Akciğer kanseri tanısı için derin öğrenme modellerinin karşılaştırılması ve uygulanması
Yıl 2024,
Sayı: 007, 1 - 9, 31.08.2024
Ekrem Gökberk Koç
,
Durmuş Özdemir
Öz
Akciğer kanseri, dünya genelinde yaygın bir sağlık sorunu haline gelmiştir. Erken teşhis ve doğru tedavi, hastalığın seyrini önemli ölçüde etkileyebilmektedir. Bu çalışmada, akciğer tomografisi (CT) görüntülerini kullanarak akciğer kanserinin erken teşhisini yapabilmek amaçlanmıştır. Bu teşhisi yapabilmek için derin öğrenme modellerinin karşılaştırılması ve uygulanması üzerine odaklanılmıştır. CNN, DenseNet ve ResNet gibi üç popüler derin öğrenme modeli kullanılarak, akciğer kanseri tanısı için performansları değerlendirilmiştir. Ayrıca eğitim verileri için 1440 akciğer tomografisi görüntüsü, test verileri için 174 akciğer tomografisi görüntüsü ve doğrulama verileri için 36 adet akciğer tomografisi görüntüsü kullanılmıştır. Sonuçlar değerlendirildiğinde en başarılı modelin ResNet (%96.55), bir sonraki başarılı modelin CNN (%89.08) ve son olarak DenseNet modelinin (%88.51) başarısı olduğu gözlenmiştir.
Destekleyen Kurum
Kütahya Dumlupınar Üniversitesi
Kaynakça
- [1] I. Tunali, R. J. Gillies, and M. B. Schabath, "Application of radiomics and AI for lung cancer precision medicine," Cold Spring Harbor Perspectives in Medicine, vol. 11, no. 8, Jan. 2021, doi: 10.1101/cshperspect.a039537.
- [2] F. Binczyk, W. Prazuch, P. Bozek, ve J. Polanska, "Radiomics and artificial intelligence in lung cancer screening," Translational Lung Cancer Research, vol. 10, no. 2, pp. 1186-1199, Feb. 2021, doi: 10.21037/tlcr-20-708.
- [3] P. Batırel, «drhasanbatirel,» 2019. [Online]. Available: https://www.drhasanbatirel.com/erken-evre-akciger-kanserinde-cerrahi/.
- [4] Y. Xu, A. Hosny, R. Zeleznik, C. Parmar, T. Coroller, I. Franco, ... ve H. J. Aerts, "Deep learning predicts lung cancer treatment response from serial medical imaging," Clinical Cancer Research, vol. 25, no. 11, pp. 3266-3275, 2019, doi: 10.1158/1078-0432.CCR-18-2495.
- [5] Y. LeCun, Y. Bengio, ve G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015, doi: 10.1038/nature14539.
- [6] P. P. Shinde ve S. Shah, "A review of machine learning and deep learning applications," in 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), IEEE, pp. 1-6, Aug. 2018, doi: 10.1109/ICCUBEA.2018.8697857
- [7] F. Binczyk, W. Prazuch, P. Bozek, ve J. Polanska, "Radiomics and artificial intelligence in lung cancer screening," Translational Lung Cancer Research, vol. 10, no. 2, pp. 1186, Feb. 2021, doi: 10.21037/tlcr-20-708.
- [8] J. Chamberlin, M. R. Kocher, J. Waltz, M. Snoddy, N. F. Stringer, J. Stephenson, ... ve J. R. Burt,
"Automated detection of lung nodules and coronary artery calcium using artificial intelligence on low-dose CT scans for lung cancer screening: accuracy and prognostic value," BMC Medicine, vol. 19, no. 1, pp. 1-14, Mar. 2021, doi: 10.1186/s12916-021-01928-3.
- [9] M. A. CİFCİ, "Derin Öğrenme Metodu ve Ayrık Dalgacık Dönüşümü Kullanarak BT Görüntülerinden Akciğer Kanseri Teşhisi," Mühendislik Bilimleri ve Araştırmaları Dergisi, vol. 4, no. 2, pp. 141-154, 2022, doi: 10.46387/bjesr.1114243.
- [10] N. KARACA ve A. KARACI, "DERİN ÖĞRENME VE GÖRÜNTÜ İŞLEME YÖNTEMLERİNİ KULLANARAK GÖĞÜS X-IŞINI GÖRÜNTÜLERİNDEN AKCİĞER BÖLGESİNİ TESPİT ETME," International Journal of 3D Printing Technologies and Digital Industry, vol. 6, no. 3, pp. 459-468, 2022, doi: 10.46519/ij3dptdi.1140171.
- [11] L. Liu ve C. Li, "Comparative study of deep learning models on the images of biopsy specimens for diagnosis of lung cancer treatment," Journal of Radiation Research and Applied Sciences, vol. 16, no. 2, pp. 100555, Jun. 2023, doi: 10.1016/j.jrras.2023.100555.
- [12] Z. Xu, H. Ren, W. Zhou, ve Z. Liu, "ISANET: Non-small cell lung cancer classification and detection based on CNN and attention mechanism," Biomedical Signal Processing and Control, vol. 77, pp. 103773, 2022, doi: 10.1016/j.bspc.2022.103773.
- [13] H. F. Al-Yasriy, «kaggle,» 2020. [Online]. Available: https://www.kaggle.com/datasets/hamdallak/the-iqothnccd-lung-cancer-dataset.
- [14] A. Mahimkar, «kaggle,» 2021. [Online]. Available: https://www.kaggle.com/datasets/adityamahimkar/iqothnccd-lung-cancer-dataset.
- [15] K. He, X. Zhang, S. Ren, ve J. Sun, "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, ss. 630-645, Springer International Publishing, Sep. 2016, doi: 10.1007/978-3-319-46493-0_38.
- [16] «TensorFlow ResNet50 documentation,» [Online]. Available: https://www.tensorflow.org/api_docs/python/tf/keras/applications/ResNet50.
- [17] W. Alakwaa, M. Nassef, ve A. Badr, "Lung cancer detection and classification with 3D convolutional neural network (3D-CNN)," International Journal of Advanced Computer Science and Applications, vol. 8, no. 8, 2017, doi: 10.14569/IJACSA.2017.080853.
- [18] C. J. Lin, S. Y. Jeng, ve M. K. Chen, "Using 2D CNN with Taguchi parametric optimization for lung cancer recognition from CT images," Applied Sciences, vol. 10, no. 7, pp. 2591, 2020, doi: 10.3390/app10072591.
- [19] G. Huang, Z. Liu, L. Van Der Maaten, ve K. Q. Weinberger, "Densely connected convolutional networks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700-4708, 2017, doi: 10.1109/CVPR.2017.243.
- [20] K. Team, «DenseNet,» [Online]. Available: https://keras.io/api/applications/densenet/.
- [21] M. Šarić, M. Russo, M. Stella, ve M. Sikora, "CNN-based method for lung cancer detection in whole slide histopathology images," in 2019 4th International Conference on Smart and Sustainable Technologies (SpliTech), pp. 1-4, IEEE, Jun. 2019, doi: 10.23919/SpliTech.2019.8783041.
- [22] N. Faruqui, M. A. Yousuf, M. Whaiduzzaman, A. K. M. Azad, A. Barros, ve M. A. Moni, "LungNet: A hybrid deep-CNN model for lung cancer diagnosis using CT and wearable sensor-based medical IoT data," Computers in Biology and Medicine, vol. 139, pp. 104961, Dec. 2021, doi: 10.1016/j.compbiomed.2021.104961.
- [23] Z. Tao, H. Bingqiang, L. Huiling, Y. Zaoli, ve S. Hongbin, "NSCR-based DenseNet for lung tumor recognition using chest CT image," BioMed Research International, vol. 2020, Dec. 2020, doi: 10.1155/2020/6636321.
COMPARISON AND APPLICATION OF DEEP LEARNING MODELS FOR DIAGNOSIS OF LUNG CANCER
Yıl 2024,
Sayı: 007, 1 - 9, 31.08.2024
Ekrem Gökberk Koç
,
Durmuş Özdemir
Öz
Lung cancer is a widespread health issue globally. Early detection and proper treatment can greatly impact the progression of the disease. This study aimed to identify lung cancer at an early stage using lung tomography (CT) images. The focus was on comparing and applying deep learning models for this diagnosis. The performance of three popular deep learning models - CNN, DenseNet, and ResNet - was evaluated for lung cancer diagnosis. The training data consisted of 1440 lung tomography images, while 174 images were used for testing and 36 for validation. Upon evaluation, it was observed that the most successful model was ResNet (96.55%), followed by CNN (89.08%), and finally the DenseNet model (88.51%).
Kaynakça
- [1] I. Tunali, R. J. Gillies, and M. B. Schabath, "Application of radiomics and AI for lung cancer precision medicine," Cold Spring Harbor Perspectives in Medicine, vol. 11, no. 8, Jan. 2021, doi: 10.1101/cshperspect.a039537.
- [2] F. Binczyk, W. Prazuch, P. Bozek, ve J. Polanska, "Radiomics and artificial intelligence in lung cancer screening," Translational Lung Cancer Research, vol. 10, no. 2, pp. 1186-1199, Feb. 2021, doi: 10.21037/tlcr-20-708.
- [3] P. Batırel, «drhasanbatirel,» 2019. [Online]. Available: https://www.drhasanbatirel.com/erken-evre-akciger-kanserinde-cerrahi/.
- [4] Y. Xu, A. Hosny, R. Zeleznik, C. Parmar, T. Coroller, I. Franco, ... ve H. J. Aerts, "Deep learning predicts lung cancer treatment response from serial medical imaging," Clinical Cancer Research, vol. 25, no. 11, pp. 3266-3275, 2019, doi: 10.1158/1078-0432.CCR-18-2495.
- [5] Y. LeCun, Y. Bengio, ve G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015, doi: 10.1038/nature14539.
- [6] P. P. Shinde ve S. Shah, "A review of machine learning and deep learning applications," in 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), IEEE, pp. 1-6, Aug. 2018, doi: 10.1109/ICCUBEA.2018.8697857
- [7] F. Binczyk, W. Prazuch, P. Bozek, ve J. Polanska, "Radiomics and artificial intelligence in lung cancer screening," Translational Lung Cancer Research, vol. 10, no. 2, pp. 1186, Feb. 2021, doi: 10.21037/tlcr-20-708.
- [8] J. Chamberlin, M. R. Kocher, J. Waltz, M. Snoddy, N. F. Stringer, J. Stephenson, ... ve J. R. Burt,
"Automated detection of lung nodules and coronary artery calcium using artificial intelligence on low-dose CT scans for lung cancer screening: accuracy and prognostic value," BMC Medicine, vol. 19, no. 1, pp. 1-14, Mar. 2021, doi: 10.1186/s12916-021-01928-3.
- [9] M. A. CİFCİ, "Derin Öğrenme Metodu ve Ayrık Dalgacık Dönüşümü Kullanarak BT Görüntülerinden Akciğer Kanseri Teşhisi," Mühendislik Bilimleri ve Araştırmaları Dergisi, vol. 4, no. 2, pp. 141-154, 2022, doi: 10.46387/bjesr.1114243.
- [10] N. KARACA ve A. KARACI, "DERİN ÖĞRENME VE GÖRÜNTÜ İŞLEME YÖNTEMLERİNİ KULLANARAK GÖĞÜS X-IŞINI GÖRÜNTÜLERİNDEN AKCİĞER BÖLGESİNİ TESPİT ETME," International Journal of 3D Printing Technologies and Digital Industry, vol. 6, no. 3, pp. 459-468, 2022, doi: 10.46519/ij3dptdi.1140171.
- [11] L. Liu ve C. Li, "Comparative study of deep learning models on the images of biopsy specimens for diagnosis of lung cancer treatment," Journal of Radiation Research and Applied Sciences, vol. 16, no. 2, pp. 100555, Jun. 2023, doi: 10.1016/j.jrras.2023.100555.
- [12] Z. Xu, H. Ren, W. Zhou, ve Z. Liu, "ISANET: Non-small cell lung cancer classification and detection based on CNN and attention mechanism," Biomedical Signal Processing and Control, vol. 77, pp. 103773, 2022, doi: 10.1016/j.bspc.2022.103773.
- [13] H. F. Al-Yasriy, «kaggle,» 2020. [Online]. Available: https://www.kaggle.com/datasets/hamdallak/the-iqothnccd-lung-cancer-dataset.
- [14] A. Mahimkar, «kaggle,» 2021. [Online]. Available: https://www.kaggle.com/datasets/adityamahimkar/iqothnccd-lung-cancer-dataset.
- [15] K. He, X. Zhang, S. Ren, ve J. Sun, "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, ss. 630-645, Springer International Publishing, Sep. 2016, doi: 10.1007/978-3-319-46493-0_38.
- [16] «TensorFlow ResNet50 documentation,» [Online]. Available: https://www.tensorflow.org/api_docs/python/tf/keras/applications/ResNet50.
- [17] W. Alakwaa, M. Nassef, ve A. Badr, "Lung cancer detection and classification with 3D convolutional neural network (3D-CNN)," International Journal of Advanced Computer Science and Applications, vol. 8, no. 8, 2017, doi: 10.14569/IJACSA.2017.080853.
- [18] C. J. Lin, S. Y. Jeng, ve M. K. Chen, "Using 2D CNN with Taguchi parametric optimization for lung cancer recognition from CT images," Applied Sciences, vol. 10, no. 7, pp. 2591, 2020, doi: 10.3390/app10072591.
- [19] G. Huang, Z. Liu, L. Van Der Maaten, ve K. Q. Weinberger, "Densely connected convolutional networks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700-4708, 2017, doi: 10.1109/CVPR.2017.243.
- [20] K. Team, «DenseNet,» [Online]. Available: https://keras.io/api/applications/densenet/.
- [21] M. Šarić, M. Russo, M. Stella, ve M. Sikora, "CNN-based method for lung cancer detection in whole slide histopathology images," in 2019 4th International Conference on Smart and Sustainable Technologies (SpliTech), pp. 1-4, IEEE, Jun. 2019, doi: 10.23919/SpliTech.2019.8783041.
- [22] N. Faruqui, M. A. Yousuf, M. Whaiduzzaman, A. K. M. Azad, A. Barros, ve M. A. Moni, "LungNet: A hybrid deep-CNN model for lung cancer diagnosis using CT and wearable sensor-based medical IoT data," Computers in Biology and Medicine, vol. 139, pp. 104961, Dec. 2021, doi: 10.1016/j.compbiomed.2021.104961.
- [23] Z. Tao, H. Bingqiang, L. Huiling, Y. Zaoli, ve S. Hongbin, "NSCR-based DenseNet for lung tumor recognition using chest CT image," BioMed Research International, vol. 2020, Dec. 2020, doi: 10.1155/2020/6636321.