Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learning
Abstract Background We evaluated the role of radiomics applied to contrast-enhanced computed tomography (CT) in the detection of lymph node (LN) metastases in patients with known lung cancer compared to 18F-fluorodeoxyglucose positron emission tomography (PET)/CT as a reference. Methods This retrosp...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-09-01
|
| Series: | European Radiology Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41747-022-00296-8 |
| _version_ | 1798000648292139008 |
|---|---|
| author | Boris Gorodetski Philipp Hendrik Becker Alexander Daniel Jacques Baur Alexander Hartenstein Julian Manuel Michael Rogasch Christian Furth Holger Amthauer Bernd Hamm Marcus Makowski Tobias Penzkofer |
| author_facet | Boris Gorodetski Philipp Hendrik Becker Alexander Daniel Jacques Baur Alexander Hartenstein Julian Manuel Michael Rogasch Christian Furth Holger Amthauer Bernd Hamm Marcus Makowski Tobias Penzkofer |
| author_sort | Boris Gorodetski |
| collection | DOAJ |
| description | Abstract Background We evaluated the role of radiomics applied to contrast-enhanced computed tomography (CT) in the detection of lymph node (LN) metastases in patients with known lung cancer compared to 18F-fluorodeoxyglucose positron emission tomography (PET)/CT as a reference. Methods This retrospective analysis included 381 patients with 1,799 lymph nodes (450 malignant, 1,349 negative). The data set was divided into a training and validation set. A radiomics analysis with 4 filters and 6 algorithms resulting in 24 different radiomics signatures and a bootstrap algorithm (Bagging) with 30 bootstrap iterations was performed. A decision curve analysis was applied to generate a net benefit to compare the radiomics signature to two expert radiologists as one-by-one and as a prescreening tool in combination with the respective radiologist and only the radiologists. Results All 24 modeling methods showed good and reliable discrimination for malignant/benign LNs (area under the curve 0.75−0.87). The decision curve analysis showed a net benefit for the least absolute shrinkage and selection operator (LASSO) classifier for the entire probability range and outperformed the expert radiologists except for the high probability range. Using the radiomics signature as a prescreening tool for the radiologists did not improve net benefit. Conclusions Radiomics showed good discrimination power irrespective of the modeling technique in detecting LN metastases in patients with known lung cancer. The LASSO classifier was a suitable diagnostic tool and even outperformed the expert radiologists, except for high probabilities. Radiomics failed to improve clinical benefit as a prescreening tool. |
| first_indexed | 2024-04-11T11:23:41Z |
| format | Article |
| id | doaj.art-5b6e5baefbba4665bbd3cca80eaa9811 |
| institution | Directory Open Access Journal |
| issn | 2509-9280 |
| language | English |
| last_indexed | 2024-04-11T11:23:41Z |
| publishDate | 2022-09-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Radiology Experimental |
| spelling | doaj.art-5b6e5baefbba4665bbd3cca80eaa98112022-12-22T04:26:22ZengSpringerOpenEuropean Radiology Experimental2509-92802022-09-016111510.1186/s41747-022-00296-8Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learningBoris Gorodetski0Philipp Hendrik Becker1Alexander Daniel Jacques Baur2Alexander Hartenstein3Julian Manuel Michael Rogasch4Christian Furth5Holger Amthauer6Bernd Hamm7Marcus Makowski8Tobias Penzkofer9Department of Radiology (including Pediatric Radiology), Charité–Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Campus Virchow-KlinikumDepartment of Radiology (including Pediatric Radiology), Charité–Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Campus Virchow-KlinikumDepartment of Radiology (including Pediatric Radiology), Charité–Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Campus Virchow-KlinikumDepartment of Radiology (including Pediatric Radiology), Charité–Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Campus Virchow-KlinikumDepartment of Nuclear Medicine, Charité–Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Campus Virchow-KlinikumDepartment of Nuclear Medicine, Charité–Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Campus Virchow-KlinikumDepartment of Nuclear Medicine, Charité–Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Campus Virchow-KlinikumDepartment of Radiology (including Pediatric Radiology), Charité–Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Campus Virchow-KlinikumDepartment of Radiology (including Pediatric Radiology), Charité–Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Campus Virchow-KlinikumDepartment of Radiology (including Pediatric Radiology), Charité–Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Campus Virchow-KlinikumAbstract Background We evaluated the role of radiomics applied to contrast-enhanced computed tomography (CT) in the detection of lymph node (LN) metastases in patients with known lung cancer compared to 18F-fluorodeoxyglucose positron emission tomography (PET)/CT as a reference. Methods This retrospective analysis included 381 patients with 1,799 lymph nodes (450 malignant, 1,349 negative). The data set was divided into a training and validation set. A radiomics analysis with 4 filters and 6 algorithms resulting in 24 different radiomics signatures and a bootstrap algorithm (Bagging) with 30 bootstrap iterations was performed. A decision curve analysis was applied to generate a net benefit to compare the radiomics signature to two expert radiologists as one-by-one and as a prescreening tool in combination with the respective radiologist and only the radiologists. Results All 24 modeling methods showed good and reliable discrimination for malignant/benign LNs (area under the curve 0.75−0.87). The decision curve analysis showed a net benefit for the least absolute shrinkage and selection operator (LASSO) classifier for the entire probability range and outperformed the expert radiologists except for the high probability range. Using the radiomics signature as a prescreening tool for the radiologists did not improve net benefit. Conclusions Radiomics showed good discrimination power irrespective of the modeling technique in detecting LN metastases in patients with known lung cancer. The LASSO classifier was a suitable diagnostic tool and even outperformed the expert radiologists, except for high probabilities. Radiomics failed to improve clinical benefit as a prescreening tool.https://doi.org/10.1186/s41747-022-00296-8Machine learningLymph nodesLymphatic metastasisLung neoplasmsTomography (x-ray computed) |
| spellingShingle | Boris Gorodetski Philipp Hendrik Becker Alexander Daniel Jacques Baur Alexander Hartenstein Julian Manuel Michael Rogasch Christian Furth Holger Amthauer Bernd Hamm Marcus Makowski Tobias Penzkofer Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learning European Radiology Experimental Machine learning Lymph nodes Lymphatic metastasis Lung neoplasms Tomography (x-ray computed) |
| title | Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learning |
| title_full | Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learning |
| title_fullStr | Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learning |
| title_full_unstemmed | Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learning |
| title_short | Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learning |
| title_sort | inferring fdg pet positivity of lymph node metastases in proven lung cancer from contrast enhanced ct using radiomics and machine learning |
| topic | Machine learning Lymph nodes Lymphatic metastasis Lung neoplasms Tomography (x-ray computed) |
| url | https://doi.org/10.1186/s41747-022-00296-8 |
| work_keys_str_mv | AT borisgorodetski inferringfdgpetpositivityoflymphnodemetastasesinprovenlungcancerfromcontrastenhancedctusingradiomicsandmachinelearning AT philipphendrikbecker inferringfdgpetpositivityoflymphnodemetastasesinprovenlungcancerfromcontrastenhancedctusingradiomicsandmachinelearning AT alexanderdanieljacquesbaur inferringfdgpetpositivityoflymphnodemetastasesinprovenlungcancerfromcontrastenhancedctusingradiomicsandmachinelearning AT alexanderhartenstein inferringfdgpetpositivityoflymphnodemetastasesinprovenlungcancerfromcontrastenhancedctusingradiomicsandmachinelearning AT julianmanuelmichaelrogasch inferringfdgpetpositivityoflymphnodemetastasesinprovenlungcancerfromcontrastenhancedctusingradiomicsandmachinelearning AT christianfurth inferringfdgpetpositivityoflymphnodemetastasesinprovenlungcancerfromcontrastenhancedctusingradiomicsandmachinelearning AT holgeramthauer inferringfdgpetpositivityoflymphnodemetastasesinprovenlungcancerfromcontrastenhancedctusingradiomicsandmachinelearning AT berndhamm inferringfdgpetpositivityoflymphnodemetastasesinprovenlungcancerfromcontrastenhancedctusingradiomicsandmachinelearning AT marcusmakowski inferringfdgpetpositivityoflymphnodemetastasesinprovenlungcancerfromcontrastenhancedctusingradiomicsandmachinelearning AT tobiaspenzkofer inferringfdgpetpositivityoflymphnodemetastasesinprovenlungcancerfromcontrastenhancedctusingradiomicsandmachinelearning |