Segmentation of precursor lesions in cervical cancer using convolutional neural networks Rahim Aǧzi (Serviks) Kanserinde Öncü Lezyonlarin Evrişimsel Sinir Aǧlariyla Bölütlenmesi

Albayrak A., Unlu A., Calik N., BİLGİN G., Turkmen I., ÇAKIR A., ...More

25th Signal Processing and Communications Applications Conference, SIU 2017, Antalya, Turkey, 15 - 18 May 2017, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/siu.2017.7960459
  • City: Antalya
  • Country: Turkey
  • Keywords: Cervical cancer, convolutional neural networks, histopathological images, precursor lesions, segmentation
  • Istanbul Medipol University Affiliated: Yes

Abstract

Cervical carcinoma is one of the frequently seen cancers in the world and in our country, develops from precursor lesions. These precursor lesions are analyzed by pathologists so that the diagnosis of the disease can be made. In this study, a system that performs automatic detection of pre-cancerous lesions was performed using the convolutional neural networks (CNNs). In the training phase, lesion recognition performance of the proposed system has reached 92%. Thereafter, whole image was segmented by using 60 × 60 pixel tiles during the training phase. After all, the precursor lesions were segmented with 81.71% Dice coefficient.