1. DergiPark
  2. Electronic Letters on Science and Engineering
  3. Archive
  4. Volume 16, Issue 2
Year 2020, Volume 16 , Issue 2, Pages 77 - 83 2020-12-30

Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine

Ahmet Haşim YURTTAKAL [1] , Hasan ERBAY [2] , Recep ARSLAN [3]

Abstract

Beyin kanseri, beyinde tümör oluşumuna bağlı olarak ortaya çıkan ölümcül bir hastalıktır. Kol ve bacaklarda güçsüzlük, konuşma ve görme bozuklukları, aşırı şiddetli baş ağrıları ve kusma gibi semptomlara neden olabilir. Genelde dört sınıfa ayrılır. Birinci ve ikinci sınıflar "düşük dereceli", yani "iyi huylu", üçüncü ve dördüncü sınıflar "yüksek dereceli", yani "kötü huylu" olarak değerlendirilir. Tedavi prosedürleri için tümörün erken evrelenmesi önemlidir. Beyin tümörlerinin histopatolojik görüntülere göre derecelendirilmesi, uzmanlık gerektiren yorucu bir süreçtir. Öte yandan, derin öğrenme algoritmaları bilgisayar destekli teşhis sistemlerinde sıklıkla kullanılmaktadır. Bu çalışmada, dört faza ait 1133x40 beyin histopatolojik görüntülerinin otomatik derecelendirilmesi yapılmıştır. Öncelikle, ResNet50 ve ResNet101 modelleri ile en son teknoloji önceden eğitilmiş Artık ağlardan özellikler çıkarılmıştır. Ardından, hiper parametreler Bayesian Optimizasyonu ile optimize edilerek, Destek Vektör Makinesi (SVM) algoritması ile sınıflandırılmıştır. Veri setinin %80'i eğitim ve %20'si test için ayrılmıştır. Çoklu sınıflandırma problemleri açısından değerlendirildiğinde Resnet50'de %80.09 gibi yüksek bir doğruluk oranına ulaşılırken, Resnet101'de Grade I tespitinde %100 yüksek duyarlılık değerine ulaşılmaktadır

Keywords

Residual Networks, Support Vector Machine, Histopathology, Grading

References

  • [1] L. M. DeAngelis, “Brain tumors,” New England journal of medicine, vol. 344, no. 2, pp. 114-123, 2001.
  • [2] W. Penfield, “The classification of gliomas and neuroglia cell types,” Archives of Neurology & Psychiatry, vol. 26, no. 4, pp. 745-753, 1931.
  • [3] K. Herholz, K.-J. Langen, C. Schiepers, and J. M. Mountz, "Brain tumors." pp. 356-370.
  • [4] N. Coudray, P. S. Ocampo, T. Sakellaropoulos, N. Narula, M. Snuderl, D. Fenyö, A. L. Moreira, N. Razavian, and A. Tsirigos, “Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning,” Nature medicine, vol. 24, no. 10, pp. 1559-1567, 2018.
  • [5] S. Khan, N. Islam, Z. Jan, I. U. Din, and J. J. C. Rodrigues, “A novel deep learning based framework for the detection and classification of breast cancer using transfer learning,” Pattern Recognition Letters, vol. 125, pp. 1-6, 2019.
  • [6] J. J. Nirschl, A. Janowczyk, E. G. Peyster, R. Frank, K. B. Margulies, M. D. Feldman, and A. Madabhushi, "Deep learning tissue segmentation in cardiac histopathology images," Deep Learning for Medical Image Analysis, pp. 179-195: Elsevier, 2017.
  • [7] S. Kostopoulos, P. Ravazoula, P. Asvestas, I. Kalatzis, G. Xenogiannopoulos, D. Cavouras, and D. Glotsos, “Development of a reference image collection library for histopathology image processing, analysis and decision support systems research,” Journal of digital imaging, vol. 30, no. 3, pp. 287-295, 2017.
  • [8] D. Glotsos, I. Kalatzis, P. Spyridonos, S. Kostopoulos, A. Daskalakis, E. Athanasiadis, P. Ravazoula, G. Nikiforidis, and D. Cavouras, “Improving accuracy in astrocytomas grading by integrating a robust least squares mapping driven support vector machine classifier into a two level grade classification scheme,” computer methods and programs in biomedicine, vol. 90, no. 3, pp. 251-261, 2008.
  • [9] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks." pp. 1097-1105.
  • [10] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition." pp. 770-778.
  • [11] I. L. S. V. R. Challenge, “Available online: http://www. image-net. org/challenges,” LSVRC/(accessed on 26 February 2019), 2014.

Details

Primary Language en
Subjects Engineering
Journal Section Articles
Authors

Orcid: 0000-0001-5170-6466
Author: Ahmet Haşim YURTTAKAL (Primary Author)
Institution: Yozgat Bozok University
Country: Turkey

Orcid: 0000-0002-7555-541X
Author: Hasan ERBAY
Institution: TÜRK HAVA KURUMU ÜNİVERSİTESİ
Country: Turkey

Orcid: 0000-0002-3028-0416
Author: Recep ARSLAN
Institution: Yozgat Bozok University
Country: Turkey
Dates

Application Date : September 3, 2020
Acceptance Date : December 11, 2020
Publication Date : December 30, 2020

Cite

Bibtex @research article { else789773, journal = {Electronic Letters on Science and Engineering}, issn = {1305-8614}, address = {Bozok University, Electrical and Electronics Engineering, Erdoğan Akdag Kampus, 66200, Yozgat, TURKEY.}, publisher = {Fevzullah TEMURTAŞ}, year = {2020}, volume = {16}, pages = {77 - 83}, doi = {}, title = {Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine}, key = {cite}, author = {Yurttakal, Ahmet Haşim and Erbay, Hasan and Arslan, Recep} }
APA Yurttakal, A , Erbay, H , Arslan, R . (2020). Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine . Electronic Letters on Science and Engineering , 16 (2) , 77-83 . Retrieved from https://dergipark.org.tr/en/pub/else/issue/58236/789773
MLA Yurttakal, A , Erbay, H , Arslan, R . "Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine" . Electronic Letters on Science and Engineering 16 (2020 ): 77-83 <https://dergipark.org.tr/en/pub/else/issue/58236/789773>
Chicago Yurttakal, A , Erbay, H , Arslan, R . "Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine". Electronic Letters on Science and Engineering 16 (2020 ): 77-83
RIS TY - JOUR T1 - Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine AU - Ahmet Haşim Yurttakal , Hasan Erbay , Recep Arslan Y1 - 2020 PY - 2020 N1 - DO - T2 - Electronic Letters on Science and Engineering JF - Journal JO - JOR SP - 77 EP - 83 VL - 16 IS - 2 SN - 1305-8614- M3 - UR - Y2 - 2020 ER -
EndNote %0 Electronic Letters on Science and Engineering Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine %A Ahmet Haşim Yurttakal , Hasan Erbay , Recep Arslan %T Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine %D 2020 %J Electronic Letters on Science and Engineering %P 1305-8614- %V 16 %N 2 %R %U
ISNAD Yurttakal, Ahmet Haşim , Erbay, Hasan , Arslan, Recep . "Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine". Electronic Letters on Science and Engineering 16 / 2 (December 2020): 77-83 .
AMA Yurttakal A , Erbay H , Arslan R . Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine. Electronic Letters on Science and Engineering. 2020; 16(2): 77-83.
Vancouver Yurttakal A , Erbay H , Arslan R . Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine. Electronic Letters on Science and Engineering. 2020; 16(2): 77-83.
IEEE A. Yurttakal , H. Erbay and R. Arslan , "Grading Brain Histopathological Images Using Deep Residual Networks and Support Vector Machine", Electronic Letters on Science and Engineering, vol. 16, no. 2, pp. 77-83, Dec. 2021
Authors of the Article
Ahmet Haşim YURTTAKAL [1]
Hasan ERBAY [2]
Recep ARSLAN [3]
Submit Article
Archive
Editorial Board
Contact