Auto-detection and segmentation of involved lymph nodes in HPV-associated oropharyngeal cancer using a convolutional deep learning neural network
Purpose: Segmentation of involved lymph nodes on head and neck computed tomography (HN-CT) scans is necessary for the radiotherapy planning of early-stage human papilloma virus (HPV) associated oropharynx cancers (OPC). We aimed to train a deep learning convolutional neural network (DL-CNN) to segme...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-09-01
|
| Series: | Clinical and Translational Radiation Oncology |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405630822000520 |
| _version_ | 1828148304619241472 |
|---|---|
| author | Nicolette Taku Kareem A. Wahid Lisanne V. van Dijk Jaakko Sahlsten Joel Jaskari Kimmo Kaski Clifton D. Fuller Mohamed A. Naser |
| author_facet | Nicolette Taku Kareem A. Wahid Lisanne V. van Dijk Jaakko Sahlsten Joel Jaskari Kimmo Kaski Clifton D. Fuller Mohamed A. Naser |
| author_sort | Nicolette Taku |
| collection | DOAJ |
| description | Purpose: Segmentation of involved lymph nodes on head and neck computed tomography (HN-CT) scans is necessary for the radiotherapy planning of early-stage human papilloma virus (HPV) associated oropharynx cancers (OPC). We aimed to train a deep learning convolutional neural network (DL-CNN) to segment involved lymph nodes on HN-CT scans. Methods: Ground-truth segmentation of involved nodes was performed on pre-surgical HN-CT scans for 90 patients who underwent levels II-IV neck dissection for node-positive HPV-OPC (training/validation [n = 70] and testing [n = 20]). A 5-fold cross validation approach was used to train 5 DL-CNN sub-models based on a residual U-net architecture. Validation and testing segmentation masks were compared to ground-truth masks using predetermined metrics. A lymph auto-detection model to discriminate between “node-positive” and “node-negative” HN-CT scans was developed by thresholding segmentation model outputs and evaluated using the area under the receiver operating characteristic curve (AUC). Results: In the DL-CNN validation phase, all sub-models yielded segmentation masks with median Dice ≥ 0.90 and median volume similarity score of ≥ 0.95. In the testing phase, the DL-CNN produced consensus segmentation masks with median Dice of 0.92 (IQR, 0.89–0.95), median volume similarity of 0.97 (IQR, 0.94–0.99), and median Hausdorff distance of 4.52 mm (IQR, 1.22–8.38). The detection model achieved an AUC of 0.98. Conclusion: The results from this single-institution study demonstrate the successful automation of lymph node segmentation for patients with HPV-OPC using a DL-CNN. Future studies, including validation with an external dataset, are necessary to clarify its role in the larger radiation oncology treatment planning workflow. |
| first_indexed | 2024-04-11T21:14:03Z |
| format | Article |
| id | doaj.art-acef4a8ea97a4eaea5d9d9663a1f7715 |
| institution | Directory Open Access Journal |
| issn | 2405-6308 |
| language | English |
| last_indexed | 2024-04-11T21:14:03Z |
| publishDate | 2022-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Clinical and Translational Radiation Oncology |
| spelling | doaj.art-acef4a8ea97a4eaea5d9d9663a1f77152022-12-22T04:02:53ZengElsevierClinical and Translational Radiation Oncology2405-63082022-09-01364755Auto-detection and segmentation of involved lymph nodes in HPV-associated oropharyngeal cancer using a convolutional deep learning neural networkNicolette Taku0Kareem A. Wahid1Lisanne V. van Dijk2Jaakko Sahlsten3Joel Jaskari4Kimmo Kaski5Clifton D. Fuller6Mohamed A. Naser7Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesDepartment of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesDepartment of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States; Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, NetherlandsAalto University School of Science, Aalto, FinlandAalto University School of Science, Aalto, FinlandDepartment of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, NetherlandsDepartment of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesDepartment of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States; Corresponding author at: The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, 1515 Holcombe Blvd., Houston, TX 77030-4009, United States.Purpose: Segmentation of involved lymph nodes on head and neck computed tomography (HN-CT) scans is necessary for the radiotherapy planning of early-stage human papilloma virus (HPV) associated oropharynx cancers (OPC). We aimed to train a deep learning convolutional neural network (DL-CNN) to segment involved lymph nodes on HN-CT scans. Methods: Ground-truth segmentation of involved nodes was performed on pre-surgical HN-CT scans for 90 patients who underwent levels II-IV neck dissection for node-positive HPV-OPC (training/validation [n = 70] and testing [n = 20]). A 5-fold cross validation approach was used to train 5 DL-CNN sub-models based on a residual U-net architecture. Validation and testing segmentation masks were compared to ground-truth masks using predetermined metrics. A lymph auto-detection model to discriminate between “node-positive” and “node-negative” HN-CT scans was developed by thresholding segmentation model outputs and evaluated using the area under the receiver operating characteristic curve (AUC). Results: In the DL-CNN validation phase, all sub-models yielded segmentation masks with median Dice ≥ 0.90 and median volume similarity score of ≥ 0.95. In the testing phase, the DL-CNN produced consensus segmentation masks with median Dice of 0.92 (IQR, 0.89–0.95), median volume similarity of 0.97 (IQR, 0.94–0.99), and median Hausdorff distance of 4.52 mm (IQR, 1.22–8.38). The detection model achieved an AUC of 0.98. Conclusion: The results from this single-institution study demonstrate the successful automation of lymph node segmentation for patients with HPV-OPC using a DL-CNN. Future studies, including validation with an external dataset, are necessary to clarify its role in the larger radiation oncology treatment planning workflow.http://www.sciencedirect.com/science/article/pii/S2405630822000520 |
| spellingShingle | Nicolette Taku Kareem A. Wahid Lisanne V. van Dijk Jaakko Sahlsten Joel Jaskari Kimmo Kaski Clifton D. Fuller Mohamed A. Naser Auto-detection and segmentation of involved lymph nodes in HPV-associated oropharyngeal cancer using a convolutional deep learning neural network Clinical and Translational Radiation Oncology |
| title | Auto-detection and segmentation of involved lymph nodes in HPV-associated oropharyngeal cancer using a convolutional deep learning neural network |
| title_full | Auto-detection and segmentation of involved lymph nodes in HPV-associated oropharyngeal cancer using a convolutional deep learning neural network |
| title_fullStr | Auto-detection and segmentation of involved lymph nodes in HPV-associated oropharyngeal cancer using a convolutional deep learning neural network |
| title_full_unstemmed | Auto-detection and segmentation of involved lymph nodes in HPV-associated oropharyngeal cancer using a convolutional deep learning neural network |
| title_short | Auto-detection and segmentation of involved lymph nodes in HPV-associated oropharyngeal cancer using a convolutional deep learning neural network |
| title_sort | auto detection and segmentation of involved lymph nodes in hpv associated oropharyngeal cancer using a convolutional deep learning neural network |
| url | http://www.sciencedirect.com/science/article/pii/S2405630822000520 |
| work_keys_str_mv | AT nicolettetaku autodetectionandsegmentationofinvolvedlymphnodesinhpvassociatedoropharyngealcancerusingaconvolutionaldeeplearningneuralnetwork AT kareemawahid autodetectionandsegmentationofinvolvedlymphnodesinhpvassociatedoropharyngealcancerusingaconvolutionaldeeplearningneuralnetwork AT lisannevvandijk autodetectionandsegmentationofinvolvedlymphnodesinhpvassociatedoropharyngealcancerusingaconvolutionaldeeplearningneuralnetwork AT jaakkosahlsten autodetectionandsegmentationofinvolvedlymphnodesinhpvassociatedoropharyngealcancerusingaconvolutionaldeeplearningneuralnetwork AT joeljaskari autodetectionandsegmentationofinvolvedlymphnodesinhpvassociatedoropharyngealcancerusingaconvolutionaldeeplearningneuralnetwork AT kimmokaski autodetectionandsegmentationofinvolvedlymphnodesinhpvassociatedoropharyngealcancerusingaconvolutionaldeeplearningneuralnetwork AT cliftondfuller autodetectionandsegmentationofinvolvedlymphnodesinhpvassociatedoropharyngealcancerusingaconvolutionaldeeplearningneuralnetwork AT mohamedanaser autodetectionandsegmentationofinvolvedlymphnodesinhpvassociatedoropharyngealcancerusingaconvolutionaldeeplearningneuralnetwork |