PERFORMANCE OF DEEP RESIDUAL NETWORKS IN LUNG CANCER CLASSIFICATION: AN ANALYSIS ON HISTOPATHOLOGICAL IMAGES

Year 2024, Volume: 3 Issue: 2, 87 - 95, 26.12.2024

Merve Yağmurcu , Sultan Uzun , Özlem Polat

https://doi.org/10.69560/cujast.1591111

Abstract

Lung cancer is one of the most commonly seen and deadly types of cancer worldwide. Early diagnosis of this disease is crucial for prolonging life and improving treatment success. This study focuses on classifying lung cancer from histopathological images and investigates the performance of residual-based models (ResNet18, ResNet34, ResNet50, ResNet50V2, ResNet101, ResNet101V2, ResNet152, ResNet152V2) in classification. The LC25000 dataset, containing three classes—adenocarcinoma, benign, and squamous cell carcinoma—with 5000 images per class, was used. Among the tested models, ResNet18 achieved the highest classification performance with an accuracy of 99.90%. The results demonstrate that ResNet-based models perform excellently in accurately classifying complex histopathological images and highlight the potential of deep learning methods as a practical solution for lung cancer diagnosis.

Keywords

Lung Cancer, Histopathological Images, Classification, ResNet

DERİN REZİDÜEL AĞLARIN AKCİĞER KANSERİ SINIFLANDIRMADAKİ BAŞARIMI: HİSTOPATOLOJİK GÖRÜNTÜLER ÜZERİNDE İNCELEME

Abstract

Akciğer kanseri, dünya genelinde yaygın olarak görülen ve yüksek ölüm oranına sahip kanser türlerinden biridir. Bu hastalığın erken teşhisi, yaşam süresini uzatmak ve tedavi başarısını artırmak açısından hayati önem taşımaktadır. Bu çalışmada, histopatolojik görüntülerden akciğer kanserinin sınıflandırılmasına odaklanılmış ve rezidüel tabanlı modellerin (ResNet18, ResNet34, ResNet50, ResNet50V2, ResNet101, ResNet101V2, ResNet152, ResNet152V2) sınıflandırma üzerindeki başarımı incelenmiştir. Veri seti olarak adenokarsinom, iyi huylu ve skuamöz hücreli karsinom olmak üzere üç sınıf içeren ve her sınıfta 5000 görüntünün olduğu LC25000 veri seti kullanılmıştır. Test edilen modeller arasında ResNet18 %99,90 doğruluk oranı ile en yüksek sınıflandırma performansı göstermiştir. Elde edilen sonuçlar, ResNet tabanlı modellerin karmaşık histopatolojik görüntüleri doğru bir şekilde sınıflandırmada üstün performans sergilediğini ve akciğer kanseri teşhisinde derin öğrenme yöntemlerinin pratik bir çözüm sunabileceğini göstermektedir.

Keywords

Akciğer Kanseri, Histopatolojik Görüntüler, Sınıflama, ResNet

References

• Borkowski, A. A., Bui, M. M., Thomas, L. B., Wilson, C. P., DeLand, L. A., & Mastorides, S. M. (2019). Lung and colon cancer histopathological image dataset (lc25000). arXiv preprint arXiv:1912.12142.
• Callaghan, R. C., Allebeck, P., & Sidorchuk, A. (2013). Marijuana use and risk of lung cancer: a 40-year cohort study. Cancer Causes & Control, 24, 1811-1820.
• Gautam, N., Ghosh, S., & Sarkar, R. (2024). Cnn models aided with a metaclassifier for lung Carcinoma classification using histopathological images. Multimedia Tools and Applications, 1-25.
• Hamed, E. A. R., Salem, M. A. M., Badr, N. L., & Tolba, M. F. (2023a). An efficient combination of convolutional neural network and LightGBM algorithm for lung cancer histopathology classification. Diagnostics, 13(15), 2469.
• Hamed, E. A. R., Salem, M. A. M., Badr, N. L., & Tolba, M. F. (2023b, March). Lung Cancer Classification Model Using Convolution Neural Network. In The International Conference on Artificial Intelligence and Computer Vision (pp. 16-26). Cham: Springer Nature Switzerland.
• Hatuwal, B. K., & Thapa, H. C. (2020). Lung cancer detection using convolutional neural network on histopathological images. Int. J. Comput. Trends Technol, 68(10), 21-24.
• He, K., Zhang, X., Ren, S., & Sun, J. (2016a). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
• He, K., Zhang, X., Ren, S., & Sun, J. (2016b). Identity mappings in deep residual networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14 (pp. 630-645). Springer International Publishing.
• Islam, M., & Tasnim, N. (2020). Human gender classification using transfer learning via Pareto Frontier CNN networks. Inventions 5, 16.
• Kalshetty, R., & Parveen, A. (2023). Abnormal event detection model using an improved ResNet101 in context aware surveillance system. Cognitive Computation and Systems, 5(2), 153-167.
• Katar, O., Yildirim, O., Tan, R. S., & Acharya, U. R. (2024). A Novel Hybrid Model for Automatic Non-Small Cell Lung Cancer Classification Using Histopathological Images. Diagnostics, 14(22), 2497.
• LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
• Ma, S., Huang, T., Sun, X., & Wei, Y. (2021, May). Driver Drowsiness Detection Based On ResNet-18 And Transfer Learning. In 2021 33rd Chinese Control and Decision Conference (CCDC) (pp. 2390-2394). IEEE.
• Masud, M., Sikder, N., Nahid, A. A., Bairagi, A. K., & AlZain, M. A. (2021). A machine learning approach to diagnosing lung and colon cancer using a deep learning-based classification framework. Sensors, 21(3), 748.
• Nergiz, M. (2023). Federe Öğrenmede Birleştirme Algoritmalarının Model Performansına Etkisi. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 14(1), 65-73.
• Nguyen, L. D., Lin, D., Lin, Z., & Cao, J. (2018, May). Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation. In 2018 IEEE international symposium on circuits and systems (ISCAS) (pp. 1-5). IEEE.
• Noaman, N. F., Kanber, B. M., Smadi, A. A., Jiao, L., & Alsmadi, M. K. (2024). Advancing Oncology Diagnostics: AI-Enabled Early Detection of Lung Cancer through Hybrid Histological Image Analysis. IEEE Access.
• Patel, S., & Khan, N. R. (2023). A Weighted-Average-Ensembling Based Hybrid CNN Model for Improved Covid-19 Detection.
• Ramesh, M., Maheswaran, S., Theivanayaki, S., Kodeeswari, K., Krishnasamy, L., & Sriram, N. (2023, July). Efficient Lung Cancer Classification on Multi level Convolution Neural Network using Histopathological Images. In 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT) (pp. 1-7). IEEE.
• Shabrina, N. H., Lika, R. A., & Indarti, S. (2023). Deep learning models for automatic identification of plant-parasitic nematode. Artificial Intelligence in Agriculture, 7, 1-12.
• Singh, O., & Singh, K. K. (2023). An approach to classify lung and colon cancer of histopathology images using deep feature extraction and an ensemble method. International journal of information technology, 15(8), 4149-4160.
• Singh, O., Singh, K. K., Das, S., Akbari, A. S., & Abd Manap, N. (2023, October). Classification of lung cancer from histopathology Images using a Deep Ensemble Classifier. In 2023 IEEE International Conference on Imaging Systems and Techniques (IST) (pp. 1-6). IEEE.
• Sumon, R. I., Mazumdar, M. A. I., Uddin, S. M. I., & Kim, H. C. (2024, July). Exploring Deep Learning and Machine Learning Techniques for Histopathological Image Classification in Lung Cancer Diagnosis. In 2024 International Conference on Electrical, Computer and Energy Technologies (ICECET (pp. 1-6). IEEE.
• Sung, H., Ferlay, J., Siegel, R. L., Laversanne, M., Soerjomataram, I., Jemal, A., & Bray, F. (2021). Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians, 71(3), 209-249.
• Şeker, D., Kartal, M. S., Yıldız, A., & Öksüz, İ. (2024). Akciğer Kanseri Tespitinde Dönüşüm ve Evrişim Tabanlı Modeller ile Açıklanabilir Yapay Zeka Uygulaması. EMO Bilimsel Dergi, 14(2), 59-69.
• Talukder, M. A., Layek, M. A., Kazi, M., Uddin, M. A., & Aryal, S. (2024). Empowering covid-19 detection: Optimizing performance through fine-tuned efficientnet deep learning architecture. Computers in Biology and Medicine, 168, 107789.
• Toğaçar, M., Eşidir, K. A., & Ergen, B. (2021). Yapay Zekâ Tabanlı Doğal Dil İşleme Yaklaşımını Kullanarak İnternet Ortamında Yayınlanmış Sahte Haberlerin Tespiti. Journal of Intelligent Systems: Theory and Applications, 5(1), 1-8.
• Uçar, E. (2021). Akciğer Histopatoloji Görüntülerinden Çıkarılan Derin Özellikleri Kullanan Makine Öğrenmesi Sınıflandırıcıları ile Akciğer Kanseri Tespiti. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 10(4), 1552-1562.
• Uddin, J. (2024). Attention-Based DenseNet for Lung Cancer Classification Using CT Scan and Histopathological Images.
• Yang, L., & Lima, D. (2021). Covid-19 Recognition by Chest CT and Deep Learning. EAI Endorsed Transactions on e-Learning, 7(23), e3-e3.Designs, 8(2), 27.
• Zhang, Z., Wang, S., Li, Z., Gao, F., & Wang, H. (2023). A Multi-Dimensional Covert Transaction Recognition Scheme for Blockchain. Mathematics.