EFFICIENT SKIN CANCER DIAGNOSIS VIA CNN-BASED BINARY CLASSIFICATION OF DERMATOLOGICAL IMAGES

Creative Commons License

Noğay H. S.

7th INTERNATIONAL CONGRESS ON ENGINEERING SCIENCES AND MULTIDISCIPLINARY APPROACHES, İstanbul, Türkiye, 25 - 26 Mayıs 2024, ss.227-235, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.227-235
  • Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
  • Bursa Uludağ Üniversitesi Adresli: Evet

Özet

EFFICIENT SKIN CANCER DIAGNOSIS VIA CNN‐BASED BINARY CLASSIFICATION OF DERMATOLOGICAL IMAGES H. Selcuk NOGAY Bursa Uludağ University Vocational School of Technical Sciences Department of Electricity and Energy Bursa / Türkiye Abstract: Skin cancer is one of the most common types of cancer, and early diagnosis is crucial for effective treatment. This study focuses on the application of a pre-trained Convolutional Neural Network (CNN) model, specifically ShuffleNet, for the binary classification of dermatological images to diagnose skin cancer. The study aims to develop an efficient and accurate method for distinguishing between cancerous and non cancerous skin lesions. The model achieved an accuracy rate of 87%, demonstrating its potential as a reliable tool for skin cancer diagnosis. The proposed method offers a cost effective and time-efficient solution for the early detection of skin cancer, which can be easily integrated into clinical practice. Keywords: Deep Learning, CNN, Skin Cancer Detection, Shufflenet, Transfer Learning