SavedAdd your journal

Journals / Black Sea Journal of Engineering and Science / 2026 / Cilt: 8 Sayı: 1

Oral Cancer Classification with CNN Based State-of-the-art Transfer Learning Methods

Kaan Gümele(İSTANBUL MEDENİYET ÜNİVERSİTESİ)0009-0002-4262-0585
Muhammet Sinan Başarslan(İSTANBUL MEDENİYET ÜNİVERSİTESİ)0000-0002-7996-9169
Pages
94–101
Publication Date
2025-01-15
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

In intraoral images, ConvNextBase with 0.84 Acc, and 0.80 F1 was found to be more accurate.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The importance of oral and dental health closely affects other vital organs.
📊
Key Findings & Data:EfficientNetB7, ResNet50, VGG16, and VGG19, Xception, ConvNextBase, and MobileNetV2 were used as transfer learning methods.
💡
Conclusion & Impact:In intraoral images, ConvNextBase with 0.84 Acc, and 0.80 F1 was found to be more accurate.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Oral cancer · Image processing · Convolutional neural network

Abstract

The importance of oral and dental health closely affects other vital organs. In this study, CNN-based transfer learning models are built on histopathologic and intraoral images with benign and malignant lesions. Histopathologic and intraoral images from two different sources have benign or malignant classes of lesions in the mouth. EfficientNetB7, ResNet50, VGG16, and VGG19, Xception, ConvNextBase, and MobileNetV2 were used as transfer learning methods. Model training was performed with 80%-20% train test separation and 20% validation separation on the train set. Accuracy (Acc), Precision (Prec), Recall (Rec), and F1-score (F1) metrics were used to evaluate the model. In histopathologocial images, ResNet50 was ahead with 0.8125 Acc and 0.8525 F1. In intraoral images, ConvNextBase with 0.84 Acc, and 0.80 F1 was found to be more accurate.

Özet

The importance of oral and dental health closely affects other vital organs. In this study, CNN-based transfer learning models are built on histopathologic and intraoral images with benign and malignant lesions. Histopathologic and intraoral images from two different sources have benign or malignant classes of lesions in the mouth. EfficientNetB7, ResNet50, VGG16, and VGG19, Xception, ConvNextBase, and MobileNetV2 were used as transfer learning methods. Model training was performed with 80%-20% train test separation and 20% validation separation on the train set. Accuracy (Acc), Precision (Prec), Recall (Rec), and F1-score (F1) metrics were used to evaluate the model. In histopathologocial images, ResNet50 was ahead with 0.8125 Acc and 0.8525 F1. In intraoral images, ConvNextBase with 0.84 Acc, and 0.80 F1 was found to be more accurate.

🔖

Cite This Article

Gümele, K., Başarslan, M. S. (2025). Oral Cancer Classification with CNN Based State-of-the-art Transfer Learning Methods. Black Sea Journal of Engineering and Science, Cilt: 8 Sayı: 1, 94–101. https://doi.org/10.34248/bsengineering.1528581

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (30)

  1. Babu PA, Rai AK, Ramesh JVN, Nithyasri A, Sangeetha S, Kshirsagar PR, Rajendran A, Rajaram A, Dilipkumar S. 2024. An explainable deep learning approach for oral cancer detection. J Electr Eng Technol., 19: 1837–1848.
  2. Bakare YB, Kumarasamy M, 2021. Histopathologıcal image analysis for oral cancer classification by support vector machine. Int J Adv Signal Image Sci, 7: 1–10.
  3. Bal F, Kayaalp F, 2023. A novel deep learning-based hybrid method for the determination of productivity of agricultural products: apple case study. IEEE access, 11:7808–7821.
  4. Başarslan MS, Kayaalp F, 2023. MBi-GRUMCONV: A novel Multi Bi-GRU and Multi CNN-Based deep learning model for social media sentiment analysis. J Cloud Comput, 12: 1-16.
  5. Chandrashekar HS. Geetha A, Kiran S, Murali MS, Dinesh BR, Nanditha, 2021. Oral images dataset, URL: https://data.mendeley.com/datasets/mhjyrn35p4/2 (accessed date 13 April, 2024)
  6. Chang SW, Abdul-Kareem S, Merican AF, Zain RB. 2013. Oral cancer prognosis based on clinicopathologic and genomic markers using a hybrid of feature selection and machine learning methods. BMC Bioinform, 14: 1-15.
  7. Chollet F. 2017. Xception: Deep Learning with depthwise separable convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp: 1800–1807.
  8. Chu CS, Lee NP, Adeoye J, Thomson P, Choi SW. 2020. Machine learning and treatment outcome prediction for oral cancer. J Oral Pathol Med, 49: 977-985.
  9. Dawud AM, Yurtkan K, Oztoprak H, 2019. Application of deep learning in neuroradiology: brain haemorrhage classification using transfer learning. Comput Intell Neurosci, 2019: 4629859
  10. de Lima LM, de Assis MCFR, Soares JP, Grão-Velloso TR, de Barros LAP, Camisasca DR, Krohling RA, 2023. Importance of complementary data to histopathological image analysis of oral leukoplakia and carcinoma using deep neural networks. Intell Med 3: 258–266.
  11. Dinesh Y, Ramalingam K, Ramani P, Deepak RM, 2023. Machine learning in the detection of oral lesions with clinical intraoral images. Cureus 15:e44018
  12. Dong K, Zhou C, Ruan Y, Li Y, 2020. MobileNetV2 model for image classification. 2nd International Conference on Information Technology and Computer Application (ITCA), December 18-20, Guangzhou, China, pp: 476–480.
  13. Gilik A, Ogrenci AS, Ozmen A. Air quality prediction using CNN+LSTM-based hybrid deep learning architecture. Environ Sci Pollut Res 29: 11920–11938 2022.
  14. Goswami B, Bhuyan MK, Alfarhood S, Safran M, 2024. Classification of oral cancer into pre-cancerous stages from white light images using LightGBM algorithm. IEEE Access, 12: 31626–31639.
  15. He K, Zhang X, Ren S, Sun J. 2016. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 17-20 March, NV, USA, pp: 770-778.
  16. Jeyaraj PR, Samuel N, 2019. Computer-assisted medical image classification for early diagnosis of oral cancer employing deep learning algorithm. J Cancer Res Clin Oncol, 145: 829–837.
  17. Kabakus AT, Erdogmus P, 2022. An experimental comparison of the widely used pre‐trained deep neural networks for image classification tasks towards revealing the promise of transfer‐learning. Concurr Comput Pract Ex, 34: e7216.
  18. Kayaalp F, Basarslan MS, Polat K, 2018. TSCBAS: A novel correlation based attribute selection method and application on telecommunications churn analysis. International Conference on Artificial Intelligence and Data Processing (IDAP), 28-30 September, Malatya, Tükiye, pp: 1–5.
  19. Koonce B. 2021a EfficientNet. In convolutional neural networks with swift for tensorflow. Apress Berkeley, CA, USA, 1st ed., pp: 109–123
  20. Koonce B. 2021b. VGG Network. convolutional neural networks with swift for tensorflow. Apress Berkeley, CA, USA, 1st ed., pp: 35-50
  21. Lu C, Lewis Jr, JS, Dupont WD, Plummer Jr, WD, Janowczyk A, Madabhushi, A. 2017. An oral cavity squamous cell carcinoma quantitative histomorphometric-based image classifier of nuclear morphology can risk stratify patients for disease-specific survival. Mod Pathol, 30: 1655-1665.
  22. Muthu Rama Krishnan M, Shah P, Chakraborty C. 2012 Statistical analysis of textural features for improved classification of oral histopathological images. J Med Syst 36: 865–881.
  23. Öztürk T, Turgut Z, Akgün G, Köse C. 2022. Machine learning-based intrusion detection for SCADA systems in healthcare. Netw Model Anal Health Inform Bioinform, 11: 47.
  24. Ribeiro-de-Assis MCF, Soares JP, de Lima LM, de Barros LAP, Grão-Velloso TR, Krohling RA, Camisasca DR. 2023 NDB-UFES: An oral cancer and leukoplakia dataset composed of histopathological images and patient data. Data Brief, 48: 109128.
  25. Shavlokhova V, Sandhu, S, Flechtenmacher C, Koveshazi, I Neumeier F, Padrón-Laso V, Jonke Ž, Saravi B, Vollmer M, Vollmer A. 2021. Deep learning on oral squamous cell carcinoma ex vivo fluorescent confocal microscopy data: a feasibility study. J. Clin. Med. 10:5326
  26. Song B, Sunny S, Li S, Gurushanth K., Mendonca P, Mukhia N, Liang R, 2021. Bayesian deep learning for reliable oral cancer image classification. Biomed Opt Express, 12: 6422-6430.
  27. Warin K, Limprasert W, Suebnukarn S, Jinaporntham S, Jantana P, 2021. Automatic classification and detection of oral cancer in photographic images using deep learning algorithms. J Oral Pathol Med, 50: 911–918.
  28. Welikala, RA, Remagnino P, Lim JH, Chan CS, Rajendran S, Kallarakkal TG, Zain RB, Jayasinghe RD, Rimal J, Kerr AR, Amtha R, Patil K, Tilakaratne WM, Gibson J, Cheong SC, Barman SA. 2020. Automated detection and classification of oral lesions using deep learning for early detection of oral cancer. IEEE Access, 8: 132677–132693.
  29. Woo S, Debnath S, Hu R, Chen X, Liu Z, Kweon IS, Xie, S. 2023. ConvNeXt V2: Co-Designing and scaling convnets with masked autoencoders. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 11-15 Vancouver, BC, Canada, pp: 16133–16142.
  30. Zavrak S, Yilmaz S, 2023. Email spam detection using hierarchical attention hybrid deep learning method. Expert Syst Appl, 233: 120977.