Automated localization and segmentation of cervical lymph nodes on contrast-enhanced CT using a 3D foveal fully convolutional neural network
Abstract Background In the management of cancer patients, determination of TNM status is essential for treatment decision-making and therefore closely linked to clinical outcome and survival. Here, we developed a tool for automatic three-dimensional (3D) localization and segmentation of cervical lym...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-07-01
|
| Series: | European Radiology Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41747-023-00360-x |
| _version_ | 1827890618173489152 |
|---|---|
| author | Miriam Rinneburger Heike Carolus Andra-Iza Iuga Mathilda Weisthoff Simon Lennartz Nils Große Hokamp Liliana Caldeira Rahil Shahzad David Maintz Fabian Christopher Laqua Bettina Baeßler Tobias Klinder Thorsten Persigehl |
| author_facet | Miriam Rinneburger Heike Carolus Andra-Iza Iuga Mathilda Weisthoff Simon Lennartz Nils Große Hokamp Liliana Caldeira Rahil Shahzad David Maintz Fabian Christopher Laqua Bettina Baeßler Tobias Klinder Thorsten Persigehl |
| author_sort | Miriam Rinneburger |
| collection | DOAJ |
| description | Abstract Background In the management of cancer patients, determination of TNM status is essential for treatment decision-making and therefore closely linked to clinical outcome and survival. Here, we developed a tool for automatic three-dimensional (3D) localization and segmentation of cervical lymph nodes (LNs) on contrast-enhanced computed tomography (CECT) examinations. Methods In this IRB-approved retrospective single-center study, 187 CECT examinations of the head and neck region from patients with various primary diseases were collected from our local database, and 3656 LNs (19.5 ± 14.9 LNs/CECT, mean ± standard deviation) with a short-axis diameter (SAD) ≥ 5 mm were segmented manually by expert physicians. With these data, we trained an independent fully convolutional neural network based on 3D foveal patches. Testing was performed on 30 independent CECTs with 925 segmented LNs with an SAD ≥ 5 mm. Results In total, 4,581 LNs were segmented in 217 CECTs. The model achieved an average localization rate (LR), i.e., percentage of localized LNs/CECT, of 78.0% in the validation dataset. In the test dataset, average LR was 81.1% with a mean Dice coefficient of 0.71. For enlarged LNs with a SAD ≥ 10 mm, LR was 96.2%. In the test dataset, the false-positive rate was 2.4 LNs/CECT. Conclusions Our trained AI model demonstrated a good overall performance in the consistent automatic localization and 3D segmentation of physiological and metastatic cervical LNs with a SAD ≥ 5 mm on CECTs. This could aid clinical localization and automatic 3D segmentation, which can benefit clinical care and radiomics research. Relevance statement Our AI model is a time-saving tool for 3D segmentation of cervical lymph nodes on contrast-enhanced CT scans and serves as a solid base for N staging in clinical practice and further radiomics research. Key points • Determination of N status in TNM staging is essential for therapy planning in oncology. • Segmenting cervical lymph nodes manually is highly time-consuming in clinical practice. • Our model provides a robust, automated 3D segmentation of cervical lymph nodes. • It achieves a high accuracy for localization especially of enlarged lymph nodes. • These segmentations should assist clinical care and radiomics research. Graphical Abstract |
| first_indexed | 2024-03-12T21:12:16Z |
| format | Article |
| id | doaj.art-bc0de49ac82a4782afe929759e5a25e7 |
| institution | Directory Open Access Journal |
| issn | 2509-9280 |
| language | English |
| last_indexed | 2024-03-12T21:12:16Z |
| publishDate | 2023-07-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Radiology Experimental |
| spelling | doaj.art-bc0de49ac82a4782afe929759e5a25e72023-07-30T11:06:59ZengSpringerOpenEuropean Radiology Experimental2509-92802023-07-017111510.1186/s41747-023-00360-xAutomated localization and segmentation of cervical lymph nodes on contrast-enhanced CT using a 3D foveal fully convolutional neural networkMiriam Rinneburger0Heike Carolus1Andra-Iza Iuga2Mathilda Weisthoff3Simon Lennartz4Nils Große Hokamp5Liliana Caldeira6Rahil Shahzad7David Maintz8Fabian Christopher Laqua9Bettina Baeßler10Tobias Klinder11Thorsten Persigehl12Institute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of ColognePhilips ResearchInstitute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of CologneInstitute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of CologneInstitute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of CologneInstitute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of CologneInstitute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of CologneInstitute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of CologneInstitute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of CologneInstitute of Diagnostic and Interventional Radiology, University Hospital WürzburgInstitute of Diagnostic and Interventional Radiology, University Hospital WürzburgPhilips ResearchInstitute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of CologneAbstract Background In the management of cancer patients, determination of TNM status is essential for treatment decision-making and therefore closely linked to clinical outcome and survival. Here, we developed a tool for automatic three-dimensional (3D) localization and segmentation of cervical lymph nodes (LNs) on contrast-enhanced computed tomography (CECT) examinations. Methods In this IRB-approved retrospective single-center study, 187 CECT examinations of the head and neck region from patients with various primary diseases were collected from our local database, and 3656 LNs (19.5 ± 14.9 LNs/CECT, mean ± standard deviation) with a short-axis diameter (SAD) ≥ 5 mm were segmented manually by expert physicians. With these data, we trained an independent fully convolutional neural network based on 3D foveal patches. Testing was performed on 30 independent CECTs with 925 segmented LNs with an SAD ≥ 5 mm. Results In total, 4,581 LNs were segmented in 217 CECTs. The model achieved an average localization rate (LR), i.e., percentage of localized LNs/CECT, of 78.0% in the validation dataset. In the test dataset, average LR was 81.1% with a mean Dice coefficient of 0.71. For enlarged LNs with a SAD ≥ 10 mm, LR was 96.2%. In the test dataset, the false-positive rate was 2.4 LNs/CECT. Conclusions Our trained AI model demonstrated a good overall performance in the consistent automatic localization and 3D segmentation of physiological and metastatic cervical LNs with a SAD ≥ 5 mm on CECTs. This could aid clinical localization and automatic 3D segmentation, which can benefit clinical care and radiomics research. Relevance statement Our AI model is a time-saving tool for 3D segmentation of cervical lymph nodes on contrast-enhanced CT scans and serves as a solid base for N staging in clinical practice and further radiomics research. Key points • Determination of N status in TNM staging is essential for therapy planning in oncology. • Segmenting cervical lymph nodes manually is highly time-consuming in clinical practice. • Our model provides a robust, automated 3D segmentation of cervical lymph nodes. • It achieves a high accuracy for localization especially of enlarged lymph nodes. • These segmentations should assist clinical care and radiomics research. Graphical Abstracthttps://doi.org/10.1186/s41747-023-00360-xArtificial intelligenceDeep learningLymph nodesNeoplasm stagingTomography (x-ray computed) |
| spellingShingle | Miriam Rinneburger Heike Carolus Andra-Iza Iuga Mathilda Weisthoff Simon Lennartz Nils Große Hokamp Liliana Caldeira Rahil Shahzad David Maintz Fabian Christopher Laqua Bettina Baeßler Tobias Klinder Thorsten Persigehl Automated localization and segmentation of cervical lymph nodes on contrast-enhanced CT using a 3D foveal fully convolutional neural network European Radiology Experimental Artificial intelligence Deep learning Lymph nodes Neoplasm staging Tomography (x-ray computed) |
| title | Automated localization and segmentation of cervical lymph nodes on contrast-enhanced CT using a 3D foveal fully convolutional neural network |
| title_full | Automated localization and segmentation of cervical lymph nodes on contrast-enhanced CT using a 3D foveal fully convolutional neural network |
| title_fullStr | Automated localization and segmentation of cervical lymph nodes on contrast-enhanced CT using a 3D foveal fully convolutional neural network |
| title_full_unstemmed | Automated localization and segmentation of cervical lymph nodes on contrast-enhanced CT using a 3D foveal fully convolutional neural network |
| title_short | Automated localization and segmentation of cervical lymph nodes on contrast-enhanced CT using a 3D foveal fully convolutional neural network |
| title_sort | automated localization and segmentation of cervical lymph nodes on contrast enhanced ct using a 3d foveal fully convolutional neural network |
| topic | Artificial intelligence Deep learning Lymph nodes Neoplasm staging Tomography (x-ray computed) |
| url | https://doi.org/10.1186/s41747-023-00360-x |
| work_keys_str_mv | AT miriamrinneburger automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT heikecarolus automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT andraizaiuga automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT mathildaweisthoff automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT simonlennartz automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT nilsgroßehokamp automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT lilianacaldeira automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT rahilshahzad automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT davidmaintz automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT fabianchristopherlaqua automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT bettinabaeßler automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT tobiasklinder automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork AT thorstenpersigehl automatedlocalizationandsegmentationofcervicallymphnodesoncontrastenhancedctusinga3dfovealfullyconvolutionalneuralnetwork |