Get 20% Off Journals at LWW.com

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

Eur Radiol 2020 Nov 25. Epub 2020 Nov 25.

Department of Nuclear Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea.

Objectives: We aimed to find the best machine learning (ML) model using F-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 F-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 F-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 F-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.

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00330-020-07523-zDOI Listing
November 2020
Get 20% Off Journals at LWW.com

Similar Publications

Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from F-FDG PET/CT images.

EJNMMI Res 2017 Dec 28;7(1):11. Epub 2017 Jan 28.

Center of PET/CT, The Affiliated Tumor Hospital of Harbin Medical University, 150 Haping Road, Nangang District, Harbin, Heilongjiang Province, 150081, China.

Background: This study aimed to compare one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from F-FDG PET/CT images. Another objective was to compare the discriminative power of the recently popular PET/CT texture features with the widely used diagnostic features such as tumor size, CT value, SUV, image contrast, and intensity standard deviation. The four classical machine learning methods included random forests, support vector machines, adaptive boosting, and artificial neural network. Read More

View Article and Full-Text PDF
December 2017

More advantages in detecting bone and soft tissue metastases from prostate cancer using F-PSMA PET/CT.

Hell J Nucl Med 2019 Jan-Apr;22(1):6-9. Epub 2019 Mar 7.

Department of Nuclear Medicine and PET/CT, Evangelismos General Hospital, Ypsilantou 45-47, PC 106 76, Athens, Greece.

Prostate cancer (PCa) is the most common solid cancer affecting men worldwide. Serum prostate-specific antigen (PSA) is at present the most commonly used biomarker for PCa screening, as well as a reliable marker of disease recurrence after initial treatment. Bone metastases (BM) are present in advanced stages of the disease. Read More

View Article and Full-Text PDF
July 2019

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 2014 Jul 18;85(1):53-8. Epub 2014 Apr 18.

Department of PET/CT, The Affiliated Tumor Hospital of Harbin Medical University, 150 Haping Road, Nangang District, Harbin 150081, Heilongjiang Province, China. Electronic address:

Objectives: To evaluate the efficacy of (18)F-FDG PET/CT in depicting metastatic mediastinal lymph nodes in patients with lung squamous-cell carcinoma (LSCC) or lung adenocarcinoma (LAC) in a tuberculosis-endemic country.

Methods: This study retrospectively reviewed patients with LSCC or LAC, who underwent preoperative (18)F-FDG PET/CT to assess mediastinal lymph node metastasis. Patients with the short-axis of mediastinal lymph node≤15mm were included. Read More

View Article and Full-Text PDF
July 2014

Prediction of mediastinal lymph node metastasis based on F-FDG PET/CT imaging using support vector machine in non-small cell lung cancer.

Eur Radiol 2020 Nov 17. Epub 2020 Nov 17.

Department of Molecular Imaging and Nuclear Medicine, Tianjin Medical University Cancer Institute and Hospital, Huanhuxi Road, Hexi Distinct, Tianjin City, 300060, People's Republic of China.

Objective: The purpose of this study was to develop a classification method based on support vector machine (SVM) to improve the diagnostic performance of F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) to detect the lymph node (LN) metastasis in non-small cell lung cancer (NSCLC).

Method: Two hundred nineteen lymph nodes (37 metastatic) from 71 patients were evaluated in this study. SVM models were developed with 7 LN features. Read More

View Article and Full-Text PDF
November 2020