Ağırlıklandırılmış Evrişimsel Sinir Ağları Topluluğu ile Göğüs Radyografilerinden Kardiyomegali Tespiti

Yıl 2024, Cilt: 16 Sayı: 1, 178 - 188, 31.01.2024

Enes Ayan

https://doi.org/10.29137/umagd.1367772

Öz

Kardiyomegali bir hastalık olmamasına karşın birçok kalp rahatsızlığının belirtisi olarak ortaya çıkabilmektedir. Bu belirtinin erken teşhis edilip altında yatan sebeplerin araştırılması hasta için hayati bir önem arz etmektedir. Kardiyomegali teşhisi için en sık kullanılan yöntemlerden biri göğüs radyografisidir. Derin öğrenme yöntemleri ile radyografik görüntülerin analizi son yıllarda oldukça popüler bir çalışma alanıdır. Özellikle evrişimsel sinir ağları medikal görüntü analizinde başarılı sonuçlar elde etmiştir. Bu çalışmada hekimlerin göğüs radyografilerini analiz ederken ikinci bir görüş alabilecekleri, göğüs radyografilerini normal ve kardiyomegali olmak üzere sınıflandıracak ağırlıklandırılmış evrişimsel sinir ağı (ESA) topluluğu önerilmiştir. Bu bağlamda kardiyomegali tespit etmesi için eğitilen on ESA modeli arasından en başarılı üç model ağırlıklandırılmış topluluk yöntemi için seçilmiştir. Seçilen modellerin ağırlıkları parçacık sürü optimizasyon algoritması kullanılarak belirlenmiştir. Elde edilen ağırlıklar kullanılarak yapılan testler sonucunda önerilen yöntem %89,09 doğruluk %89,09 duyarlılık, %89,30 kesinlik ve %89,08 F1 skor değerleri elde etmiştir.

Anahtar Kelimeler

Evrişimsel Sinir Ağları, Parçacık Sürü Optimizasyonu, Kardiyomegali, Derin Öğrenme

Kaynakça

• Abdelrahman, L., Al Ghamdi, M., Collado-Mesa, F., & Abdel-Mottaleb, M. (2021). Convolutional neural networks for breast cancer detection in mammography: A survey. Computers in biology and medicine, 131, 104248.
• Ayan, E., Erbay, H., & Varçın, F. (2020). Crop pest classification with a genetic algorithm-based weighted ensemble of deep convolutional neural networks. Computers and Electronics in Agriculture, 179, 105809.
• Bougias, H., Georgiadou, E., Malamateniou, C., & Stogiannos, N. (2021). Identifying cardiomegaly in chest X-rays: a cross-sectional study of evaluation and comparison between different transfer learning methods. Acta Radiologica, 62(12), 1601-1609.
• Bouslama, A., Laaziz, Y., & Tali, A. (2020). Diagnosis and precise localization of cardiomegaly disease using U-NET. Informatics in Medicine Unlocked, 19, 100306.
• Candemir, S., & Antani, S. (2019). A review on lung boundary detection in chest X-rays. International journal of computer assisted radiology and surgery, 14, 563-576.
• Candemir, S., Rajaraman, S., Thoma, G., & Antani, S. (2018). Deep learning for grading cardiomegaly severity in chest x-rays: an investigation. Paper presented at the 2018 IEEE Life Sciences Conference (LSC).
• Chen, L., Mao, T., & Zhang, Q. (2022). Identifying cardiomegaly in chest x-rays using dual attention network. Applied Intelligence, 52(10), 11058-11067.
• Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
• Dash, S., Shakyawar, S. K., Sharma, M., & Kaushik, S. (2019). Big data in healthcare: management, analysis and future prospects. Journal of big data, 6(1), 1-25.
• Eberhart, R., & Kennedy, J. (1995). Particle swarm optimization. Paper presented at the Proceedings of the IEEE international conference on neural networks.
• He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
• Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
• Ilovar, M., & Šajn, L. (2011). Analysis of radiograph and detection of cardiomegaly. Paper presented at the 2011 Proceedings of the 34th International Convention MIPRO.
• Innat, M., Hossain, M. F., Mader, K., & Kouzani, A. Z. (2023). A convolutional attention mapping deep neural network for classification and localization of cardiomegaly on chest X-rays. Scientific Reports, 13(1), 6247.
• Ishida, T., Katsuragawa, S., Chida, K., MacMahon, H., & Doi, K. (2005). Computer-aided diagnosis for detection of cardiomegaly in digital chest radiographs. Paper presented at the Medical Imaging 2005: Image Processing.
• Jamroży, M., Leyko, T., & Lewenstein, K. (2010). Early detection of the cardiac insufficiency. In Recent Advances in Mechatronics (pp. 407-411): Springer.
• Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.
• Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2021). A survey of convolutional neural networks: analysis, applications, and prospects. IEEE transactions on neural networks and learning systems.
• Peng, T., Wang, Y., Xu, T. C., & Chen, X. (2019). Segmentation of lung in chest radiographs using hull and closed polygonal line method. IEEE Access, 7, 137794-137810.
• Qin, C., Yao, D., Shi, Y., & Song, Z. (2018). Computer-aided detection in chest radiography based on artificial intelligence: a survey. Biomedical engineering online, 17(1), 1-23.
• Que, Q., Tang, Z., Wang, R., Zeng, Z., Wang, J., Chua, M., . . . Veeravalli, B. (2018). CardioXNet: automated detection for cardiomegaly based on deep learning. Paper presented at the 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).
• Semsarian, C., Ingles, J., Maron, M. S., & Maron, B. J. (2015). New perspectives on the prevalence of hypertrophic cardiomyopathy. Journal of the American College of Cardiology, 65(12), 1249-1254.
• Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
• Sogancioglu, E., Murphy, K., Calli, E., Scholten, E. T., Schalekamp, S., & Van Ginneken, B. (2020). Cardiomegaly detection on chest radiographs: Segmentation versus classification. IEEE Access, 8, 94631-94642.
• Summers RM. NIH Chest X-ray Dataset of 14 Cardiomegaly Disease Cat-egories. https://nihcc.app.box.com/v/ChestXray-NIHCC/file/220660789610. Erişim Tarihi Eylül 2023
• Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. Paper presented at the Proceedings of the AAAI conference on artificial intelligence.
• Torres-Robles, F., Rosales-Silva, A. J., Gallegos-Funes, F. J., & Bazán-Trujillo, I. (2014). A robust neuro-fuzzy classifier for the detection of cardiomegaly in digital chest radiographies. Dyna, 81(186), 35-41.
• Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017). Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
• Wu, J.-X., Pai, C.-C., Kan, C.-D., Chen, P.-Y., Chen, W.-L., & Lin, C.-H. (2022). Chest X-ray image analysis with combining 2D and 1D convolutional neural network based classifier for rapid cardiomegaly screening. IEEE Access, 10, 47824-47836.
• Zhou, S., Zhang, X., & Zhang, R. (2019). Identifying cardiomegaly in ChestX-ray8 using transfer learning. In MEDINFO 2019: Health and Wellbeing e-Networks for All (pp. 482-486): IOS Press.
• Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018). Learning transferable architectures for scalable image recognition. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.