KaydedilenlerDerginizi ekleyin

Dergiler / Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi / 2026 / Cilt: 41 Sayı: 2

Görsel dönüştürücüler kullanılarak göğüs BT görüntülerinden akciğer kanseri alt tipi sınıflandırması

Lung cancer subtype classification from chest CT scans using vision transformers

Sinan Toklu(GAZI UNIVERSITY)0000-0002-8147-9089
Abdullah Talha Kabakuş(DUZCE UNIVERSITY)0000-0003-2181-4292
Sayfa
829–840
Yayın Tarihi
2026-07-20
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Bu çalışmada göğüs BT (bilgisayarlı tomografi) görüntülerinden akciğer kanseri alt tiplerinin otomatik sınıflandırılması amacıyla dönüştürücü (transformer) tabanlı bir derin öğrenme modeli önerilmektedir.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Akciğer kanseri, dünya genelinde önemli bir sağlık sorunu olmaya devam etmekte ve kanser kaynaklı ölümlerin başlıca nedenlerinden biri olarak öne çıkmaktadır; bu durum hasta sağkalım oranlarını artırmak için doğru ve erken tanı yaklaşımlarının geliştirilmesi gerekliliğini açıkça ortaya koymaktadır.
📊
Temel Bulgular & Veri:Model, dört tanısal kategori (adenokarsinom, skuamöz hücreli karsinom, büyük hücreli karsinom ve normal dokular) içeren halka açık Chest CT-Scan Images Dataset veriseti üzerinde eğitilip değerlendirilmiştir.
💡
Sonuç & Katkı:Bu çalışmada göğüs BT (bilgisayarlı tomografi) görüntülerinden akciğer kanseri alt tiplerinin otomatik sınıflandırılması amacıyla dönüştürücü (transformer) tabanlı bir derin öğrenme modeli önerilmektedir.
🔬Tür:Modelleme & Sayısal Simülasyon
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:akciğer kanseri sınıflandırması · derin öğrenme · göğüs BT görüntüleri

Özet

Akciğer kanseri, dünya genelinde önemli bir sağlık sorunu olmaya devam etmekte ve kanser kaynaklı ölümlerin başlıca nedenlerinden biri olarak öne çıkmaktadır; bu durum hasta sağkalım oranlarını artırmak için doğru ve erken tanı yaklaşımlarının geliştirilmesi gerekliliğini açıkça ortaya koymaktadır. Bu çalışmada göğüs BT (bilgisayarlı tomografi) görüntülerinden akciğer kanseri alt tiplerinin otomatik sınıflandırılması amacıyla dönüştürücü (transformer) tabanlı bir derin öğrenme modeli önerilmektedir. Model, dört tanısal kategori (adenokarsinom, skuamöz hücreli karsinom, büyük hücreli karsinom ve normal dokular) içeren halka açık Chest CT-Scan Images Dataset veriseti üzerinde eğitilip değerlendirilmiştir. Etiket normalizasyonu, görüntü yeniden boyutlandırma, veri dengelenmesi ve RandAugment yöntemiyle veri artırımı adımlarını içeren kapsamlı bir ön işleme hattı uygulanmıştır. Tıbbi görüntülerde uzun menzilli uzamsal bağımlılıkları yakalamadaki üstün kapasitesi nedeniyle Görsel Dönüştürücü (ViT-Large) mimarisi tercih edilmiştir. Deneysel sonuçlar modelin test kümesi üzerinde %98,5 doğruluk ve 0,980 makro ortalamalı F1-skoru elde ettiğini göstermektedir. Bu çalışmanın yeniliği klinik olarak anlamlı bir veri kümesinde ViT-Large omurgasıyla entegre edilen güçlü bir ön işleme stratejisinin ve jeton düzeyinde eğitim kararlılığını artırıcı yöntemlerin bir araya getirilmesiyle güncel en iyi (state-of-the-art) performansın elde edilmesinde yatmaktadır.

Abstract

Lung cancer is a major global health concern and remains a leading cause of cancer-related mortality, highlighting the urgent need for accurate and early diagnostic approaches to improve patient survival rates. In this study, we propose a transformer-based deep learning model for the automatic classification of lung cancer subtypes from chest CT images. The model is trained and evaluated on the publicly available Chest CT-Scan Images Dataset, which includes four diagnostic categories: adenocarcinoma, squamous cell carcinoma, large cell carcinoma, and normal tissues. A comprehensive preprocessing pipeline was employed, including label normalization, image resizing, data balancing, and augmentation using RandAugment. We adopted the Vision Transformer (ViT-Large) architecture due to its superior capacity for capturing long-range spatial dependencies in medical imaging. Experimental results demonstrate significant performance gains, with the model achieving 98.5% accuracy and a macro-averaged F1-score of 0.980 on the test set. The novelty of this study lies in the integration of a robust preprocessing strategy with a ViT-Large backbone and token-level training stability enhancements to achieve state-of-the-art performance on a clinically relevant dataset.

🔖

Bu Makaleye Atıf Yap

Toklu, S., Kabakuş, A. T. (2026). Görsel dönüştürücüler kullanılarak göğüs BT görüntülerinden akciğer kanseri alt tipi sınıflandırması. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, Cilt: 41 Sayı: 2, 829–840. https://doi.org/10.17341/gazimmfd.1811234

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...

Kaynakça (59)

  1. Sharma R., Mapping of global, regional and national incidence, mortality and mortality-to-incidence ratio of lung cancer in 2020 and 2050, Int J Clin Oncol, 27 (4), 665-675, 2022.
  2. Thandra K.C., Barsouk A., Saginala K., Aluru J.S., Barsouk A., Epidemiology of lung cancer, Contemp Oncol, 25 (1), 45-52, 2021.
  3. Jung K.W. vd., Prediction of Cancer Incidence and Mortality in Korea, 2025, Cancer Res Treat, 57 (2), 331-338, 2025.
  4. Luo G. vd., Projections of Lung Cancer Incidence by 2035 in 40 Countries Worldwide: Population-Based Study, JMIR Public Health Surveill, 9, e43651, 2023.
  5. Siegel R.L., Kratzer T.B., Giaquinto A.N., Sung H., Jemal A., Cancer statistics, 2025, CA Cancer J Clin, 75 (1), 10-45, 2025.
  6. Thandra K.C., Barsouk A., Saginala K., Aluru J.S., Barsouk A., Epidemiology of lung cancer, Contemp Oncol, 25 (1), 45, 2021.
  7. Chen Q. vd., Evaluating the tumor response assessment of modified-RECIST 1.1 in advance non-small cell lung cancer: a post-hoc analysis of 1,147 patients from the EAST-LC trial, Transl Lung Cancer Res, 14 (5), 1688-1698, 2025.
  8. Mandala A., Kurapati V.S.R., Musunuri S.R.K., Mutthina J.V.S.C., Sistla V.P.K., Kolli V.K.K., An Experimental Study on Prediction of Lung Cancer from CT Scan Images, Proceedings of the International Conference on Intelligent Systems and Computational Networks (ICISCN 2025), IEEE, 1-6, 2025.
  9. Wan Y., Wang D., Li H., Xu Y., The imaging techniques and diagnostic performance of ultrasound, CT, and MRI in detecting liver steatosis and fat quantification: A systematic review, J Radiat Res Appl Sci, 16 (4), 100658, 2023.
  10. Priya A., Shyamala Bharathi P., SE-ResNeXt-50-CNN: A deep learning model for lung cancer classification, Appl Soft Comput, 171, 112696, 2025.
  11. Chowdary S., Purushotaman S.B., An Improved Archimedes Optimization-aided Multi-scale Deep Learning Segmentation with Dilated Ensemble CNN Classification for Detecting Lung Cancer Using CT Images, Network: Computation in Neural Systems, 2024.
  12. Tyagi S., Talbar S.N., Predicting lung cancer treatment response from CT images using deep learning, Int J Imaging Syst Technol, 33 (5), 1577-1592, 2023.
  13. Bherje A. vd., Design of Deep Learning-based Approach to Predict Lung Cancer on CT Scan Images, Proceedings of the 5th International Conference on Innovative Trends in Information Technology (ICITIIT 2024), IEEE, Kottayam, India, 1-5, 2024.
  14. Park Y.J., Choi D., Choi J.Y., Hyun S.H., Performance Evaluation of a Deep Learning System for Differential Diagnosis of Lung Cancer with Conventional CT and FDG PET/CT Using Transfer Learning and Metadata, Clin Nucl Med, 46 (8), 635-640, 2021.
  15. Kim G., Park Y.M., Yoon H.J., Choi J.H., A multi-kernel and multi-scale learning based deep ensemble model for predicting recurrence of non-small cell lung cancer, PeerJ Comput Sci, 9, e1311, 2023.
  16. Li L., Zhao X., Lu W., Tan S., Deep learning for variational multimodality tumor segmentation in PET/CT, Neurocomputing, 392, 277-295, 2020.
  17. Raza R. vd., Lung-EffNet: Lung cancer classification using EfficientNet from CT-scan images, Eng Appl Artif Intell, 126, 106902, 2023.
  18. Jain R., Singh P., Kaur A., An ensemble reinforcement learning-assisted deep learning framework for enhanced lung cancer diagnosis, Swarm Evol Comput, 91, 101767, 2024.
  19. Xie Y., Zhang J., Xia Y., Fulham M., Zhang Y., Fusing texture, shape and deep model-learned information at decision level for automated classification of lung nodules on chest CT, Information Fusion, 42, 102-110, 2018.
  20. Ashames M.M.A. vd., Indifference subspace of deep features for lung nodule classification from CT images, Expert Syst Appl, 262, 125571, 2025.
  21. Riquelme D., Akhloufi M.A., Deep Learning for Lung Cancer Nodules Detection and Classification in CT Scans, AI (Switzerland), 1 (1), 28-67, 2020.
  22. Kalkan M., Guzel M.S., Ekinci F., Akcapinar Sezer E., Asuroglu T., Comparative Analysis of Deep Learning Methods on CT Images for Lung Cancer Specification, Cancers (Basel), 16, 3321, 2024.
  23. Mastouri R., Khlifa N., Neji H., Hantous-Zannad S., Performance analysis of various deep learning models based on Max-Min CNN for lung nodule classification on CT images, Mach Vis Appl, 35 (83), 1-16, 2024.
  24. Uzulmez S., Cifci M.A., Early diagnosis of lung cancer using deep learning and uncertainty measures, Journal of the Faculty of Engineering and Architecture of Gazi University, 39 (1), 385-400, 2024.
  25. Alshayeji M.H., Abed S., Lung cancer classification and identification framework with automatic nodule segmentation screening using machine learning, Applied Intelligence, 53, 19724-19741, 2023.
  26. Bhandary A. vd., Deep-learning framework to detect lung abnormality – A study with chest X-Ray and lung CT scan images, Pattern Recognit Lett, 129, 271-278, 2020.
  27. Rajasekar V., Vaishnnave M.P., Premkumar S., Sarveshwaran V., Rangaraaj V., Lung cancer disease prediction with CT scan and histopathological images feature analysis using deep learning techniques, Results in Engineering, 18, 101111, 2023.
  28. Dunn B., Pierobon M., Wei Q., Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis, Bioengineering, 10 (6), 690, 2023.
  29. Paszke A. vd., PyTorch: An Imperative Style, High-Performance Deep Learning Library, Proceedings of the Thirty-third Conference on Neural Information Processing Systems (NIPS 2019), Vancouver, Canada, 8026-8037, 2019.
  30. Wolf T., Debut L., Sanh V., Chaumond J. vd., Transformers: State-of-the-art Natural Language Processing, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, ACL, Online, 38-45, 2020.
  31. Harris C.R. vd., Array Programming with NumPy, Nature, 585, 357-362, 2020.
  32. The pandas development team, pandas: Python Data Analysis Library, https://pandas.pydata.org, Erişim tarihi: 07 Ocak 2024.
  33. Clark A. ve Contributors, Pillow (Python Imaging Library Fork), https://python-pillow.github.io/, Erişim tarihi: 05 Ağustos 2025.
  34. Hunter J.D., Matplotlib: A 2D Graphics Environment, Comput Sci Eng, 9 (3), 90-95, 2007.
  35. Waskom M.L., seaborn: statistical data visualization, J Open Source Softw, 6 (60), 1-4, 2021.
  36. Pedregosa F. vd., Scikit-learn: Machine Learning in Python, J Mach Learn Res, 12, 2825-2830, 2011.
  37. Hany M., Chest CT-Scan images Dataset, Kaggle, https://www.kaggle.com/datasets/mohamedhanyyy/chest-ctscan-images/data, Erişim tarihi: 05 Ağustos 2025.
  38. Dosovitskiy A. vd., An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, Proceedings of the 9th International Conference on Learning Representations (ICLR 2021), Vienna, Austria, 2021.
  39. Akiba T., Sano S., Yanase T., Ohta T., Koyama M., Optuna: A Next-generation Hyperparameter Optimization Framework, Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’19), Anchorage, USA, 2623-2631, 2019.
  40. Hugging Face, Trainer, https://huggingface.co/docs/transformers/en/main_classes/trainer, Erişim tarihi: 05 Ağustos 2025.
  41. Loshchilov I., Hutter F., Decoupled Weight Decay Regularization, Proceedings of the 7th International Conference on Learning Representations (ICLR 2019), New Orleans, USA, 1-19, 2019.
  42. Hugging Face, Evaluate, https://huggingface.co/docs/evaluate/index, Erişim tarihi: 09 Nisan 2025.
  43. Hossain M.S., Basak N., Mollah M.A., Nahiduzzaman M., Ahsan M., Haider J., Ensemble-based multiclass lung cancer classification using hybrid CNN-SVD feature extraction and selection method, PLoS One, 20 (3), e0318219, 2025.
  44. Riadi A., Achmad A., Zainuddin Z., Performance Analysis of Optimizers on Convolutional Neural Network for Lung Cancer Classification Using CT Scan Images, Proceedings of the 3rd International Conference on Disruptive Technologies (ICDT 2025), Greater Noida, India, IEEE, 1467-1472, 2025.
  45. Chandra Sekhar J., Buvaneswari B., Vimala Devi K., Ezhilarasi P., Muniyandy E., Asif Alisha S., Machine Learning based Early-detection of Lung Cancer Using CT Scan for the Early Identification and Classification, Journal of Electrical Systems, 20 (2s), 828-836, 2024.
  46. Rani R., Gupta S., Enhanced Chest Cancer Classification using Convolutional Neural Networks on CT Scan Images for Improved Diagnostic Accuracy, Proceedings of the 5th International Conference on Smart Electronics and Communication (ICOSEC 2024), Trichy, India, IEEE, 1237-1241, 2024.
  47. Bumpenje H., Rahmadwati, Abidin Z., Chest Cancer Classification from Chest CT-Scan Images using Deep Learning, Proceedings of the 2024 International Conference on Smart Computing, IoT and Machine Learning (SIML 2024), Surakarta, Indonesia, IEEE, 49-55, 2024.
  48. Deepa P., Arulselvi M., Sundaram S.M., Classification of Lung Cancer in Segmented CT Images Using Pre-Trained Deep Learning Models, Int J Electr Electron Res, 12 (1), 154-159, 2024.
  49. Mamun M., Mahmud M.I., Meherin M., Abdelgawad A., LCDctCNN: Lung Cancer Diagnosis of CT Scan Images Using CNN Based Model, Proceedings of the 10th International Conference on Signal Processing and Integrated Networks (SPIN 2023), Noida, India, IEEE, 205-212, 2023.
  50. Lanjewar M.G., Panchbhai K.G., Charanarur P., Lung cancer detection from CT scans using modified DenseNet with feature selection methods and ML classifiers, Expert Syst Appl, 224, 119961, 2023.
  51. Sandag G.A., Kabo D.T., Comparative Analysis of Lung Cancer Classification Models Using EfficientNet and ResNet on CT-Scan Lung Images, CogITo Smart Journal, 10 (1), 259-270, 2024.
  52. Sari S., Soesanti I., Setiawan N.A., Best Performance Comparative Analysis of Architecture Deep Learning on CT Images for Lung Nodules Classification, Proceedings of the IEEE 5th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE 2021), Purwokerto, Indonesia, IEEE, 138-143, 2021.
  53. Adnan Palash M.I., Yousuf M.A., A Federated Learning-based Model for the Detection of Lung Cancer from CT Scan Images, Proceedings of the 6th International Conference on Electrical Engineering and Information and Communication Technology (ICEEICT 2024), Dhaka, Bangladesh, IEEE, 741-745, 2024.
  54. Rehman A., Kashif M., Abunadi I., Ayesha N., Lung Cancer Detection and Classification from Chest CT Scans Using Machine Learning Techniques, Proceedings of the 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA 2021), Riyadh, Saudi Arabia, IEEE, 101-104, 2021.
  55. Verma A., Upadhyay A.K., Singh A.K., Joshi G., EfficientNet-B3-Based Automated Lung Cancer Detection System for CT Scans, Proceedings of the 11th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON 2024), Lucknow, India, IEEE, 1-6, 2024.
  56. Ray A., Chakraborty N., ETL-LWNet: An Ensemble of Transfer Learning Based Light Weight Deep Learning Models for Identification of Lung Cancer Type in CT-Scan Images, Proceedings of the Third International Conference on Advanced Computing and Applications (ICACA 2024), Springer, Singapore, 575-585, 2024.
  57. Macasoi E.-D., Neagoe V.-E., An Approach to Lung Cancer Detection and Classification from Chest CT-Scan Images Using Deep Convolutional Neural Networks and Decision Fusion as a Diagnostic Tool, Proceedings of the 17th International Conference on Electronics, Computers and Artificial Intelligence (ECAI 2025), Targoviste, Romania, IEEE, 1-6, 2025.
  58. Akhand Z.-E.-N. vd., Lung Cancer Detection Using Ensemble Technique of CNN, Proceedings of the International Conference on Information and Communication Technology for Development (ICICTD 2022), Khulna, Bangladesh, Springer, Singapore, 497-507, 2022.
  59. Goh Y.T., Chua H.N., Jasser M.B., Wong R.T.K., Issa B., Multi-Class Classification of Lung Cancer Using Streamlined Convolutional Neural Networks, Proceedings of the International Colloquium on Signal Processing and Its Applications (CSPA 2025), Pulau Pinang, Malaysia, IEEE, 301-306, 2025.