Machine learning classification of mediastinal lymph node metastasis in NSCLC: a multicentre study in a Western European patient population
Abstract Background [18F] FDG PET-CT has an important role in the initial staging of lung cancer; however, accurate differentiation between activity in malignant and benign intrathoracic lymph nodes on PET-CT scans can be challenging. The purpose of the current study was to investigate the effect of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-09-01
|
| Series: | EJNMMI Physics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40658-022-00494-8 |
| _version_ | 1797863501503397888 |
|---|---|
| author | Sara S. A. Laros Dennis Dieckens Stephan P. Blazis Johannes A. van der Heide |
| author_facet | Sara S. A. Laros Dennis Dieckens Stephan P. Blazis Johannes A. van der Heide |
| author_sort | Sara S. A. Laros |
| collection | DOAJ |
| description | Abstract Background [18F] FDG PET-CT has an important role in the initial staging of lung cancer; however, accurate differentiation between activity in malignant and benign intrathoracic lymph nodes on PET-CT scans can be challenging. The purpose of the current study was to investigate the effect of incorporating primary tumour data and clinical features to differentiate between [18F] FDG-avid malignant and benign intrathoracic lymph nodes. Methods We retrospectively selected lung cancer patients who underwent PET-CT for initial staging in two centres in the Netherlands. The primary tumour and suspected lymph node metastases were annotated and cross-referenced with pathology results. Lymph nodes were classified as malignant or benign. From the image data, we extracted radiomic features and trained the classifier model using the extreme gradient boost (XGB) algorithm. Various scenarios were defined by selecting different combinations of data input and clinical features. Data from centre 1 were used for training and validation of the models using the XGB algorithm. To determine the performance of the model in a different hospital, the XGB model was tested using data from centre 2. Results Adding primary tumour data resulted in a significant gain in the performance of the trained classifier model. Adding the clinical information about distant metastases did not lead to significant improvement. The performance of the model in the test set (centre 2) was slightly but statistically significantly lower than in the validation set (centre 1). Conclusions Using the XGB algorithm potentially leads to an improved model for the classification of intrathoracic lymph nodes. The inclusion of primary tumour data improved the performance of the model, while additional knowledge of distant metastases did not. In patients in whom metastases are limited to lymph nodes in the thorax, this may reduce costly and invasive procedures such as endobronchial ultrasound or mediastinoscopy procedures. |
| first_indexed | 2024-04-09T22:37:34Z |
| format | Article |
| id | doaj.art-d1a623dbb95e4565954ab7984a9fc8cb |
| institution | Directory Open Access Journal |
| issn | 2197-7364 |
| language | English |
| last_indexed | 2024-04-09T22:37:34Z |
| publishDate | 2022-09-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EJNMMI Physics |
| spelling | doaj.art-d1a623dbb95e4565954ab7984a9fc8cb2023-03-22T12:25:27ZengSpringerOpenEJNMMI Physics2197-73642022-09-019111010.1186/s40658-022-00494-8Machine learning classification of mediastinal lymph node metastasis in NSCLC: a multicentre study in a Western European patient populationSara S. A. Laros0Dennis Dieckens1Stephan P. Blazis2Johannes A. van der Heide3Department of Medical Physics and Engineering, Albert Schweitzer HospitalDepartment of Nuclear Medicine, Albert Schweitzer HospitalDepartment of Medical Physics and Engineering, Albert Schweitzer HospitalDepartment of Nuclear Medicine, Albert Schweitzer HospitalAbstract Background [18F] FDG PET-CT has an important role in the initial staging of lung cancer; however, accurate differentiation between activity in malignant and benign intrathoracic lymph nodes on PET-CT scans can be challenging. The purpose of the current study was to investigate the effect of incorporating primary tumour data and clinical features to differentiate between [18F] FDG-avid malignant and benign intrathoracic lymph nodes. Methods We retrospectively selected lung cancer patients who underwent PET-CT for initial staging in two centres in the Netherlands. The primary tumour and suspected lymph node metastases were annotated and cross-referenced with pathology results. Lymph nodes were classified as malignant or benign. From the image data, we extracted radiomic features and trained the classifier model using the extreme gradient boost (XGB) algorithm. Various scenarios were defined by selecting different combinations of data input and clinical features. Data from centre 1 were used for training and validation of the models using the XGB algorithm. To determine the performance of the model in a different hospital, the XGB model was tested using data from centre 2. Results Adding primary tumour data resulted in a significant gain in the performance of the trained classifier model. Adding the clinical information about distant metastases did not lead to significant improvement. The performance of the model in the test set (centre 2) was slightly but statistically significantly lower than in the validation set (centre 1). Conclusions Using the XGB algorithm potentially leads to an improved model for the classification of intrathoracic lymph nodes. The inclusion of primary tumour data improved the performance of the model, while additional knowledge of distant metastases did not. In patients in whom metastases are limited to lymph nodes in the thorax, this may reduce costly and invasive procedures such as endobronchial ultrasound or mediastinoscopy procedures.https://doi.org/10.1186/s40658-022-00494-8Lung cancerIntrathoracic lymph nodesMachine learningRadiomicsPET-CT |
| spellingShingle | Sara S. A. Laros Dennis Dieckens Stephan P. Blazis Johannes A. van der Heide Machine learning classification of mediastinal lymph node metastasis in NSCLC: a multicentre study in a Western European patient population EJNMMI Physics Lung cancer Intrathoracic lymph nodes Machine learning Radiomics PET-CT |
| title | Machine learning classification of mediastinal lymph node metastasis in NSCLC: a multicentre study in a Western European patient population |
| title_full | Machine learning classification of mediastinal lymph node metastasis in NSCLC: a multicentre study in a Western European patient population |
| title_fullStr | Machine learning classification of mediastinal lymph node metastasis in NSCLC: a multicentre study in a Western European patient population |
| title_full_unstemmed | Machine learning classification of mediastinal lymph node metastasis in NSCLC: a multicentre study in a Western European patient population |
| title_short | Machine learning classification of mediastinal lymph node metastasis in NSCLC: a multicentre study in a Western European patient population |
| title_sort | machine learning classification of mediastinal lymph node metastasis in nsclc a multicentre study in a western european patient population |
| topic | Lung cancer Intrathoracic lymph nodes Machine learning Radiomics PET-CT |
| url | https://doi.org/10.1186/s40658-022-00494-8 |
| work_keys_str_mv | AT sarasalaros machinelearningclassificationofmediastinallymphnodemetastasisinnsclcamulticentrestudyinawesterneuropeanpatientpopulation AT dennisdieckens machinelearningclassificationofmediastinallymphnodemetastasisinnsclcamulticentrestudyinawesterneuropeanpatientpopulation AT stephanpblazis machinelearningclassificationofmediastinallymphnodemetastasisinnsclcamulticentrestudyinawesterneuropeanpatientpopulation AT johannesavanderheide machinelearningclassificationofmediastinallymphnodemetastasisinnsclcamulticentrestudyinawesterneuropeanpatientpopulation |