Imaging Science in Dentistry

Korean Academy of Oral and Maxillofacial Radiology (대한영상치의학회)
권호 표지
DOI QR코드

DOI QR Code

Effect of deep transfer learning with a different kind of lesion on classification performance of pre-trained model: Verification with radiolucent lesions on panoramic radiographs

  • Yoshitaka Kise (Department of Oral and Maxillofacial Radiology, Aichi Gakuin University School of Dentistry) ;
  • Yoshiko Ariji (Department of Oral Radiology, Osaka Dental University) ;
  • Chiaki Kuwada (Department of Oral and Maxillofacial Radiology, Aichi Gakuin University School of Dentistry) ;
  • Motoki Fukuda (Department of Oral and Maxillofacial Radiology, Aichi Gakuin University School of Dentistry) ;
  • Eiichiro Ariji (Department of Oral and Maxillofacial Radiology, Aichi Gakuin University School of Dentistry)
  • Received : 2022.07.25
  • Accepted : 2022.10.31
  • Published : 2023.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: The aim of this study was to clarify the influence of training with a different kind of lesion on the performance of a target model. Materials and Methods: A total of 310 patients(211 men, 99 women; average age, 47.9±16.1 years) were selected and their panoramic images were used in this study. We created a source model using panoramic radiographs including mandibular radiolucent cyst-like lesions (radicular cyst, dentigerous cyst, odontogenic keratocyst, and ameloblastoma). The model was simulatively transferred and trained on images of Stafne's bone cavity. A learning model was created using a customized DetectNet built in the Digits version 5.0 (NVIDIA, Santa Clara, CA). Two machines(Machines A and B) with identical specifications were used to simulate transfer learning. A source model was created from the data consisting of ameloblastoma, odontogenic keratocyst, dentigerous cyst, and radicular cyst in Machine A. Thereafter, it was transferred to Machine B and trained on additional data of Stafne's bone cavity to create target models. To investigate the effect of the number of cases, we created several target models with different numbers of Stafne's bone cavity cases. Results: When the Stafne's bone cavity data were added to the training, both the detection and classification performances for this pathology improved. Even for lesions other than Stafne's bone cavity, the detection sensitivities tended to increase with the increase in the number of Stafne's bone cavities. Conclusion: This study showed that using different lesions for transfer learning improves the performance of the model.

Keywords

Acknowledgement

We thank Helen Jeays, BDSc AE from Edanz (https://jp.edanz.com/ac) for editing a draft of this manuscript.

References

  1. Kim HG, Lee KM, Kim EJ, Lee JS. Improvement diagnostic accuracy of sinusitis recognition in paranasal sinus X-ray using multiple deep learning models. Quant Imaging Med Surg 2019; 9: 942-51.  https://doi.org/10.21037/qims.2019.05.15
  2. Murata M, Ariji Y, Ohashi Y, Kawai T, Fukuda M, Funakoshi T, et al. Deep-learning classification using convolutional neural network for evaluation of maxillary sinusitis on panoramic radiography. Oral Radiol 2019; 35: 301-7.  https://doi.org/10.1007/s11282-018-0363-7
  3. Nishiyama M, Ishibashi K, Ariji Y, Fukuda M, Nishiyama W, Umemura M, et al. Performance of deep learning models constructed using panoramic radiographs from two hospitals to diagnose fractures of the mandibular condyle. Dentomaxillofac Radiol 2021; 50: 20200611. 
  4. Lee A, Kim MS, Han SS, Park P, Lee C, Yun JP. Deep learning neural networks to differentiate Stafne's bone cavity from pathological radiolucent lesions of the mandible in heterogeneous panoramic radiography. PLoS One 2021; 16: e0254997. 
  5. Kise 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 Sjogren's syndrome on CT images. Dentomaxillofac Radiol 2019; 48: 20190019. 
  6. Kise Y, Shimizu M, Ikeda H, Fujii T, Kuwada C, Nishiyama M, et al. Usefulness of a deep learning system for diagnosing Sjogren's syndrome using ultrasonography images. Dentomaxillofac Radiol 2020; 49: 20190348. 
  7. Ariji 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.  https://doi.org/10.1016/j.oooo.2018.10.002
  8. Yang H, Jo E, Kim HJ, Cha IH, Jung YS, Nam W, et al. Deep learning for automated detection of cyst and tumors of the jaw in panoramic radiographs. J Clin Med 2020; 9: 1839. 
  9. Watanabe H, Ariji Y, Fukuda M, Kuwada C, Kise Y, Nozawa M, et al. Deep learning object detection of maxillary cyst-like lesions on panoramic radiographs: preliminary study. Oral Radiol 2021; 37: 487-93.  https://doi.org/10.1007/s11282-020-00485-4
  10. Kuwana R, Ariji Y, Fukuda M, Kise Y, Nozawa M, Kuwada C, et al. Performance of deep learning object detection technology in the detection and diagnosis of maxillary sinus lesions on panoramic radiographs. Dentomaxillofac Radiol 2021; 50: 20200171. 
  11. Kuwada C, Ariji Y, Kise Y, Funakoshi T, Fukuda M, Kuwada T, et al. Detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning system. Sci Rep 2021; 11: 16044. 
  12. Ariji Y, Fukuda M, Nozawa M, Kuwada C, Goto M, Ishibashi K, et al. Automatic detection of cervical lymph nodes in patients with oral squamous cell carcinoma using a deep learning technique: a preliminary study. Oral Radiol 2021; 37: 290-6.  https://doi.org/10.1007/s11282-020-00449-8
  13. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. The 3rd International Conference on Learning Representations; 2015 May 7-9; San Diego, California, USA. Available from: https://arxiv.org/abs/1409.1556. 
  14. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition; 2015 Jun 7-12; Boston, Massachusetts, USA. P. 1-9. Available from: https://arxiv.org/abs/1409.4842. 
  15. Mohammadi R, Salehi M, Ghaffari H, Rohani AA, Reiazi R. Transfer learning-based automatic detection of coronavirus disease 2019 (COVID-19) from chest X-ray images. J Biomed Phys Eng 2020; 10: 559-68.  https://doi.org/10.31661/jbpe.v0i0.2008-1153
  16. Mori M, Ariji Y, Katsumata A, Kawai T, Araki K, Kobayashi K, et al. A deep transfer learning approach for the detection and diagnosis of maxillary sinusitis on panoramic radiographs. Odontology 2021; 109: 941-8.  https://doi.org/10.1007/s10266-021-00615-2
  17. Ishibashi K, Ariji Y, Kuwada C, Kimura M, Hashimoto K, Umemura M, et al. Efficacy of a deep leaning model created with the transfer learning method in detecting sialoliths of the submandibular gland on panoramic radiography. Oral Surg Oral Med Oral Pathol Oral Radiol 2022; 133: 238-44.  https://doi.org/10.1016/j.oooo.2021.08.010
  18. Ariji 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
  19. Tao A, Barker J, Sarathy S. DetectNet: deep neural network for object detection in DIGITS. [updated 2016 Aug 11; cited 2022 July 25]. In: NVIDIA Developer. Technical Bog [Internet]. Santa Clara: NVIDA. Available from: URL: https://developer.nvidia.com/blog/detectnet-deep-neural-network-object-detection-digits/. 
  20. Barker J, Prasanna S. Deep learning for object detection with DIGITS. [updated 2016 Aug 11; cited 2022 July 25]. In: NVIDIA Developer. Technical Bog [Internet]. Santa Clara: NVIDA. Available from: https://developer.nvidia.com/blog/deep-learning-object-detection-digits/. 
  21. Koivisto T, Bowles WR, Rohrer M. Frequency and distribution of radiolucent jaw lesions: a retrospective analysis of 9,723 cases. J Endod 2012; 38: 729-32.  https://doi.org/10.1016/j.joen.2012.02.028
  22. Robinson RA. Diagnosing the most common odontogenic cystic and osseous lesions of the jaws for the practicing pathologist. Mod Pathol 2017; 30(s1): S96-103.  https://doi.org/10.1038/modpathol.2016.191
  23. Yeung AW. Radiolucent lesions of the jaws: an attempted demonstration of the use of co-word analysis to list main similar pathologies. Int J Environ Res Public Health 2022; 19: 1933. 
  24. Avril L, Lombardi T, Ailianou A, Burkhardt K, Varoquaux A, Scolozzi P, et al. Radiolucent lesions of the mandible: a patternbased approach to diagnosis. Insights Imaging 2014; 5: 85-101.  https://doi.org/10.1007/s13244-013-0298-9
  25. Liu Z, Liu J, Zhou Z, Zhang Q, Wu H, Zhai G, et al. Differential diagnosis of ameloblastoma and odontogenic keratocyst by machine learning of panoramic radiographs. Int J Comput Assist Radiol Surg 2021; 16: 415-22.  https://doi.org/10.1007/s11548-021-02309-0
  26. Ariji E, Fujiwara N, Tabata O, Nakayama E, Kanda S, Shiratsuchi Y, et al. Stafne's bone cavity. Classification based on outline and content determined by computed tomography. Oral Surg Oral Med Oral Pathol 1993; 76: 375-80.  https://doi.org/10.1016/0030-4220(93)90271-5
  27. Estai M, Tennant M, Gebauer D, Brostek A, Vignarajan J, Mehdizadeh M, et al. Deep learning for automated detection and numbering of permanent teeth on panoramic images. Dentomaxillofac Radiol 2022; 51: 20210296.