A preliminary application of intraoral Doppler ultrasound images to deep learning techniques for predicting late cervical lymph node metastasis in early tongue cancers
Corresponding Author
Yoshiko Ariji
Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Correspondence
Yoshiko Ariji, Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, 2-11 Suemori-dori, Chikusa-ku, Nagoya 464-8651, Japan.
Email: [email protected]
Search for more papers by this authorMotoki Fukuda
Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorYoshitaka Kise
Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorMichihito Nozawa
Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorToru Nagao
Department of Maxillofacial Surgery, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorAtsushi Nakayama
Department of Oral and Maxillofacial Surgery, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorYoshihiko Sugita
Department of Oral Pathology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorAkitoshi Katumata
Department of Oral Radiology, Asahi University School of Dentistry, Mizuho, Japan
Search for more papers by this authorEiichiro Ariji
Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorCorresponding Author
Yoshiko Ariji
Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Correspondence
Yoshiko Ariji, Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, 2-11 Suemori-dori, Chikusa-ku, Nagoya 464-8651, Japan.
Email: [email protected]
Search for more papers by this authorMotoki Fukuda
Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorYoshitaka Kise
Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorMichihito Nozawa
Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorToru Nagao
Department of Maxillofacial Surgery, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorAtsushi Nakayama
Department of Oral and Maxillofacial Surgery, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorYoshihiko Sugita
Department of Oral Pathology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorAkitoshi Katumata
Department of Oral Radiology, Asahi University School of Dentistry, Mizuho, Japan
Search for more papers by this authorEiichiro Ariji
Department of Oral and Maxillofacial Radiology, Aichi-Gakuin University School of Dentistry, Nagoya, Japan
Search for more papers by this authorAbstract
Aims
Various factors, including depth of invasion (DOI) and hemodynamics have been linked with the prediction of late cervical lymph nodes metastasis in patients with early tongue cancers. The objective of this study was to examine the deep learning performance of the intraoral Doppler ultrasound images for predicting the late cervical metastasis, by comparing DOI.
Methods
Thirty-three patients with early squamous cell tongue carcinomas were divided into two groups: 12 with late cervical metastasis, and 21 without metastasis. Intraoral Doppler ultrasound images of all subjects were cropped to 400 × 400 pixel squares, and 80% were used for a training dataset, and 20% were used for a testing dataset. The training dataset was imported into the DIGITS deep learning training system, the learning process for 300 epochs was performed using AlexNet neural network, and the resultant learning model was created. The testing dataset was applied to the model to evaluate the performance for distinguishing between the two groups.
Results
Use of intraoral Doppler ultrasound images for predicting the late cervical metastasis achieved deep learning performances of 0.883 for the area under the ROC curve (AUC), 85.9% for accuracy, and 84.0% for sensitivity. On the other hand, the corresponding performances of DOI were 0.873, 84.8%, and 75.0%, using a DOI threshold of 5.6 mm.
Conclusion
Our findings suggested that the performance of a deep learning system using intraoral Doppler ultrasound images of early tongue cancers to predict late cervical metastasis was sufficiently high, suggesting possible applications in imaging diagnosis support.
CONFLICT OF INTEREST
Yoshiko Ariji, Motoki Fukuda, Yoshitaka Kise, Michihito Nozawa, Toru Nagao, Atsushi Nakayama, Yoshihiko Sugita, Akitoshi Katumata, and Eiichiro Ariji declare that they have no conflict of interest.
REFERENCES
- 1Pimenta Amaral TM, Da Silva Freire AR, Carvalho AL, Pinto CA, Kowalski LP. Predictive factors of occult metastasis and prognosis of clinical stages I and II squamous cell carcinoma of the tongue and floor of the mouth. Oral Oncol. 2004; 40: 780–6.
- 2Okamoto M, Nishimine M, Kishi M, Kirita T, Sugimura M, Nakamura M, et al. Prediction of delayed neck metastasis in patients with stage I/II squamous cell carcinoma of the tongue. J Oral Pathol Med. 2002; 31: 227–33.
- 3Akhtar S, Ikram M, Ghaffar S. Neck involvement in early carcinoma of tongue. Is elective neck dissection warranted? J Pak Med Assoc. 2007; 57: 305–7.
- 4Kaya S, Yilmaz T, Gürsel B, Saraç S, Sennaroğlu L. The value of elective neck dissection in treatment of cancer of the tongue. Am J Otolaryngol. 2001; 22: 59–64.
- 5Kligerman J, Lima RA, Soares JR, Prado L, Dias FL, Freitas EQ, et al. Supraomohyoid neck dissection in the treatment of T1/T2 squamous cell carcinoma of oral cavity. Am J Surg. 1994; 168: 391–4.
- 6Lydiatt DD, Robbins KT, Byers RM, Wolf PF. Treatment of stage I and II oral tongue cancer. Head Neck. 1993; 15: 308–12.
- 7Ho CM, Lam KH, Wei WI, Lau SK, Lam LK. Occult lymph node metastasis in small oral tongue cancers. Head Neck. 1992; 14: 359–63.
- 8Pentenero M, Gandolfo S, Carrozzo M. Importance of tumor thickness and depth of invasion in nodal involvement and prognosis of oral squamous cell carcinoma: a review of the literature. Head Neck. 2005; 27: 1080–91.
- 9Lim SC, Zhang S, Ishii G, Endoh Y, Kodama K, Miyamoto S, et al. Predictive markers for late cervical metastasis in stage I and II invasive squamous cell carcinoma of the oral tongue. Clin Cancer Res. 2004; 10: 166–72.
- 10Furusawa J, Oridate N, Suzuki F, Homma A, Furuta Y, Fukuda S. Initial CT findings in early tongue and oral floor cancer as predictors of late neck metastasis. Oral Oncol. 2008; 44: 793–7.
- 11Imai T, Satoh I, Matsumoto K, Asada Y, Yamazaki T, Morita S, et al. Retrospective observational study of occult cervical lymph-node metastasis in T1N0 tongue cancer. Jpn J Clin Oncol. 2017; 47: 130–6.
- 12Hayashi T, Ito J, Taira S, Katsura K. The relationship of primary tumor thickness in carcinoma of the tongue to subsequent lymph node metastasis. Dentomaxillofac Radiol. 2001; 30: 242–5.
- 13Karakida K, Ota Y, Aoki T, Yamazaki H, Tsukinoki K. Examination of factors predicting occult metastasis of the cervical lymph nodes in T1 and T2 tongue carcinoma. Tokai J Exp Clin Med. 2002; 27: 65–71.
- 14Ariji Y, Goto M, Fukano H, Sugita Y, Izumi M, Ariji E. Role of intraoral color Doppler sonography in predicting delayed cervical lymph node metastasis in patients with early-stage tongue cancer: a pilot study. Oral Surg Oral Med Oral Pathol Oral Radiol. 2015; 119: 246–53.
- 15Goto M, Hasegawa Y, Terada A, Hyodo I, Hanai N, Ijichi K, et al. Prognostic significance of late cervical metastasis and distant failure in patients with stage I and II oral tongue cancers. Oral Oncol. 2005; 41: 62–9.
- 16O-charoenrat P, Pillai G, Patel S, Fisher C, Archer D, Eccles S, et al. Tumour thickness predicts cervical nodal metastases and survival in early oral tongue cancer. Oral Oncol. 2003; 39: 386–90.
- 17Kurokawa H, Yamashita Y, Takeda S, Zhang M, Fukuyama H, Takahashi T. Risk factors for late cervical lymph node metastases in patients with stage I or II carcinoma of the tongue. Head Neck. 2002; 24: 731–6.
- 18Mark Taylor S, Drover C, MacEachern R, Bullock M, Hart R, Psooy B, et al. Is preoperative ultrasonography accurate in measuring tumor thickness and predicting the incidence of cervical metastasis in oral cancer? Oral Oncol. 2010; 46: 38–41.
- 19O'Sullivan B. Head and neck tumours. In: J Brierley, MK Gospodarowicz, C Wittekind, editors. UICC TNM classification of Malignant Tumours, 8th ed. Chichester: Wiley, 2017; p. 17–54.
- 20Amin M, Edge S, Greene F, Schilsky RL, Gaspar LE, Washington MK, et al. AJCC cancer staging manual, 8th edn. New York: Springer, 2017; p. P55–65.
10.1007/978-3-319-40618-3_5 Google Scholar
- 21Spiro RH, Huvos AG, Wong GY, Spiro JD, Gnecco CA, Strong EW. Predictive value of tumor thickness in squamous carcinoma confined to the tongue and floor of the mouth. Am J Surg. 1986; 152: 345–50.
- 22Mao MH, Wang S, Feng ZE, Li JZ, Li H, Qin LZ, et al. Accuracy of magnetic resonance imaging in evaluating the depth of invasion of tongue cancer. A prospective cohort study. Oral Oncol. 2019; 91: 79–84.
- 23Baba A, Okuyama Y, Ikeda K, Kozakai A, Suzuki T, Saito H, et al. Undetectability of oral tongue cancer on magnetic resonance imaging; clinical significance as a predictor to avoid unnecessary elective neck dissection in node negative patients. Dentomaxillofac Radiol. 2019; 48: 20180272.
- 24Murakami R, Shiraishi S, Yoshida R, Sakata J, Yamana K, Hirosue A, et al. Reliability of MRI-derived depth of invasion of oral tongue cancer. Acad Radiol. 2019; 26: e180–e186.
- 25Tarabichi O, Bulbul MG, Kanumuri VV, Faquin WC, Juliano AF, Cunnane ME, et al. Utility of intraoral ultrasound in managing oral tongue squamous cell carcinoma: systematic review. Laryngoscope. 2019; 129: 662–70.
- 26Klein Nulent TJW, Noorlag R, Van Cann EM, Pameijer FA, Willems SM, Yesuratnam A, et al. Intraoral ultrasonography to measure tumor thickness of oral cancer: a systematic review and meta-analysis. Oral Oncol. 2018; 77: 29–36.
- 27Iida Y, Kamijo T, Kusafuka K, Omae K, Nishiya Y, Hamaguchi N, et al. Depth of invasion in superficial oral tongue carcinoma quantified using intraoral ultrasonography. Laryngoscope. 2018; 128: 2778–82.
- 28Yamamoto C, Yuasa K, Okamura K, Shiraishi T, Miwa K. Vascularity as assessed by Doppler intraoral ultrasound around the invasion front of tongue cancer is a predictor of pathological grade of malignancy and cervical lymph node metastasis. Dentomaxillofac Radiol. 2016; 45: 20150372.
- 29Kaneoya A, Hasegawa S, Tanaka Y, Omura K. Quantitative analysis of invasive front in tongue cancer using ultrasonography. J Oral Maxillofac Surg. 2009; 67: 40–6.
- 30Kimura Y, Ariji Y, Gotoh M, Toyoda T, Kato M, Kawamata A, et al. Doppler sonography of the deep lingual artery. Acta Radiol. 2001; 42: 306–11.
- 31Ogura I, Sasaki Y, Sue M, Oda T. Strain elastography of tongue carcinoma using intraoral ultrasonography: a preliminary study to characterize normal tissues and lesions. Imaging Sci Dent. 2018; 48: 45–9.
- 32Zanella-Calzada LA, Galván-Tejada CE, Chávez-Lamas NM, Rivas-Gutierrez J, Magallanes-Quintanar R, Celaya-Padilla JM, et al. Artificial Neural networks for the diagnostic of caries using socioeconomic and nutritional features as determinants: data from NHANES 2013⁻2014. Bioengineering (Basel). 2018; 5: 47. https://doi.org/10.3390/bioengineering5020047
10.3390/bioengineering5020047 Google Scholar
- 33Ekert T, Krois J, Meinhold L, Elhennawy K, Emara R, Golla T, et al. Deep learning for the radiographic detection of apical lesions. J Endod. 2019; 45: 917–922. https://doi.org/10.1016/j.joen.2019.03.016
- 34Lee JH, Kim DH, Jeong SN, Choi SH. Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm. J Periodontal Implant Sci. 2018; 48: 114–23.
- 35Chu P, Bo C, Liang X, Yang J, Megalooikonomou V, Yang F, et al. Using Octuplet Siamese network for osteoporosis analysis on dental panoramic radiographs. Conf Proc IEEE Eng Med Biol Soc. 2018; 2018: 2579–82.
- 36Lee JS, Adhikari S, Liu L, Jeong HG, Kim H, Yoon SJ. Osteoporosis detection in panoramic radiographs using a deep convolutional neural network-based computer-assisted diagnosis system: a preliminary study. Dentomaxillofac Radiol. 2018; 48: 20170344. https://doi.org/10.1259/dmfr.20170344.
- 37Ariji Y, Yanashita Y, Kutsuna S, Muramatsu C, Fukuda M, Kise Y, et al. Automatic detection and classification of radiolucent lesions in the mandible on panoramic radiographs using a deep learning object detection technique. Oral Surg Oral Med Oral Pathol Oral Radiol. 2019; 128: 424–30. https://doi.org/10.1016/j.oooo.2019.05.014.
- 38Tuzoff DV, Tuzova LN, Bornstein MM, Krasnov AS, Kharchenko MA, Nikolenko SI, et al. Tooth detection and numbering in panoramic radiographs using convolutional neural networks. Dentomaxillofac Radiol. 2019; 48: 20180051.
- 39Chen H, Zhang K, Lyu P, Li H, Zhang L, Wu J, et al. A deep learning approach to automatic teeth detection and numbering based on object detection in dental periapical films. Sci Rep. 2019; 9: 3840.
- 40Ariji Y, Fukuda M, Kise Y, Nozawa M, Yanashita Y, Fujita H, et al. Contrast-enhanced computed tomography image assessment of cervical lymph node metastasis in patients with oral cancer by using a deep learning system of artificial intelligence. Oral Surg Oral Med Oral Pathol Oral Radiol. 2019; 127: 458–63.
- 41Ariji Y, Sugita Y, Nagao T, Nakayama A, Fukuda M, Kise Y, et al. CT evaluation of extranodal extension of cervical lymph node metastases in patients with oral squamous cell carcinoma using deep learning classification. Oral Radiol. 2019. https://doi.org/10.1007/s11282-019-00391-4. [Epub ahead of print].
- 42Zhou Z, Chen L, Sher D, Zhang Q, Shah J, Pham NL, et al. Predicting lymph node metastasis in head and neck cancer by combining many-objective radiomics and 3-dimensioal convolutional neural network through evidential reasoning. Conf Proc IEEE Eng Med Biol Soc. 2018; 2018: 1–4.
- 43Kann BH, Aneja S, Loganadane GV, Kelly JR, Smith SM, Decker RH, et al. Pretreatment identification of head and neck cancer nodal metastasis and extranodal extension using deep learning neural networks. Sci Rep. 2018; 8: 14036.
- 44Kise Y, Ikeda H, Fujii T, Fukuda M, Ariji Y, Fujita H, et al. Preliminary study on the application of deep learning system to diagnosis of Sjögren's syndrome on CT images. Dentomaxillofac Radiol. 2019; 48(6): 20190019. https://doi.org/10.1259/dmfr.20190019.
- 45Lin L, Dou Q, Jin YM, Zhou GQ, Tang YQ, Chen WL, et al. Deep learning for automated contouring of primary tumor volumes by MRI for nasopharyngeal carcinoma. Radiology. 2019; 291: 677–86.
- 46Huang B, Chen Z, Wu PM, Ye Y, Feng ST, Wong CO, et al. Fully automated delineation of gross tumor volume for head and neck cancer on PET-CT Using deep learning: a dual-center study. Contrast Media Mol Imaging. 2018; 2018: 8923028.
- 47Tong N, Gou S, Yang S, Ruan D, Sheng K. Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks. Med Phys. 2018; 45: 4558–67.
- 48Aubreville M, Stoeve M, Oetter N, Goncalves M, Knipfer C, Neumann H, et al. Deep learning-based detection of motion artifacts in probe-based confocal laser endomicroscopy images. Int J Comput Assist Radiol Surg. 2019; 14: 31–42.
- 49Guan Q, Wang Y, Du J, Qin Y, Lu H, Xiang J, et al. Deep learning based classification of ultrasound images for thyroid nodules: a large scale of pilot study. Ann Transl Med. 2019; 7: 137.
- 50Chiao JY, Chen KY, Liao KY, Hsieh PH, Zhang G, Huang TC. Detection and classification the breast tumors using mask R-CNN on sonograms. Medicine (Baltimore). 2019; 98:e15200.
- 51Liu X, Song JL, Wang SH, Zhao JW, Chen YQ. Learning to diagnose cirrhosis with liver capsule guided ultrasound image classification. Sensors (Basel). 2017; 17(12): 149. https://doi.org/10.3390/s17010149
10.3390/s17010149 Google Scholar
- 52Yamane M, Ishii J, Izumo T, Nagasawa T, Amagasa T. Noninvasive quantitative assessment of oral tongue cancer by intraoral ultrasonography. Head Neck. 2007; 29: 307–14.
- 53Tseng HS, Wu HK, Chen ST, Kuo SJ, Huang YL, Chen DR. Speckle reduction imaging of breast ultrasound does not improve the diagnostic performance of morphology-based CAD System. J Clin Ultrasound. 2012; 40: 1–6.
Citing Literature
