Fuzzy Local Information C-means Algorithm for Histopathological Image Segmentation

Cetin M., Dokur Z., Ölmez T.

International Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science (EBBT), İstanbul, Türkiye, 24 - 26 Nisan 2019 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/ebbt.2019.8742034
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: fuzzy c-means, fuzzy local information c-means, clustering, histopathological image segmentation, nuclei segmentation, computer aided diagnosis
  • İstanbul Teknik Üniversitesi Adresli: Evet

Özet

Accurate analysis of cellular structures has great importance for cancer diagnosis in histopathological images. Manual analysis of sections carried out by pathologists is time-consuming and costly. Analysis of cell structures with computer aid supports pathologists to diagnose cancer easily. In this paper, automated cell nuclei segmentation from histopathological images is investigated by using Fuzzy Local Information C-means Clustering (FLICM) Method. The Cancer Genome Atlas data set annotated by expert pathologists is used to evaluate the method. Compared with the other related studies, the highest f-measure and overlap values are obtained with this method.