y et al (2015) The method and efficacy of support vector machine classifiers based on texture features and multi-resolution histogram from (18)F-FDG PET-CT images for the evaluation of mediastinal lymph nodes in patients with lung cancer. Eur J Radiol 84:312–317CrossRef
18.
Shim SS, Lee KS, Kim BT et al (2005) Non-small cell lung cancer: prospective comparison of integrated FDG PET/CT and CT alone for preoperative staging. Radiology 236:1011–1019CrossRef
19.
Kim YK, Lee KS, Kim BT et al (2007) Mediastinal nodal staging of nonsmall cell lung cancer using integrated 18F-FDG PET/CT in a tuberculosis-endemic country: diagnostic efficacy in 674 patients. Cancer 109:1068–1077CrossRef
20.
Rogasch JM, Apostoloval I, Steffen IG et al (2016) Standardized visual reading of F18-FDG PET in patients with non-small cell lung cancer scheduled for preoperative thoracic lymph node staging. Eur J Radiol 85:1345–1350CrossRef
21.
Lee AY, Choi SJ, Jung KP, Park JS, Lee SM, Bae SK (2014) Characteristics of metastatic mediastinal lymph nodes of non-small cell lung cancer on preoperative F-18 FDG PET/CT. Nucl Med Mol Imaging 48:41–46
22.
Budiawan H, Cheon GJ, Im HJ et al (2013) Heterogeneity analysis of (18)F-FDG uptake in differentiating between metastatic and inflammatory lymph nodes in adenocarcinoma of the lung: comparison with other parameters and its application in a clinical setting. Nucl Med Mol Imaging 47:232–241CrossRef
23.
Cho J, Choe JG, Pahk K et al (2017) Ratio of mediastinal lymph node SUV to primary tumor SUV in 18F-FDG PET/CT for nodal staging in non-small-cell lung cancer. Nucl Med Mol Imaging 51:140–146CrossRef
24.
Flechsig P, Frank P, Kratochwil C et al (2017) Radiomics analysis using density threshold for FDG-PET/CT-based N-staging in lung cancer patients. Mol Imaging Biol 19:315–322CrossRef
25.
van Baardwijk A, Bosmans G, van Suylen RJ et al (2008) Correlation of intra-tumor heterogeneity on 18F-FDG PET with pathologic features in non-small cell lung cancer: a feasibility study. Radiother Oncol 87:55–58CrossRef
26.
Pahk K, Chung JH, Yi E, Kim S, Lee SH (2018) Metabolic tumor heterogeneity analysis by F-18 FDG PET/CT predicts mediastinal lymph node metastasis in non-small cell lung cancer patients with clinically suspected N2. Eur J Radiol 106:145–149
27.
Choi JY (2018) Radiomics and deep learning in clinical imaging: what should we do? Nucl Med Mol Imaging 52:89–90CrossRef
28.
Kaseda K, Watanabe K, Asakura K, Kazama A, Ozawa Y (2016) Identification of false-negative and false-positive diagnoses of lymph node metastases in non-small cell lung cancer patients staged by integrated (18F-) fluorodeoxyglucose-positron emission tomography/computed tomography: A retrospective cohort study. Thorac Cancer 7:473–480
29.
Li S, Zheng Q, Ma Y et al (2013) Implications of false negative and false positive diagnosis in lymph node staging of NSCLC by means of 18F-FDG PET/CT. PLoS One 8:e78552CrossRef
30.
Bryant AS, Cerfolio RJ (2006) The clinical stage of non-small cell lung cancer as assessed by means of fluorodeoxyglucose-positron emission tomographic/computed tomographic scanning is less accurate in cigarette smokers. J Thorac Cardiovasc Surg 132:1363–1368CrossRef
31.
El-Sherief AH, Lau CT, Wu CC, Drake RL, Abbott GF, Rice TW (2014) International association for the study of lung cancer (IASLC) lymph node map: radiologic review with CT illustration. Radiographics 34:1680–1691
32.
Kim BT, Lee KS, Shim SS et al (2006) Stage T1 non-small cell lung cancer: preoperative mediastinal nodal staging with integrated FDG PET/CT – a prospective study. Radiology 241:501–509CrossRef
33.
Park HK, Jeon K, Koh WJ et al (2010) Occult nodal metastasis in patients with non-small cell lung cancer at clinical stage IA by PET/CT. Respirology 15:1179–1184CrossRef
34.
Haruki T, Aokage K, Miyoshi T et al (2015) Mediastinal nodal involvement in patients with clinical stage I non-small-cell lung cancer: possibility of rational lymph node dissection. J Thorac Oncol 10:930–936CrossRef
35.
Liang RB, Yang J, Zeng TS et al (2018) Incidence and distribution of lobe-specific mediastinal lymph node metastasis in non-small cell lung cancer: data from 4511 resected cases. Ann Surg Oncol 25:3300–3307CrossRef
36.
Riquet M, Rivera C, Pricopi C et al (2015) Is the lymphatic drainage of lung cancer lobe-specific? A surgical appraisal. Eur J Cardiothorac Surg 47:543–549CrossRef
37.
Shimada Y, Saji H, Kakihana M et al (2012) Retrospective analysis of nodal spread patterns according to tumor location in pathological N2 non-small cell lung cancer. World J Surg 36:2865–2871CrossRef
Metadata
Title
Machine learning-based diagnostic method of pre-therapeutic 18F-FDG PET/CT for evaluating mediastinal lymph nodes in non-small cell lung cancer
Authors
Jang Yoo
Miju Cheon
Yong Jin Park
Seung Hyup Hyun
Jae Ill Zo
Sang-Won Um
Hong-Hee Won
Kyung-Han Lee
Byung-Tae Kim
Joon Young Choi
Publication date
01-06-2021
Publisher
Springer Berlin Heidelberg
Published in
European Radiology / Issue 6/2021
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI
https://doi.org/10.1007/s00330-020-07523-z

Other articles of this Issue 6/2021

European Radiology 6/2021 Go to the issue

Neuro

The prevalence of brain lesions after in utero surgery for twin-to-twin transfusion syndrome on third-trimester MRI: a retrospective cohort study

Molecular Imaging

Prognostic impact of bone metastases detected by 18F-DOPA PET in patients with metastatic midgut neuroendocrine tumors

Obituary

Obituary for Professor Harry K. Genant, MD

Breast

Deep learning with convolutional neural network in the assessment of breast cancer molecular subtypes based on US images: a multicenter retrospective study

Imaging Informatics and Artificial Intelligence

Artificial intelligence in radiology: 100 commercially available products and their scientific evidence

Vascular-Interventional

Mesenteric artery calcium scoring: a potential screening method for chronic mesenteric ischemia