Comparison of Type-2 Fuzzy Inference Method and Deep Neural Networks for Mass Detection from Breast Ultrasonography Images

Creative Commons License

UZUNHİSARCIKLI E., GÖREKE V., SARI V.

Cumhuriyet Science Journal, cilt.41, sa.4, ss.968-975, 2020 (Hakemli Dergi)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 41 Sayı: 4
  • Basım Tarihi: 2020
  • Doi Numarası: 10.17776/csj.691683
  • Dergi Adı: Cumhuriyet Science Journal
  • Derginin Tarandığı İndeksler: Directory of Open Access Journals, TR DİZİN (ULAKBİM)
  • Sayfa Sayıları: ss.968-975
  • Sivas Cumhuriyet Üniversitesi Adresli: Evet

Özet

In this study, mass detection from breast ultrasonography images was realized using deep neural networks. Dataset is a collection of publicly available ultrasonography images which were classified by their biopsy results. A total of 153 breast ultrasonography images that contain 89 malign and 64 benign tumours were used. Image augmentation and deep neural network software was developed using Python 3,5 environment on Visual Studio Community 2017 IDE. A hybrid method including Keras ImageDataGenerator Class and image preprocessing techniques was introduced. Twenty images from both classes were randomly split from the dataset for testing after the network was designed. The network had a success rate of 100% at an epoch value of 70. The result of this study was compared with the result of another study that implemented type-2 fuzzy inference system with a success rate of 99,34%.
As a conclusion, it can be expressed that the deep neural networks are more successful than fuzzy inference systems in tumour detection from breast ultrasonography images. Therefore, it can be more convenient to use deep neural network technology in computer aided detection systems for mass detection from breast ultrasonography images.