A Novel Approach for Deep Learning Based Cancer Classification Based on Feature Extraction and Selection on Histopathological Images Histopatolojik G r nt lerde znitelik ikarma ve Se meye Dayali Derin grenme Tabanli Kanser Siniflandirmasi i in Yeni Bir Yaklasim

Baz I., Bozkurt T. N., YÜKSEL M. E.

33rd IEEE Conference on Signal Processing and Communications Applications, SIU 2025, İstanbul, Türkiye, 25 - 28 Haziran 2025, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu66497.2025.11112144
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: AlexNet, decision support system, histopathological image classification, ResNet-101
  • Erciyes Üniversitesi Adresli: Evet

Özet

Biopsy is the gold standard for definitive diagnosis of cancer. Since the histopathological images obtained in the biopsy process are quite large and contain too much detail, their analysis is quite difficult and time-consuming. Therefore, developing a system that can alleviate the workload of pathologists and support them in making fast and accurate diagnoses is of great importance. In this study, a method that includes feature extraction, feature ranking, feature selection and classification processes is proposed for the classification of histopathological images. The obtained results showed that the presented method is quite successful in the rapid and high-accuracy classification of histopathological images.