Detection of Mucous Retention Cysts Using Deep Learning Methods on Panoramic Radiographs

Abstract

Aim: This study aimed to perform clinical diagnosis and treatment planning of mucous retention cysts with high accuracy and low error using the deep learning-based EfficientNet method. For this purpose, a hybrid approach that distinguishes healthy individuals from individuals with mucous retention cysts using panoramic radiographic images was presented. Material and Methods: Radiographs of patients who applied to the Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Fırat University between 2020 and 2022 and had panoramic radiography for various reasons were evaluated retrospectively. A total of 161 radiographs, 82 panoramic radiographs with mucous retention cysts and 79 panoramic radiographs without mucous retention cysts, were included in the study. In the classification process, deep feature representations or feature maps of the images were created using eight different deep learning models of EfficientNet from B0 to B7. The efficient features obtained from these networks were given as input to the support vector machine classifier, and healthy individuals and patients with mucous retention cysts were classified. Results: As a result of the model training, it was determined that the EfficientNetB6 model performed the best. When all performance parameters of the model were evaluated together, the accuracy, precision, sensitivity, specificity, and F1 score values were obtained 0.878, 0.785, 0.916, 0.857, and 0.846, respectively. Conclusion: The proposed hybrid artificial intelligence model showed a successful classification performance in the diagnosis of mucous retention cysts. The study will shed light on other future studies that will serve the same purpose.

Keywords

• Deep Learning
• Panoramic radiography
• maxillary sinus
• cyst

Panoramik Radyografilerde Mukos Retansiyon Kistlerinin Derin Öğrenme Yöntemleri Kullanılarak Tespiti

Abstract

Amaç: Bu çalışmada derin öğrenme tabanlı EfficientNet yöntemi kullanılarak mukos retansiyon kistlerinin yüksek doğruluk ve düşük hata ile klinik tanı ve tedavi planlamasının yapılması amaçlanmıştır. Bu amaçla panoramik radyografik görüntüler kullanılarak sağlıklı bireyleri mukos retansiyon kisti olan bireylerden ayıran hibrit bir yaklaşım sunulmuştur. Gereç ve Yöntemler: Fırat Üniversitesi Diş Hekimliği Fakültesi Ağız, Diş ve Çene Radyolojisi Anabilim Dalı'na 2020 ve 2022 yılları arasında başvuran ve çeşitli nedenlerle panoramik radyografi çekilmiş olan hastaların radyografileri geriye dönük olarak değerlendirilmiştir. Mukos retansiyon kisti bulunan 82 panoramik radyografi ve mukus retansiyon kisti bulunmayan 79 panoramik radyografi olmak üzere toplamda 161 radyografi bu çalışmaya dahil edilmiştir. Sınıflandırma sürecinde EfficientNet'in B0'dan B7'ye kadar sekiz farklı derin öğrenme modeli kullanılarak görüntülerin derin özellik temsilleri veya özellik haritaları oluşturulmuştur. Bu ağlardan elde edilen verimli özellikler, destek vektör makinesi sınıflandırıcısına girdi olarak verilmiş ve sağlıklı bireyler ile mukos retansiyon kisti olan hastalar sınıflandırılmıştır. Bulgular: Model eğitimleri sonucunda EfficientNetB6 modelinin en iyi performansı sergilediği belirlenmiştir. Modelin tüm performans parametreleri birlikte değerlendirildiğinde, doğruluk, kesinlik, duyarlılık, özgüllük ve F1 puanı değerleri sırasıyla 0,878, 0,785, 0,916, 0,857 ve 0,846 olarak elde edilmiştir. Sonuç: Önerilen hibrit yapay zeka modelinin mukos retansiyon kisti teşhisinde başarılı bir sınıflandırma performansı göstermiştir. Bu çalışmanın aynı amaca hizmet edecek gelecekteki diğer çalışmalara ışık tutacağı düşünülmektedir.

Keywords

• Derin öğrenme
• panoramik radyografi
• maksiller sinüs
• kist

References

1. Roman JCM, Fretes VR, Adorno CG, Silva RG, Noguera JLV, Legal-Ayala H, et al. Panoramic dental radiography image enhancement using multiscale mathematical morphology. Sensors (Basel). 2021;21(9):3110.
2. Meer S, Altini M. Cysts and pseudocysts of the maxillary antrum revisited. SADJ. 2006;61(1):10-3.
3. Anitua E, Alkhraisat MH, Torre A, Eguia A. Are mucous retention cysts and pseudocysts in the maxillary sinus a risk factor for dental implants? A systematic review. Med Oral Patol Oral Cir Bucal. 2021;26(3): e276-83.
4. Nemati P, Jafari-Pozve N, Aryanezhad SS. Association between mucous retention cyst of paranasal sinuses and nasal septum deviation. Adv Oral Maxillofac Surg. 2023;10:100415.
5. Rastegar H, Osmani F. Evaluation of mucous retention cyst prevalence on digital panoramic radiographs in the local population of Iran. Radiol Res Pract. 2022;2022:8650027.
6. Beaumont C, Zafiropoulos GG, Rohmann K, Tatakis DN. Prevalence of maxillary sinus disease and abnormalities in patients scheduled for sinus lift procedures. J Periodontol. 2005;76(3):461-7.
7. Carrillo-Perez F, Pecho OE, Morales JC, Paravina RD, Della Bona A, Ghinea R, et al. Applications of artificial intelligence in dentistry: A comprehensive review. J Esthet Restor Dent. 2022;34(1):259-80.
8. Khanagar SB, Al-Ehaideb A, Maganur PC, Vishwanathaiah S, Patil S, Baeshen HA, et al. Developments, application, and performance of artificial intelligence in dentistry - A systematic review. J Dent Sci. 2021;16(1):508-22.

9. Agrawal P, Nikhade P. Artificial intelligence in dentistry: past, present, and future. Cureus. 2022;14(7):e27405.
10. Ilhan B, Lin K, Guneri P, Wilder-Smith P. Improving oral cancer outcomes with imaging and artificial intelligence. J Dent Res. 2020;99(3):241-8.
11. Vodanović M, Subašić M, Milošević D, Savić Pavičin I. Artificial intelligence in medicine and dentistry. Acta Stomatol Croat. 2023;57(1):70-84.
12. Kurt Z, Işık Ş, Kaya Z, Anagün Y, Koca N, Çiçek S. Evaluation of EfficientNet models for COVID-19 detection using lung parenchyma. Neural Comput Appl. 2023;35(16):12121-32.
13. Gunwant H, Joshi A, Sharma M, Gupta D. Automated medical diagnosis and classification of skin diseases using Efficinetnet-B0 convolutional neural network. In: Castillo O, Melin P, editors. New perspectives on hybrid intelligent system design based on fuzzy logic, neural networks and metaheuristics. Springer, Cham; 2022. p.3-19.
14. Duong LT, Nguyen PT, Di Sipio C, Di Ruscio D. Automated fruit recognition using EfficientNet and MixNet. Comput Electron Agric. 2020;171:105326.
15. Atila Ü, Uçar M, Akyol K, Uçar E. Plant leaf disease classification using EfficientNet deep learning model. Ecol Inform. 2021;61:101182.
16. Açıkoğlu M, Arslan Tuncer S. Classification of 1D and 2D EEG signals for seizure detection in the newborn using convolutional neural networks. BEU J Sci. 2022;11(1):194-202.
17. Çelik F, Aydemir E. Prediction of difficult tracheal intubation by artificial intelligence: a prospective observational study. Duzce Med J. 2021;23(1):47-54.
18. Rajaram Mohan K, Mathew Fenn S. Artificial intelligence and its theranostic applications in dentistry. Cureus. 2023;15(5):e38711.
19. Mureșanu S, Almășan O, Hedeșiu M, Dioșan L, Dinu C, Jacobs R. Artificial intelligence models for clinical usage in dentistry with a focus on dentomaxillofacial CBCT: a systematic review. Oral Radiol. 2023;39(1):18-40.
20. Baydar O, Ulusoy AC, Alpöz E. Artificial intelligence in maxillofacial ultrasonography applications. EÜ Dişhek Fak Derg. 2022;43(Ozel Sayi):11-7. Turkish.
21. Fujima N, Kamagata K, Ueda D, Fujita S, Fushimi Y, Yanagawa M, et al. Current state of artificial intelligence in clinical applications for head and neck MR imaging. Magn Reson Med Sci. 2023;22(4):401-14.
22. Li M, Punithakumar K, Major PW, Le LH, Nguyen KT, Pacheco-Pereira C, et al. Temporomandibular joint segmentation in MRI images using deep learning. J Dent. 2022;127:104345.
23. Sivari E, Senirkentli GB, Bostanci E, Guzel MS, Acici K, Asuroglu T. Deep learning in diagnosis of dental anomalies and diseases: a systematic review. Diagnostics (Basel). 2023;13(15):2512.
24. 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(3):301-7.
25. 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(1):20200171.
26. 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(4):941-8.
27. Kotaki S, Nishiguchi T, Araragi M, Akiyama H, Fukuda M, Ariji E, et al. Transfer learning in diagnosis of maxillary sinusitis using panoramic radiography and conventional radiography. Oral Radiol. 2023;39(3):467-74.