Köpeklerdeki Uzun Kemiklerin Evrişimsel Sinir Ağları Kullanılarak Sınıflandırılması

Son yılların en popüler konularından olan derin öğrenme, pek çok alanda olduğu gibi biyomedikal alanda da sıkça 2 kullanılmaktadır. Çeşitli görüntüleme yöntemleri ile elde edilen görüntüler kullanılarak hastalık ve kırık tespiti, biyolojik veri 3 kestirimi, doku ve organ bölütlemesi, eksik veri tamamlanması gibi nice uygulama derin öğrenme algoritmaları sayesinde 4 başarılı bir şekilde gerçekleştirilmektedir. Ancak bahsi geçen uygulamaların çok büyük bir çoğunluğu beşeri hekimlikte 5 yapılırken, veteriner tıp geri planda bırakılmıştır. Özellikle literatürde bu alandaki eksikliğin fark edilmesi bu çalışma 6 konusunun en büyük motivasyon kaynağı olmuştur. Bu çalışmada, Ankara Büyükşehir Belediyesi Sokak Hayvanları Geçici 7 Bakım Evi’nden alınan, köpeklere ait röntgenleri içeren geniş kapsamlı bir veri seti, derin öğrenme algoritmaları ile işlenmiştir. 8 Amaç, köpeklere ait X-Ray görüntülerinden uzun kemiğin çeşidinin belirlenmesidir. Biyomedikal görüntü işleme alandaki pek 9 çok çalışma gibi, bu çalışmada da Evrişimsel Sinir Ağları (Convolutional Neural Network, CNN) mimarileri kullanılmıştır. 10 Alexnet, GoogLeNet ve VGG-19 derin öğrenme modelleri ile öğrenme aktarımı gerçekleştirilmiş, destek vektör makineleri 11 (Support Vector Machines, SVM) ile sınıflandırma performansı test edilmiştir.

___

  • [1] A. Şeker, B. Diri, H. Hüseyin Balık, “Derin Öğrenme Yöntemleri ve Uygulamaları Hakkında Bir İnceleme,” Gazi Mühendislik Bilimleri Dergisi, vol. 3, pp. 47-64, 2017.
  • [2] A. Prasoon, K. Petersen, C. Igel, F. Lauze, E. Dam, M. Nielsen, “Deep Feature Learning for Knee Cartilage Segmentation Using a Triplanar Convolutional Neural Network,” MICCAI, pp. 246–253, 2013.
  • [3] Sergio, P., Adriano, P., Carlos, A, “Brain Tumor Segmentation using Convolutional Neural Networks in MRI Images” IEEE Transactions on Medical Imaging, pp. 1240-1251, 2016.
  • [4] G. Urban, M. Bendszus, F. A. Hamprecht, J. Kleesiek, “Multi-modal Brain Tumor Segmentation using Deep Convolutional Neural Networks,” MICCAI BraTS Challenge Proceedings, pp. 31–35, 2014.
  • [5] Adams M, Chen W, Holcdorf D, McCusker M W, Howe P D, Gaillard F., “Computer vs human: deep learning versus perceptual training for the detection of neck of femur fractures,” J Med Imaging Radiat Oncol; vol.63, pp. 27–32, 2019.
  • [6] Brett A, Miller C G, Hayes C W, Krasnow J, Ozanian T, Abrams K, Block J E, van Kuijk C., “Development of a clinical workflow tool to enhance the detection of vertebral fractures: accuracy and precision evaluation,” Spine, vol. 34, pp. 2437–2443, 2009.
  • [7] Chung S W, Han S S, Lee J W, Oh K S, Kim N R, Yoon J P, Kim J Y, Moon S H, Kwon J, Lee H J, Noh Y M, Kim Y., “Automated detection and classification of the proximal humerus fracture by using deep learning algorithm,” Acta Orthop, vol. 89, pp. 468–473, 2018.
  • [8] Szegedy C, Vanhoucke V, Loffe S., “Rethinking the Inception Architecture for Computer Vision,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, pp. 2818-2826, 2016.
  • [9] Lindsey R, Daluiski A, Chopra S, Lachapelle A, Mozer M, Sicular S, Hanel D, Gardner M, Gupta A, Hotchkiss R, Potter H., “Deep neural network improves fracture detection by clinicians,” Proc Natl Acad Sci USA, vol. 115 pp. 11591–11596, 2018.
  • [10] Najafabadi, M.M., Villanustre, F., Khoshgoftaar, T.M. et al. Deep learning applications and challenges in big data analytics. Journal of Big Data 2, 1, 2015.
  • [11] J. Seetha, S.S. Raja, “Brain Tumor Classification Using Convolutional Neural Networks,” Biomed Pharmacol J, vol. 11, 2018.
  • [12] Zbigniew A. Starosolski, J. Herman Kan, and Ananth Annapragada "CNN-based detection of distal tibial fractures in radiographic images in the setting of open growth plates", Proc. SPIE 11314, Medical Imaging 2020: Computer-Aided Diagnosis, 2020.
  • [13] YÖK Ulusal Tez Merkezi, “https://tez.yok.gov.tr/UlusalTezMerkezi/tezSorguSonucYeni.jsp,” erişim: 15.45, 11.10.2020.
  • [14] O. Yıldız, “Derin öğrenme yöntemleriyle dermoskopi görüntülerinden melanom tespiti: Kapsamlı bir çalışma,” Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, vol. 34, pp. 2241-2260, 2019.
  • [15] B. Harangi, “Skin lesion classification with ensembles of deep convolutional neural networks,” J Biomed Inform.vol. 86, pp. 25‐32, 2018.
  • [16] A. Esteva, B. Kuprel, R.A. Novoa, J. Ko, S.M. Swetter, H.M. Blau, and S. Thrun, “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, 2017.
  • [17] M. Siar and M. Teshnehlab, “Brain Tumor Detection Using Deep Neural Network and Machine Learning Algorithm,” 9th International Conference on Computer and Knowledge Engineering (ICCKE), Mashhad, Iran, pp. 363-368, 2019.
  • [18] S. Khawaldeh, U. Pervaiz, A. Rafiq, R. S. Alkhawaldeh, “Noninvasive Grading of Glioma Tumor Using Magnetic Resonance Imaging with Convolutional Neural Networks,” Appl. Sci., vol. 8, 2018.
  • [19] A. Le Berre, K. Kamagata, Y. Otsuka, et al. “Convolutional neural network-based segmentation can help in assessing the substantia nigra in neuromelanin MRI,” Neuroradiology, vol. 61, pp. 1387‐1395, 2019.
  • [20] Couteaux V, Si-Mohamed S, Nempont O, et al. “Automatic knee meniscus tear detection and orientation classification with Mask-RCNN,” Diagn Interv Imaging, vol. 100, pp. 235‐242, 2019.
  • [21] M. Gopalakrishnan, J. Sheng, M. Valesani, “Automated Detection of Breaks and Fractures in X-Ray Bone Images,” 2019.
  • [22] Johannes Kvam, Lars Erik Gangsei, Jørgen Kongsro, Anne H Schistad Solberg, “The use of deep learning to automate the segmentation of the skeleton from CT volumes of pigs,” Translational Animal Science, vol. 2, pp. 324–335, 2018.
  • [23] C. Chin, Y. Lin and Y. Liu, "Various Types Fracture Labeling in Bone Radiographs Using Modified AC-GAN," 2019 International Conference on Technologies and Applications of Artificial Intelligence (TAAI), Kaohsiung, Taiwan, pp. 1-6, 2019.
  • [24] A. Yi Yang, l. Cheng, “Long-Bone Fracture Detection Using Artificial Neural Networks Based on Contour Features of X-ray Images,” 2019.
  • [25] S. Beyaz, Salih, K. Açıcı, E. Sümer, “Derin Öğrenme ve Genetik Algoritma Yaklaşımları Kullanılarak X-Ray Görüntülerinde Femur Boyun Kırığı Tespiti,” Uluslararası Sağlıkta Yapay Zeka Kongresi, İzmir, Türkiye, 2020.
  • [26] F. Liu, Z. Zhou, H. Jang, A. Samsonov, G. Zhao, R. Kijowski, “Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging,” Magnetic Resonance in Medicine, 2017.
  • [27] Wang et al., "Skeletal Maturity Recognition Using a Fully Automated System with Convolutional Neural Networks," IEEE Access, vol. 6, pp. 29979-29993, 2018.
  • [28] D. H Kim, T. MacKinnon, “Artificial intelligence in fracture detection: Transfer learning from deep convolutional neural networks,” Clin. Radiol., vol. 73, pp. 439–445, 2018.
  • [29] Y. Chen, “Classification of Atypical Femur Fracture with Deep Neural Networks,” KTH University: Stockholm Sweden, 2019.
  • [30] Dargan, S., Kumar, M., Ayyagari, M.R. et al. “A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning,” Arch Computat Methods Eng., vol. 27, pp. 1071–1092, 2020.
  • [31] Stock Medical and Veterinary Illustrations, “drawing of dog skeletal system,” http://yesko.com/medical_illustrations/stock-illustration-dog-anatomy-01.htm, erişim: 19.01, 19.10.2020.
  • [32] Yamashita, R., Nishio, M., Do, R.K.G. et al. Convolutional neural networks: an overview and application in radiology. Insights Imaging, vol. 9, pp. 611–629, 2018.
  • [33] A. Krizhevsky, I. Sutskever, G. Hinton, "ImageNet classification with deep convolutional neural networks," NIPS’2012, 2012.
  • [34] Ö. İni̇k, E. Ülker, "Derin Öğrenme ve Görüntü Analizinde Kullanılan Derin Öğrenme Modelleri," Gaziosmanpaşa Bilimsel Araştırma Dergisi vol. 6, pp. 85-104, 2017.
  • [35] C. Szegedy et al., "Going deeper with convolutions," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, pp. 1-9, 2015.
  • [36] K. Simonyan, A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” conference paper at ICLR 2015.
  • [37] Ahmed Abdelbaki, “P-CNN features for Action Recognition,” Computer Vision Lab SS16, 2016.
  • [38] Cortes, C., and Vapnik, V. “Support-vector networks. Machine Learning,” vol. 20, pp. 273–297, 1995.
  • [39] Çok sınıflı DVM (Multiclass SVM), http://bilgisayarkavramlari.sadievrenseker.com/2008/12/01/cok-sinifli-dvm-multiclass-svm/, erişim: 19.51, 19.10.2020.
  • [40] A. Tekerek, “Support Vector Machine Based Spam SMS Detection,” Journal of Polytechnic, vol. 22, pp.779-784, 2019.
  • [41] Padmavathi Janardhanan, Heena L., and Fathima Sabika, “Effectiveness of Support Vector Machines in Medical Data mining,” Journal of Communications Software and Systems, vol. 11, 2015.
  • [42] A. Yahiaoui, O. Er, N. Yumusak, “A new method of automatic recognition for tuberculosis disease diagnosis using support vector machines,” Biomedical Research, vol. 28, 2017.
  • [43] L. Torrey and J. Shavlik, “Transfer Learning,” Handbook of Research on Machine Learning Applications, IGI Global, 2009.
  • [44] N. Tajbakhsh et al., “Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning,” IEEE Transactions on Medical Imaging, vol. 35, 2016.
  • [45] S. Zagoruyko, N. Komodakis, “Wide Residual Networks,” 2017.
  • [46] Nitesh Pradhan et al., “Classification of Human Bones Using Deep Convolutional Neural Network,” IOP Conference Series: Materials Science and Engineering, 2019.
  • [47] C. Shorten, T.M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J Big Data 6, 60, 2019.