Research Article
BibTex RIS Cite

InceptionResNetV2 ve Sınıf Aktivasyon Haritaları ile Akciğer Kanserinin Tespit Edilmesi

Year 2022, , 341 - 350, 30.06.2022
https://doi.org/10.21605/cukurovaumfd.1146066

Abstract

Akciğer kanseri, hayati tehlikesi son derecede yüksek olan bir hastalıktır. Dünya Sağlık Örgütü’ne göre kanserden ölüm oranı en yüksek olan hastalıktır. Oldukça sinsi olan bu hastalık erken evrelerde herhangi bir semptom göstermemektedir. İlk evrelerde hastalık doğru teşhis edildiği takdirde tedavisi mümkün olanbir hastalıktır. Bilgisayarlı tomografi ile akciğer bölgesindeki kitleler tespit edilebilmekte ve deneyimli doktorlar tarafından teşhis konulabilmektedir. Derin öğrenme yöntemlerinden biri olan evrişimsel sinir ağı günümüzde birçok hastalığın tespit edilmesinde başarılı bir şekilde uygulanmaktadır. Sınıf aktivasyon haritaları evrişimsel sinir ağı ile eğitilirken görüntünün ayırt edici bölgeleri önemine göre renklendirilmekte ve böylece hedef sınıfa yönelik önemli bölgeler tespit edilebilmektedir. Bu çalışmada bilgisayarlı tomografi ile elde edilen üç sınıftan oluşan toplam 1197 akciğer görüntüsü InceptionResNetV2 evrişimsel sinir ağı ile eğitilmiş sınıf aktivasyon haritaları ve görüntülere ait önemli bölgeler tespit edilerek bu bölgelere ait öznitelikler çıkarılmıştır. Elde edilen öznitelikler destek vektör makinaları ile sınıflandırılarak %95.44 doğruluk oranı ile sınıflandırılmıştır.

References

  • 1. Chaudhary, A., Singh, S.S., 2012. Lung Cancer Detection on CT Images by Using Image Processing. International Conference on Computing Sciences (ICCS 2012), 142–146, Phagwara, India.
  • 2. “Cancer,” 2020. https://www.who.int/newsroom/ fact-sheets/detail/cancer, Erişim Tarihi: 07.02.2022.
  • 3. Singh, G.A.P., Gupta, P.K., 2019. Performance Analysis of Various Machine Learning-based Approaches for Detection and Classification of Lung Cancer in Humans. Neural Computing and Applications, 31(10), 6863–6877.
  • 4. Toğaçar, M., Ergen, B., 2019. Biyomedikal Görüntülerde Derin Öğrenme ile Mevcut Yöntemlerin Kıyaslanması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 31(1), 109–121.
  • 5. Gao, F., 2018. SD-CNN: A Shallow-Deep CNN for Improved Breast Cancer Diagnosis. Computerized Medical Imaging and Graphics, 70, 53–62.
  • 6. Song, Q., Zhao, L., Luo, X., Dou, X., 2017. Using Deep Learning for Classification of Lung Nodules on Computed Tomography Images. Journal of Healthcare Engineering, 1-7.
  • 7. Khan, M.A., 2020. Lungs Cancer Classification from CT Images: An Integrated Design of Contrast Based Classical Features Fusion and Selection. Pattern Recognition Letter, 129, 77–85.
  • 8. Toğaçar, M., 2021. Disease Type Detection in Lung and Colon Cancer Images Using the Complement Approach of Inefficient Sets. Computers in Biology and Medicine, 137, 104827.
  • 9. “The IQ-OTHNCCD Lung Cancer Dataset,” 2020, [Online]. Available: https://www.kaggle.com/antonixx/theiqothnccd-lung-cancer-dataset. Erişim Tarihi:01.02.2022.
  • 10. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K., 2016. SqueezeNet: AlexNet-Level Accuracy with 50x Fewer Parameters and< 0.5 MB Model Size. arXiv Prepr. arXiv1602.07360.
  • 11. Sayed, G.I., Soliman, M.M., Hassanien, A. E., 2021. A Novel Melanoma Prediction Model for Imbalanced Data Using Optimized Squeezenet by Bald Eagle Search Optimization. Computers in Biology and Medicine, 136, 104712.
  • 12. Fan, J., Bi, S., Xu, R., Wang, L., Zhang, L., 2022. Hybrid Lightweight Deep-Learning Model for Sensor-Fusion Basketball Shooting- Posture Recognition. Measurement, 189, 110595.
  • 13. Ucar, F., Korkmaz, D., 2020. COVIDiagnosis- Net: Deep Bayes-SqueezeNet Based Diagnosis of the Coronavirus Disease 2019 (COVID-19) from X-ray Images. Medical. Hypotheses, 140, 109761.
  • 14. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A., 2016. Learning Deep Features for Discriminative Localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2921–2929. Las Vegas, USA.
  • 15. Zhang, R., Meng, F., Li, H., Wu, Q., Ngan, K.N., 2022. Category Boundary Re-Decision By Component Labels to Improve Generation of Class Activation Map. Neurocomputing, 469, 105–118.
  • 16. Cortes, C., Vapnik, V., 1995. Support-Vector Networks. 20(3), 273–297.
  • 17. Sonmez, M.E., Eczacıoglu, N., Gumuş, N.E., Aslan, M.F., Sabanci, K., Aşikkutlu, B., 2022. Convolutional Neural Network-support Vector Machine Based Approach for Classification of Cyanobacteria and Chlorophyta Microalgae Groups. Algal Research, 61, 102568.
  • 18. Toğaçar, M., Ergen, B., Sertkaya, M. E., 2019. Zatürre Hastalığının Derin Öğrenme Modeli ile Tespiti. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 31,1.
  • 19. Kareem, H.F., AL-Husieny, M.S., Mohsen, F.Y., Khalil, E.A., Hassan, Z.S., 2021. Evaluation of SVM Performance in the Detection of Lung Cancer in Marked CT Scan Dataset. Indonesian Journal of Electrical Engineering and Computer Science, 21(3), 1731–1738.
  • 20. Ashwin, S.G., Anurag, P.K., Reddy, N.V.S., Ashwath, R.B., 2022. Prediction of Lung Cancer Using Ensemble Classifiers. Journal of Physics: Conference Series. 2161, 1,12007.
  • 21. Kim, H., Jung, W.K., Park, Y.C., Lee, J.W., Ahn, S.H., 2022. Broken Stitch Detection Method for Sewing Operation Using CNN Feature Map and Image-processing Techniques. Expert Systems with Applications, 188, 116014.

Diagnosis of Lung Cancer with InceptionResNetV2 and Class Activation Maps

Year 2022, , 341 - 350, 30.06.2022
https://doi.org/10.21605/cukurovaumfd.1146066

Abstract

Lung cancer is a life-threatening disease. According to the World Health Organization, cancer is the disease with the highest mortality rate. This disease, which is quite insidious, does not show any symptoms in the early stages. If the disease is diagnosed correctly in the early stages, it can be treated. With computed tomography, masses in the lung region can be detected and diagnosed by experienced doctors. Convolutional neural network, which is one of the deep learning methods, is successfully applied in the detection of many diseases today. When class activation maps are trained with a convolutional neural network, distinctive regions of the image are colored according to their importance, so that the important regions for the target class can be determined. In this study, a total of 1197 lung images consisting of three classes obtained by computed tomography, class activation maps were trained with the InceptionResNetV2 convolutional neural network, and the important regions of the images were determined that the features of these regions were obtained. The Obtained features were classified using support vector machines and classified with an accuracy rate of 95.44%.

References

  • 1. Chaudhary, A., Singh, S.S., 2012. Lung Cancer Detection on CT Images by Using Image Processing. International Conference on Computing Sciences (ICCS 2012), 142–146, Phagwara, India.
  • 2. “Cancer,” 2020. https://www.who.int/newsroom/ fact-sheets/detail/cancer, Erişim Tarihi: 07.02.2022.
  • 3. Singh, G.A.P., Gupta, P.K., 2019. Performance Analysis of Various Machine Learning-based Approaches for Detection and Classification of Lung Cancer in Humans. Neural Computing and Applications, 31(10), 6863–6877.
  • 4. Toğaçar, M., Ergen, B., 2019. Biyomedikal Görüntülerde Derin Öğrenme ile Mevcut Yöntemlerin Kıyaslanması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 31(1), 109–121.
  • 5. Gao, F., 2018. SD-CNN: A Shallow-Deep CNN for Improved Breast Cancer Diagnosis. Computerized Medical Imaging and Graphics, 70, 53–62.
  • 6. Song, Q., Zhao, L., Luo, X., Dou, X., 2017. Using Deep Learning for Classification of Lung Nodules on Computed Tomography Images. Journal of Healthcare Engineering, 1-7.
  • 7. Khan, M.A., 2020. Lungs Cancer Classification from CT Images: An Integrated Design of Contrast Based Classical Features Fusion and Selection. Pattern Recognition Letter, 129, 77–85.
  • 8. Toğaçar, M., 2021. Disease Type Detection in Lung and Colon Cancer Images Using the Complement Approach of Inefficient Sets. Computers in Biology and Medicine, 137, 104827.
  • 9. “The IQ-OTHNCCD Lung Cancer Dataset,” 2020, [Online]. Available: https://www.kaggle.com/antonixx/theiqothnccd-lung-cancer-dataset. Erişim Tarihi:01.02.2022.
  • 10. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K., 2016. SqueezeNet: AlexNet-Level Accuracy with 50x Fewer Parameters and< 0.5 MB Model Size. arXiv Prepr. arXiv1602.07360.
  • 11. Sayed, G.I., Soliman, M.M., Hassanien, A. E., 2021. A Novel Melanoma Prediction Model for Imbalanced Data Using Optimized Squeezenet by Bald Eagle Search Optimization. Computers in Biology and Medicine, 136, 104712.
  • 12. Fan, J., Bi, S., Xu, R., Wang, L., Zhang, L., 2022. Hybrid Lightweight Deep-Learning Model for Sensor-Fusion Basketball Shooting- Posture Recognition. Measurement, 189, 110595.
  • 13. Ucar, F., Korkmaz, D., 2020. COVIDiagnosis- Net: Deep Bayes-SqueezeNet Based Diagnosis of the Coronavirus Disease 2019 (COVID-19) from X-ray Images. Medical. Hypotheses, 140, 109761.
  • 14. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A., 2016. Learning Deep Features for Discriminative Localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2921–2929. Las Vegas, USA.
  • 15. Zhang, R., Meng, F., Li, H., Wu, Q., Ngan, K.N., 2022. Category Boundary Re-Decision By Component Labels to Improve Generation of Class Activation Map. Neurocomputing, 469, 105–118.
  • 16. Cortes, C., Vapnik, V., 1995. Support-Vector Networks. 20(3), 273–297.
  • 17. Sonmez, M.E., Eczacıoglu, N., Gumuş, N.E., Aslan, M.F., Sabanci, K., Aşikkutlu, B., 2022. Convolutional Neural Network-support Vector Machine Based Approach for Classification of Cyanobacteria and Chlorophyta Microalgae Groups. Algal Research, 61, 102568.
  • 18. Toğaçar, M., Ergen, B., Sertkaya, M. E., 2019. Zatürre Hastalığının Derin Öğrenme Modeli ile Tespiti. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 31,1.
  • 19. Kareem, H.F., AL-Husieny, M.S., Mohsen, F.Y., Khalil, E.A., Hassan, Z.S., 2021. Evaluation of SVM Performance in the Detection of Lung Cancer in Marked CT Scan Dataset. Indonesian Journal of Electrical Engineering and Computer Science, 21(3), 1731–1738.
  • 20. Ashwin, S.G., Anurag, P.K., Reddy, N.V.S., Ashwath, R.B., 2022. Prediction of Lung Cancer Using Ensemble Classifiers. Journal of Physics: Conference Series. 2161, 1,12007.
  • 21. Kim, H., Jung, W.K., Park, Y.C., Lee, J.W., Ahn, S.H., 2022. Broken Stitch Detection Method for Sewing Operation Using CNN Feature Map and Image-processing Techniques. Expert Systems with Applications, 188, 116014.
There are 21 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Erdal Başaran This is me 0000-0001-8569-2998

Publication Date June 30, 2022
Published in Issue Year 2022

Cite

APA Başaran, E. (2022). InceptionResNetV2 ve Sınıf Aktivasyon Haritaları ile Akciğer Kanserinin Tespit Edilmesi. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 37(2), 341-350. https://doi.org/10.21605/cukurovaumfd.1146066