Abstract
Objectives
In this study, we constructed and validated models based on deep learning and radiomics to facilitate preoperative diagnosis of cervical lymph node metastasis (LNM) using contrast-enhanced computed tomography (CECT).
Materials and methods
CECT scans of 100 patients with OSCC (217 metastatic and 1973 non-metastatic cervical lymph nodes: development set, 76 patients; internally independent test set, 24 patients) who received treatment at the Peking University School and Hospital of Stomatology between 2012 and 2016 were retrospectively collected. Clinical diagnoses and pathological findings were used to establish the gold standard for metastatic cervical LNs. A reader study with two clinicians was also performed to evaluate the lymph node status in the test set. The performance of the proposed models and the clinicians was evaluated and compared by measuring using the area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE).
Results
A fusion model combining deep learning with radiomics showed the best performance (ACC, 89.2%; SEN, 92.0%; SPE, 88.9%; and AUC, 0.950 [95% confidence interval: 0.908–0.993, P < 0.001]) in the test set. In comparison with the clinicians, the fusion model showed higher sensitivity (92.0 vs. 72.0% and 60.0%) but lower specificity (88.9 vs. 97.5% and 98.8%).
Conclusion
A fusion model combining radiomics and deep learning approaches outperformed other single-technique models and showed great potential to accurately predict cervical LNM in patients with OSCC.
Clinical relevance
The fusion model can complement the preoperative identification of LNM of OSCC performed by the clinicians.
Similar content being viewed by others
Data Availability
The data that support the findings of this study are available from the corresponding author upon reasonable request.
References
Funk GF, Karnell LH, Robinson RA, Zhen WK, Trask DK, Hoffman HT (2002) Presentation, treatment, and outcome of oral cavity cancer: a National Cancer Data Base report. Head Neck 24:165–180. https://doi.org/10.1002/hed.10004
Shield KD, Ferlay J, Jemal A, Sankaranarayanan R, Chaturvedi AK, Bray F, Soerjomataram I (2017) The global incidence of lip, oral cavity, and pharyngeal cancers by subsite in 2012. CA Cancer J Clin 67:51–64. https://doi.org/10.3322/caac.21384
Amit M, Yen TC, Liao CT, Binenbaum Y, Chaturvedi P, Agarwal JP, Kowalski LP, Ebrahimi A, Clark JR, Cernea CR, Brandao SJ, Kreppel M, Zöller J, Fliss D, Bachar G, Shpitzer T, Bolzoni VA, Patel PR, Jonnalagadda S, Robbins KT, Shah JP, Patel SG, Gil Z (2013) Clinical nodal stage is a significant predictor of outcome in patients with oral cavity squamous cell carcinoma and pathologically negative neck metastases: results of the international consortium for outcome research. Ann Surg Oncol 20:3575–3581. https://doi.org/10.1245/s10434-013-3044-0
Forghani R, Yu E, Levental M, Som PM, Curtin HD (2015) Imaging evaluation of lymphadenopathy and patterns of lymph node spread in head and neck cancer. Expert Rev Anticancer Ther 15:207–224. https://doi.org/10.1586/14737140.2015.978862
Kelly HR, Curtin HD (2017) Chapter 2 Squamous cell carcinoma of the head and neck-imaging evaluation of regional lymph nodes and implications for management. Semin Ultrasound CT MR 38:466–478. https://doi.org/10.1053/j.sult.2017.05.003
Lee CS, Nagy PG, Weaver SJ, Newman-Toker DE (2013) Cognitive and system factors contributing to diagnostic errors in radiology. AJR Am J Roentgenol 201:611–617. https://doi.org/10.2214/ajr.12.10375
McDonald RJ, Schwartz KM, Eckel LJ, Diehn FE, Hunt CH, Bartholmai BJ, Erickson BJ, Kallmes DF (2015) The effects of changes in utilization and technological advancements of cross-sectional imaging on radiologist workload. Acad Radiol 22:1191–1198. https://doi.org/10.1016/j.acra.2015.05.007
Wang Y, Yan F, Lu X, Zheng G, Zhang X, Wang C, Zhou K, Zhang Y, Li H, Zhao Q, Zhu H, Chen F, Gao C, Qing Z, Ye J, Li A, Xin X, Li D, Wang H, Yu H, Cao L, Zhao C, Deng R, Tan L, Chen Y, Yuan L, Zhou Z, Yang W, Shao M, Dou X, Zhou N, Zhou F, Zhu Y, Lu G, Zhang B (2019) IILS: Intelligent imaging layout system for automatic imaging report standardization and intra-interdisciplinary clinical workflow optimization. EBioMedicine 44:162–181. https://doi.org/10.1016/j.ebiom.2019.05.040
Chen X, Xu H, Qi Q, Sun C, Jin J, Zhao H, Wang X, Weng W, Wang S, Sui X, Wang Z, Dai C, Peng M, Wang D, Hao Z, Huang Y, Wang X, Duan L, Zhu Y, Hong N, Yang F (2022) AI-based chest CT semantic segmentation algorithm enables semi-automated lung cancer surgery planning by recognizing anatomical variants of pulmonary vessels. Front Oncol 12:1021084. https://doi.org/10.3389/fonc.2022.1021084
Dong D, Luo Z, Zheng Y, Liang Y, Zhao P, Feng L, Wang D, Cao Y, Zhao Z, Ma Y (2022) Application of deep learning-based diagnostic systems in screening asymptomatic COVID-19 patients among oversea returnees. J Infect Dev Ctries 16:1706–1714. https://doi.org/10.3855/jidc.15022
Fan L, Li J, Zhang H, Yin H, Zhang R, Zhang J, Chen X (2022) Machine learning analysis for the noninvasive prediction of lymphovascular invasion in gastric cancer using PET/CT and enhanced CT-based radiomics and clinical variables. Abdom Radiol (NY) 47:1209–1222. https://doi.org/10.1007/s00261-021-03315-1
Wong AJ, Kanwar A, Mohamed AS, Fuller CD (2016) Radiomics in head and neck cancer: from exploration to application. Transl Cancer Res 5:371–382. https://doi.org/10.21037/tcr.2016.07.18
Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout R, Granton P, Zegers C, Gillies R, Boellard R, Dekker A, Aerts H (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer (Oxford, England : 1990) 48:441–446. https://doi.org/10.1016/j.ejca.2011.11.036
Gillies R, Kinahan P, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577. https://doi.org/10.1148/radiol.2015151169
Ou J, Wu L, Li R, Wu CQ, Liu J, Chen TW, Zhang XM, Tang S, Wu YP, Yang LQ, Tan BG, Lu FL (2021) CT radiomics features to predict lymph node metastasis in advanced esophageal squamous cell carcinoma and to discriminate between regional and non-regional lymph node metastasis: a case control study. Quant Imaging Med Surg 11:628–640. https://doi.org/10.21037/qims-20-241
Wu S, Zheng J, Li Y, Yu H, Shi S, Xie W, Liu H, Su Y, Huang J, Lin T (2017) A radiomics nomogram for the preoperative prediction of lymph node metastasis in bladder cancer. Clin Cancer Res 23:6904–6911. https://doi.org/10.1158/1078-0432.Ccr-17-1510
Huang YQ, Liang CH, He L, Tian J, Liang CS, Chen X, Ma ZL, Liu ZY (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 34:2157–2164. https://doi.org/10.1200/jco.2015.65.9128
Tran KA, Kondrashova O, Bradley A, Williams ED, Pearson JV, Waddell N (2021) Deep learning in cancer diagnosis, prognosis and treatment selection. Genome Med 13:152. https://doi.org/10.1186/s13073-021-00968-x
Kleppe A, Skrede OJ, De Raedt S, Liestøl K, Kerr DJ, Danielsen HE (2021) Designing deep learning studies in cancer diagnostics. Nat Rev Cancer 21:199–211. https://doi.org/10.1038/s41568-020-00327-9
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539
Ariji Y, Fukuda M, Nozawa M, Kuwada C, Goto M, Ishibashi K, Nakayama A, Sugita Y, Nagao T, Ariji E (2021) Automatic detection of cervical lymph nodes in patients with oral squamous cell carcinoma using a deep learning technique: a preliminary study. Oral Radiol 37:290–296. https://doi.org/10.1007/s11282-020-00449-8
Tomita H, Yamashiro T, Heianna J, Nakasone T, Kobayashi T, Mishiro S, Hirahara D, Takaya E, Mimura H, Murayama S, Kobayashi Y (2021) Deep learning for the preoperative diagnosis of metastatic cervical lymph nodes on contrast-enhanced computed toMography in patients with oral squamous cell carcinoma. Cancers (Basel) 13:600. https://doi.org/10.3390/cancers13040600
Tomita H, Yamashiro T, Heianna J, Nakasone T, Kimura Y, Mimura H, Murayama S (2021) Nodal-based radiomics analysis for identifying cervical lymph node metastasis at levels I and II in patients with oral squamous cell carcinoma using contrast-enhanced computed tomography. Eur Radiol 31:7440–7449. https://doi.org/10.1007/s00330-021-07758-4
Antropova N, Huynh BQ, Giger ML (2017) A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets. Med Phys 44:5162–5171. https://doi.org/10.1002/mp.12453
Zhou Z, Chen L, Sher D, Zhang Q, Shah J, Pham NL, Jiang S, Wang J (2018) Predicting lymph node metastasis in head and neck cancer by combining many-objective radiomics and 3-dimensional convolutional neural network through evidential reasoning. Annu Int Conf IEEE Eng Med Biol Soc 2018:1–4. https://doi.org/10.1109/embc.2018.8513070
Wang X, Chen K, Wang W, Li Q, Liu K, Li Q, Cui X, Tu W, Sun H, Xu S, Zhang R, Xiao Y, Fan L, Liu S (2021) Can peritumoral regions increase the efficiency of machine-learning prediction of pathological invasiveness in lung adenocarcinoma manifesting as ground-glass nodules? J Thorac Dis 13:1327–1337. https://doi.org/10.21037/jtd-20-2981
Caudell JJ, Gillison ML, Maghami E, Spencer S, Pfister DG, Adkins D, Birkeland AC, Brizel DM, Busse PM, Cmelak AJ, Colevas AD, Eisele DW, Galloway T, Geiger JL, Haddad RI, Hicks WL, Hitchcock YJ, Jimeno A, Leizman D, Mell LK, Mittal BB, Pinto HA, Rocco JW, Rodriguez CP, Savvides PS, Schwartz D, Shah JP, Sher D, St John M, Weber RS, Weinstein G, Worden F, Yang Bruce J, Yom SS, Zhen W, Burns JL, Darlow SD (2022) NCCN guidelines® insights: head and neck cancers, Version 1.2022. J Natl Compr Canc Netw 20:224–234. https://doi.org/10.6004/jnccn.2022.0016
Moeckelmann N, Ebrahimi A, Tou YK, Gupta R, Low TH, Ashford B, Ch’ng S, Palme CE, Clark JR (2018) Prognostic implications of the 8th edition American Joint Committee on Cancer (AJCC) staging system in oral cavity squamous cell carcinoma. Oral Oncol 85:82–86. https://doi.org/10.1016/j.oraloncology.2018.08.013
Sarradin V, Siegfried A, Uro-Coste E, Delord JP (2018) WHO classification of head and neck tumours 2017: main novelties and update of diagnostic methods. Bull Cancer 105:596–602. https://doi.org/10.1016/j.bulcan.2018.04.004
van den Brekel MW, Stel HV, Castelijns JA, Nauta JJ, van der Waal I, Valk J, Meyer CJ, Snow GB (1990) Cervical lymph node metastasis: assessment of radiologic criteria. Radiology 177:379–384. https://doi.org/10.1148/radiology.177.2.2217772
Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143:29–36. https://doi.org/10.1148/radiology.143.1.7063747
Oh LJ, Phan K, Kim SW, Low TH, Gupta R, Clark JR (2020) Elective neck dissection versus observation for early-stage oral squamous cell carcinoma: Systematic review and meta-analysis. Oral Oncol 105:104661. https://doi.org/10.1016/j.oraloncology.2020.104661
Pandeshwar P, Jayanthi K, Raghuram P (2013) Pre-operative contrast enhanced computer tomographic evaluation of cervical nodal metastatic disease in oral squamous cell carcinoma. Indian J Cancer 50:310–315. https://doi.org/10.4103/0019-509x.123605
Alabi RO, Youssef O, Pirinen M, Elmusrati M, Mäkitie AA, Leivo I, Almangush A (2021) Machine learning in oral squamous cell carcinoma: current status, clinical concerns and prospects for future-a systematic review. Artif Intell Med 115:102060. https://doi.org/10.1016/j.artmed.2021.102060
Santer M, Kloppenburg M, Gottfried TM, Runge A, Schmutzhard J, Vorbach SM, Mangesius J, Riedl D, Mangesius S, Widmann G, Riechelmann H, Dejaco D, Freysinger W (2022) Current applications of artificial intelligence to classify cervical lymph nodes in patients with head and neck squamous cell carcinoma-a systematic review. Cancers (Basel) 14:5397. https://doi.org/10.3390/cancers14215397
Xu X, Xi L, Wei L, Wu L, Xu Y, Liu B, Li B, Liu K, Hou G, Lin H, Shao Z, Su K, Shang Z (2022) Deep learning assisted contrast-enhanced CT-based diagnosis of cervical lymph node metastasis of oral cancer: a retrospective study of 1466 cases. Eur Radiol 33:4303–4312. https://doi.org/10.1007/s00330-022-09355-5
Rani G, Oza MG, Dhaka VS, Pradhan N, Verma S, Rodrigues J (2022) Applying deep learning-based multi-modal for detection of coronavirus. Multimed Syst 28:1251–1262. https://doi.org/10.1007/s00530-021-00824-3
Pahuja G, Prasad B (2022) Deep learning architectures for Parkinson’s disease detection by using multi-modal features. Comput Biol Med 146:105610. https://doi.org/10.1016/j.compbiomed.2022.105610
Xu F, Lou K, Chen C, Chen Q, Wang D, Wu J, Zhu W, Tan W, Zhou Y, Liu Y, Wang B, Zhang X, Zhang Z, Zhang J, Sun M, Zhang G, Dai G, Hu H (2022) An original deep learning model using limited data for COVID-19 discrimination: a multicenter study. Med Phys 49:3874–3885. https://doi.org/10.1002/mp.15549
Acknowledgements
We would like to thank Dawei Wang and Weixiong Tan of Huafang Hanying Medical Technology Co., Ltd (Beijing, PR China) for artificial intelligence modeling technical support, and we also thank the native English speaking scientists of Elixigen Company (Huntington Beach, California) for editing our manuscript.
Funding
This work was supported by Program of the new clinical techniques of Peking University School and Hospital of Stomatology [Grant Number: PKUSSNCT-20A05].
Author information
Authors and Affiliations
Contributions
Zhen Chen, Wenbo Zhang, and Xin Peng contributed to the conception and design of the study. Yao Yu, Shuo Liu, Congwei Wang, and Jiaqi Li collected the data and performed the statistical analysis. Jianbo Liu, Wen Du, and Leihao Hu performed the literature search and interpretation of data collected. Zhen Chen performed drafting of article and critical revision. All authors have approved the final version to be published.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
The study was reviewed and approved by the Institutional Review Board of Peking University School of Stomatology. All procedures performed were in accordance with the 1964 Declaration of Helsinki and its later amendments or comparable ethical standards.
Informed consent
For this type of study, formal consent is not required.
Conflict of interest
The authors declare no competing interests.
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
Chen, Z., Yu, Y., Liu, S. et al. A deep learning and radiomics fusion model based on contrast-enhanced computer tomography improves preoperative identification of cervical lymph node metastasis of oral squamous cell carcinoma. Clin Oral Invest 28, 39 (2024). https://doi.org/10.1007/s00784-023-05423-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00784-023-05423-2