Feature Extraction for Histopathological Images Using Convolutional Neural Network

Hatipoglu N., BİLGİN G.

24th Signal Processing and Communication Application Conference (SIU), Zonguldak, Türkiye, 16 - 19 Mayıs 2016, ss.645-648 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu.2016.7495823
  • Basıldığı Şehir: Zonguldak
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.645-648
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

In this study, it is intended to increase the classification accuracy results of histopathalogical images by evaluating spatial relations. As a first step, Convolutional Neural Network (CNN) based features are extracted in the original RGB color space of digital histopathalogical images. Training data sets are formed by selecting equal number of different cellular and extra-cellular structures in spatial domain from the images. Classification models of each training data set are obtained by utilizing CNN (as a supervised classifier), Support Vector Machine (SVM) and Random Forest (RF) methods. Visual classification maps and output tables which are obtained from supervised training methods are presented for comparison purpose in the experimental results section.