Abstract
Purpose
To evaluate deep learning–based segmentation models for oropharyngeal squamous cell carcinoma (OPSCC) using CT and MRI with nnU-Net.
Methods
This single-center retrospective study included 91 patients with OPSCC. The patients were grouped into the development (n = 56), test 1 (n = 13), and test 2 (n = 22) cohorts. In the development cohort, OPSCC was manually segmented on CT, MR, and co-registered CT-MR images, which served as the ground truth. The multimodal and multichannel input images were then trained using a self-configuring nnU-Net. For evaluation metrics, dice similarity coefficient (DSC) and mean Hausdorff distance (HD) were calculated for test cohorts. Pearson’s correlation and Bland–Altman analyses were performed between ground truth and prediction volumes. Intraclass correlation coefficients (ICCs) of radiomic features were calculated for reproducibility assessment.
Results
All models achieved robust segmentation performances with DSC of 0.64 ± 0.33 (CT), 0.67 ± 0.27 (MR), and 0.65 ± 0.29 (CT-MR) in test cohort 1 and 0.57 ± 0.31 (CT), 0.77 ± 0.08 (MR), and 0.73 ± 0.18 (CT-MR) in test cohort 2. No significant differences were found in DSC among the models. HD of CT-MR (1.57 ± 1.06 mm) and MR models (1.36 ± 0.61 mm) were significantly lower than that of the CT model (3.48 ± 5.0 mm) (p = 0.037 and p = 0.014, respectively). The correlation coefficients between the ground truth and prediction volumes for CT, MR, and CT-MR models were 0.88, 0.93, and 0.9, respectively. MR models demonstrated excellent mean ICCs of radiomic features (0.91–0.93).
Conclusion
The self-configuring nnU-Net demonstrated reliable and accurate segmentation of OPSCC on CT and MRI. The multimodal CT-MR model showed promising results for the simultaneous segmentation on CT and MRI.
Clinical relevance statement
Deep learning–based automatic detection and segmentation of oropharyngeal squamous cell carcinoma on pre-treatment CT and MRI would facilitate radiologic response assessment and radiotherapy planning.
Key Points
• The nnU-Net framework produced a reliable and accurate segmentation of OPSCC on CT and MRI.
• MR and CT-MR models showed higher DSC and lower Hausdorff distance than the CT model.
• Correlation coefficients between the ground truth and predicted segmentation volumes were high in all the three models.
Similar content being viewed by others
Abbreviations
- 2D:
-
Two-dimensional
- 3D:
-
Three-dimensional
- DL:
-
Deep learning
- DSC:
-
Dice similarity coefficient
- HPV:
-
Human papillomavirus
- OPSCC:
-
Oropharyngeal squamous cell carcinoma
- T1CE:
-
Fat-suppressed contrast-enhanced T1-weighted images
- T2WI:
-
T2-weighted images
References
Weatherspoon DJ, Chattopadhyay A, Boroumand S, Garcia I (2015) Oral cavity and oropharyngeal cancer incidence trends and disparities in the United States: 2000–2010. Cancer Epidemiol 39:497–504
Gormley M, Creaney G, Schache A, Ingarfield K, Conway DI (2022) Reviewing the epidemiology of head and neck cancer: definitions, trends and risk factors. Br Dent J 233:780–786
de Almeida JR, Li R, Magnuson JS et al (2015) Oncologic outcomes after transoral robotic surgery: a multi-institutional study. JAMA Otolaryngol Head Neck Surg 141:1043–1051
Forastiere AA, Zhang Q, Weber RS et al (2013) Long-term results of RTOG 91–11: a comparison of three nonsurgical treatment strategies to preserve the larynx in patients with locally advanced larynx cancer. J Clin Oncol 31:845
Eisbruch A, Harris J, Garden AS et al (2010) Multi-institutional trial of accelerated hypofractionated intensity-modulated radiation therapy for early-stage oropharyngeal cancer (RTOG 00–22). Int J Radiat Oncol Biol Phys 76:1333–1338
Urban D, Corry J, Rischin D (2014) What is the best treatment for patients with human papillomavirus–positive and –negative oropharyngeal cancer? Cancer 120:1462–1470
Tajbakhsh N, Jeyaseelan L, Li Q, Chiang JN, Wu Z, Ding X (2020) Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation. Med Image Anal 63:101693
Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein KH (2021) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18:203–211
Huo L, Hu X, Xiao Q, Gu Y, Chu X, Jiang L (2021) Segmentation of whole breast and fibroglandular tissue using nnU-Net in dynamic contrast enhanced MR images. Magn Reson Imaging 82:31–41
Lin D, Wang Z, Li H et al (2023) Automated measurement of pancreatic fat deposition on Dixon MRI using nnU-Net. J Magn Reson Imaging 57:296–307
Theis M, Tonguc T, Savchenko O et al (2023) Deep learning enables automated MRI-based estimation of uterine volume also in patients with uterine fibroids undergoing high-intensity focused ultrasound therapy. Insights Imaging 14:1
Kang H, Witanto JN, Pratama K et al (2023) Fully automated MRI segmentation and volumetric measurement of intracranial meningioma using deep learning. J Magn Reson Imaging 57:871–881. https://doi.org/10.1002/jmri.28332
Wennmann M, Neher P, Stanczyk N et al (2023) Deep learning for automatic bone marrow apparent diffusion coefficient measurements from whole-body magnetic resonance imaging in patients with multiple myeloma: a retrospective multicenter study. Investig Radiol 58:273–282. https://doi.org/10.1097/RLI.0000000000000932
Heidenreich JF, Gassenmaier T, Ankenbrand MJ, Bley TA, Wech T (2021) Self-configuring nnU-net pipeline enables fully automatic infarct segmentation in late enhancement MRI after myocardial infarction. Eur J Radiol 141:109817
Kok YE, Pszczolkowski S, Law ZK et al (2022) Semantic segmentation of spontaneous intracerebral hemorrhage, intraventricular hemorrhage, and associated edema on CT images using deep learning. Radiol Artif Intell 4:e220096
Dot G, Schouman T, Dubois G, Rouch P, Gajny L (2022) Fully automatic segmentation of craniomaxillofacial CT scans for computer-assisted orthognathic surgery planning using the nnU-Net framework. Eur Radiol 32:3639–3648
Cardenas CE, McCarroll RE, Court LE et al (2018) Deep learning algorithm for auto-delineation of high-risk oropharyngeal clinical target volumes with built-in dice similarity coefficient parameter optimization function. Int J Radiat Oncol Biol Phys 101:468–478
Kihara S, Koike Y, Takegawa H et al (2022) Clinical target volume segmentation based on gross tumor volume using deep learning for head and neck cancer treatment. Med Dosim 48:20–24. https://doi.org/10.1016/j.meddos.2022.09.004
Wahid KA, Ahmed S, He R et al (2022) Evaluation of deep learning-based multiparametric MRI oropharyngeal primary tumor auto-segmentation and investigation of input channel effects: results from a prospective imaging registry. Clin Transl Radiat Oncol 32:6–14
Rodríguez Outeiral R, Bos P, Al-Mamgani A, Jasperse B, Simões R, van der Heide UA (2021) Oropharyngeal primary tumor segmentation for radiotherapy planning on magnetic resonance imaging using deep learning. Phys Imaging Radiat Oncol 19:39–44
Li X, Morgan PS, Ashburner J, Smith J, Rorden C (2016) The first step for neuroimaging data analysis: DICOM to NIfTI conversion. J Neurosci Methods 264:47–56
Avants BB, Tustison N, Song G (2009) Advanced normalization tools (ANTS). Insight J 2:1–35
Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26:297–302
Aydin OU, Taha AA, Hilbert A et al (2021) On the usage of average Hausdorff distance for segmentation performance assessment: hidden error when used for ranking. Eur Radiol Exp 5:1–7
Savjani R (2021) nnU-Net: further automating biomedical image autosegmentation. Radiol Imaging Cancer 3:e209039
El-Hariri H, SoutoMaior Neto LA, Cimflova P et al (2022) Evaluating nnU-Net for early ischemic change segmentation on non-contrast computed tomography in patients with acute ischemic stroke. Comput Biol Med 141:105033
Cimflova P, Ospel JM, Marko M, Menon BK, Qiu W (2022) Variability assessment of manual segmentations of ischemic lesion volume on 24-h non-contrast CT. Neuroradiology 64:1165–1173
Chung KJ, Kuang H, Federico A et al (2021) Semi-automatic measurement of intracranial hemorrhage growth on non-contrast CT. Int J Stroke 16:192–199
Hodneland E, Dybvik JA, Wagner-Larsen KS et al (2021) Automated segmentation of endometrial cancer on MR images using deep learning. Sci Rep 11:1–8
Blinde S, Mohamed ASR, Al-Mamgani A et al (2017) Large interobserver variation in the International MR-LINAC Oropharyngeal Carcinoma Delineation Study. Int J Radiat Oncol Biol Phys 99:E639–E640
Moe YM, Groendahl AR, Tomic O, Dale E, Malinen E, Futsaether CM (2021) Deep learning-based auto-delineation of gross tumour volumes and involved nodes in PET/CT images of head and neck cancer patients. Eur J Nucl Med Mol Imaging 48:2782–2792
Bielak L, Wiedenmann N, Berlin A et al (2020) Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis. Radiat Oncol 15:1–9
Ren J, Eriksen JG, Nijkamp J, Korreman SS (2021) Comparing different CT, PET and MRI multi-modality image combinations for deep learning-based head and neck tumor segmentation. Acta Oncol 60:1399–1406
Shiga K, Ogawa T, Katagiri K et al (2012) Differences between oral cancer and cancers of the pharynx and larynx on a molecular level. Oncol Lett 3:238–243
Argiris A, Karamouzis MV, Raben D, Ferris RL (2008) Head and neck cancer. Lancet 371:1695–1709
Arshad M, Hara J, Rosenberg AJ et al (2022) Assessment of tumor burden and response by RECIST vs. volume change in HPV+ oropharyngeal cancer – an exploratory analysis of prospective trials. Int J Radiat Oncol Biol Phys 114:S113–S114
Choi Y, Nam Y, Jang J et al (2020) Prediction of human papillomavirus status and overall survival in patients with untreated oropharyngeal squamous cell carcinoma: development and validation of CT-based radiomics. Am J Neuroradiol 41:1897–1904
Min Park Y, Yol Lim J, Woo Koh Y, Kim S-H, Chang Choi E (2021) Prediction of treatment outcome using MRI radiomics and machine learning in oropharyngeal cancer patients after surgical treatment. Oral Oncol 122:105559
Wang P, Wang X, Zhang M, Li G, Zhao N, Qiao Q (2022) Combining the radiomics signature and HPV status for the risk stratification of patients with OPC. Oral Dis (Early View). https://doi.org/10.1111/odi.14386
Song B, Yang K, Garneau J et al (2021) Radiomic features associated with HPV status on pretreatment computed tomography in oropharyngeal squamous cell carcinoma inform clinical prognosis. Front Oncol 11:744250
Funding
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2021R1I1A1A01040285).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Guarantor
The scientific guarantor of this publication is Yangsean Choi.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Statistics and biometry
No complex statistical methods were necessary for this paper.
Informed consent
Written informed consent was not required for this study because of the retrospective study design.
Ethical approval
Institutional Review Board approval was obtained.
Study subjects or cohorts overlap
No study subjects or cohorts have been previously reported.
Methodology
• retrospective
• cross-sectional study
• performed at one institution
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Choi, Y., Bang, J., Kim, SY. et al. Deep learning–based multimodal segmentation of oropharyngeal squamous cell carcinoma on CT and MRI using self-configuring nnU-Net. Eur Radiol (2024). https://doi.org/10.1007/s00330-024-10585-y
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00330-024-10585-y