Gastric Cancer Detection Using Vision Transformers: Feature Extraction and Classical Classifier Performance Evaluation

Abstract

Gastric cancer remains one of the most prevalent and deadly forms of cancer worldwide, necessitating advanced computational methods for early and accurate detection. This study explores the effectiveness of Vision Transformers (ViTs) in feature extraction for gastric cancer image classification. A publicly available dataset was sourced from Kaggle, consisting of three categories: Normal, Stage-1, and Stage-2 gastric cancer images. Using a pre-trained Google Vision Transformer model, 1000 deep features were extracted from the fully connected head layer without additional training. These extracted features were then used as input for various classical classifiers, including Support Vector Machines (SVM), k-Nearest Neighbors (KNN), Decision Trees, and Random Forest, to evaluate their classification performance. The effectiveness of these classifiers was assessed based on classification accuracies. Comparative analysis of classifier results demonstrated the impact of feature extraction via Vision Transformers on improving gastric cancer detection. The findings highlight the potential of Vision Transformers in medical image analysis and emphasize the role of feature-based classification in aiding early diagnosis. This study provides insights into the applicability of deep learning models in feature extraction and their integration with traditional machine learning classifiers for medical diagnostics.

Keywords

• Gastric Cancer
• Image Classification
• Vision Transformers
• Features Extraction

Görüntü Dönüştürücülerini Kullanarak Mide Kanseri Tespiti: Özellik Çıkarımı ve Klasik Sınıflandırıcı Performans Değerlendirmesi

Abstract

Mide kanseri, dünya çapında en yaygın ve ölümcül kanser türlerinden biri olmaya devam etmektedir ve erken ve doğru tespit için gelişmiş hesaplama yöntemlerini gerektirmektedir. Bu çalışma, mide kanseri görüntü sınıflandırması için özellik çıkarmada Görüntü Dönüştürücülerinin (ViT) etkinliğini araştırmaktadır. Normal, Evre-1 ve Evre-2 mide kanseri görüntüleri olmak üzere üç kategoriden oluşan, herkese açık bir veri seti Kaggle'dan alınmıştır. Önceden eğitilmiş bir Google Görüntü Dönüştürücü modeli kullanılarak, ek eğitim olmaksızın tam olarak bağlı baş katmanından 1000 derin özellik çıkarılmıştır. Çıkarılan bu özellikler daha sonra, sınıflandırma performanslarını değerlendirmek için Destek Vektör Makineleri (SVM), k-En Yakın Komşular (KNN), Karar Ağaçları ve Rastgele Orman dahil olmak üzere çeşitli klasik sınıflandırıcılar için girdi olarak kullanılmıştır. Bu sınıflandırıcıların etkinliği, sınıflandırma doğruluklarına göre değerlendirilmiştir. Sınıflandırıcı sonuçlarının karşılaştırmalı analizi, Görüntü Dönüştürücüleri aracılığıyla özellik çıkarma işleminin mide kanseri tespitini iyileştirme üzerindeki etkisini göstermiştir. Bulgular, Görüntü Dönüştürücülerinin tıbbi görüntü analizindeki potansiyelini vurgulamakta ve erken tanıya yardımcı olmada özellik tabanlı sınıflandırmanın rolünü vurgulamaktadır. Bu çalışma, derin öğrenme modellerinin özellik çıkarmada uygulanabilirliği ve tıbbi teşhis için geleneksel makine öğrenimi sınıflandırıcılarıyla entegrasyonu hakkında bilgi sağlamaktadır.

Keywords

• Mide Kanseri
• Görüntü Sınıflandırma
• Görme Dönüştürücüler
• Özellik Çıkarımı

References

1. Ajani, J. A., D’Amico, T. A., Almhanna, K., Bentrem, D. J., Chao, J., Das, P., ... & Yoon, S. S. (2022). Gastric Cancer, Version 2.2022, NCCN Clinical Practice Guidelines in Oncology. Journal of the National Comprehensive Cancer Network, 20(2), 167-192.
2. Bray, F., Ferlay, J., Soerjomataram, I., Siegel, R. L., Torre, L. A., & Jemal, A. (2018). Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 68(6), 394-424.
3. Correa, P. (2016). Gastric cancer: Overview. Gastroenterology Clinics of North America, 45(3), 413-420. Dalmaz, O., Yurt, M., & Çukur, T. (2022). ResViT: residual vision transformers for multimodal medical image synthesis. IEEE Transactions on Medical Imaging, 41(10), 2598-2614.
4. Demiroğlu, U. (2025). Diagnosis of the Skin Cancer by Vision Transformers. Duzce University Journal of Science and Technology, 13(1), 588-598. https://doi.org/10.29130/dubited.1572317 Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., ... & Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.
5. Gao, L., & Guan, L. (2023). Interpretability of machine learning: Recent advances and future prospects. IEEE MultiMedia, 30(4), 105-118.
6. He, K., Gan, C., Li, Z., Rekik, I., Yin, Z., Ji, W., ... & Shen, D. (2023). Transformers in medical image analysis. Intelligent Medicine, 3(1), 59-78.
7. Henry, E. U., Emebob, O., & Omonhinmin, C. A. (2022). Vision transformers in medical imaging: A review. arXiv preprint arXiv:2211.10043.
8. Hirasawa, T., Aoyama, K., Tanimoto, T., Ishihara, S., Fujishiro, M., & Ozawa, T. (2018). Application of artificial intelligence using convolutional neural networks for detecting gastric cancer in endoscopic images. Gastrointestinal Endoscopy, 87(3), 610-617. https://doi.org/10.1016/j.gie.2017.10.010

9. Hirasawa, T., Ikenoyama, Y., Ishioka, M., Namikawa, K., Horiuchi, Y., Nakashima, H., & Fujisaki, J. (2021). Current status and future perspective of artificial intelligence applications in endoscopic diagnosis and management of gastric cancer. Digestive endoscopy, 33(2), 263-272.
10. Kaggle. (2025). Gastric Cancer [Dataset]. Retrieved March 05, 2025, from https://www.kaggle.com/datasets/dskoushik/gastric-cancer
11. Karimi, P., Islami, F., Anandasabapathy, S., Freedman, N. D., & Kamangar, F. (2014). Gastric cancer: Descriptive epidemiology, risk factors, screening, and prevention. Cancer Epidemiology, Biomarkers & Prevention, 23(5), 700-713.
12. Kasban, H., El-Bendary, M. A. M., & Salama, D. H. (2015). A comparative study of medical imaging techniques. International Journal of Information Science and Intelligent System, 4(2), 37-58.
13. Khan, A., Rauf, Z., Khan, A. R., Rathore, S., Khan, S. H., Shah, N. S., ... & Gwak, J. (2023). A recent survey of vision transformers for medical image segmentation. arXiv preprint arXiv:2312.00634.
14. Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022). Transformers in vision: A survey. ACM Computing Surveys, 54(10s), 1-41. https://doi.org/10.1145/3505244
15. Kim, Y. J., Cho, H. C., & Cho, H. C. (2021). Deep learning-based computer-aided diagnosis system for gastroscopy image classification using synthetic data. Applied Sciences, 11(2), 760.
16. Komorowski, P., Baniecki, H., & Biecek, P. (2023). Towards evaluating explanations of vision transformers for medical imaging. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 3726-3732).
17. Lin, C. H., Hsu, P. I., Tseng, C. D., Chao, P. J., Wu, I. T., Ghose, S., ... & Lee, T. F. (2023). Application of artificial intelligence in endoscopic image analysis for the diagnosis of a gastric cancer pathogen-Helicobacter pylori infection. Scientific Reports, 13(1), 13380.
18. Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., ... & van der Laak, J. A. W. M. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60-88.
19. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., ... & Guo, B. (2021). Swin Transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF International Conference on Computer Vision, 10012-10022.
20. Machlowska, J., Baj, J., Sitarz, M., Maciejewski, R., & Sitarz, R. (2020). Gastric cancer: Epidemiology, risk factors, classification, genomic characteristics, and treatment strategies. International Journal of Molecular Sciences, 21(11), 4012.
21. MathWorks. (2025). Train Vision Transformer network for image classification. Retrieved March 5, 2025, from https://uk.mathworks.com/help/deeplearning/ug/train-vision-transformer-network-for-image-classification.html
22. Niu, P. H., Zhao, L. L., Wu, H. L., Zhao, D. B., & Chen, Y. T. (2020). Artificial intelligence in gastric cancer: Application and future perspectives. World journal of gastroenterology, 26(36), 5408.
23. Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., & Dosovitskiy, A. (2021). Do vision transformers see like convolutional neural networks? Advances in Neural Information Processing Systems (NeurIPS), 34, 12116-12128. https://doi.org/10.48550/arXiv.2108.08810
24. Salam, M. A., Abdellatif, A., Abdallah, M., & Salam, N. A. (2025). A Hybrid Deep Learning and Machine Learning Model for Multi-Class Lung Disease Detection in Medical Imaging. International Journal of Intelligent Engineering & Systems, 18(1).
25. Shamshad, F., Khan, S., Zamir, S. W., Khan, M. H., Hayat, M., Khan, F. S., & Fu, H. (2023). Transformers in medical imaging: A survey. Medical image analysis, 88, 102802.
26. Smyth, E. C., Nilsson, M., Grabsch, H. I., van Grieken, N. C., & Lordick, F. (2020). Gastric cancer. The Lancet, 396(10251), 635-648.
27. Spanhol, F. A., Oliveira, L. S., Cavalin, P. R., Petitjean, C., & Heutte, L. (2017, October). Deep features for breast cancer histopathological image classification. In 2017 IEEE international conference on systems, man, and cybernetics (SMC) (pp. 1868-1873). IEEE.
28. Suganyadevi, S., Seethalakshmi, V., & Balasamy, K. (2022). A review on deep learning in medical image analysis. International Journal of Multimedia Information Retrieval, 11(1), 19-38.
29. Takahashi, S., Sakaguchi, Y., Kouno, N., Takasawa, K., Ishizu, K., Akagi, Y., ... & Hamamoto, R. (2024). Comparison of vision transformers and convolutional neural networks in medical image analysis: a systematic review. Journal of Medical Systems, 48(1), 84.