BREAST CANCER DIAGNOSIS BY USING DEEP LEARNING

Creative Commons License

Noğay H. S.

10th INTERNATIONAL CONGRESS ON ENGINEERING AND TECHNOLOGY MANAGEMENT, İstanbul, Türkiye, 14 - 15 Ekim 2023, ss.231-237, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.231-237
  • Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
  • Bursa Uludağ Üniversitesi Adresli: Evet

Özet

Abstract: Breast cancer is one of the most common and serious types of cancer, especially in women. Definitive treatment of breast cancer may vary depending on early, rapid, and accurate diagnosis. The need for scientific studies that can contribute to early diagnosis continues today. It is a fact that studies are being carried out to use deep learning methods in every field of medicine and developments are being made every day. In this study, a deep learning application that can diagnose breast cancer and classify benign, malignant and normally cancerous tumors was implemented using the deep convolutional neural networks (DCNN) method. Training and testing results show that the pre-trained DCNN model proposed in the study has a very promising performance in breast cancer diagnosis. Keywords: Deep Learning, Pre-Trained, CNN, GoogleNet, TL, Breast Cancer