The impact of deep learning on diagnostic performance in the differentiation of benign and malignant thyroid nodules.

Journal: Medical ultrasonography
PMID:

Abstract

AIMS: This study aims to use deep learning (DL) to classify thyroid nodules as benign and malignant with ultrasonography (US). In addition, this study investigates the impact of DL on the diagnostic success of radiologists with different experiences. Material and methods: This study included 576 US images of thyroid nodules. The dataset was divided into 80% training and 20% test sets. Four radiologists with different levels of experience classified the images in the test set as benign-malignant. A DL model was then trained with the train set and predicted benign-malignant for the test set. Then, the output of the DL model for each nodule in the test set was presented to 4 radiologists, who were asked to make a benign-malignant classification again considering these DL results.

Authors

  • Esat Kaba
    Radiology, Recep Tayyip Erdoğan Education and Research Hospital, Rize, TUR.
  • Merve Solak
    Department of Radiology, Recep Tayyip Erdogan University, Rize 53100, Turkey.
  • Ayşenur Topçu Varlık
    Recep Tayyip Erdogan University, Department of Radiology, Rize.
  • Yusuf Çubukçu
    Recep Tayyip Erdogan University, Department of Radiology, Rize.
  • Lütfullah Sağır
    Recep Tayyip Erdogan University, Department of Radiology, Rize.
  • Kubilay Muhammed Sünnetci
    Osmaniye Korkut Ata University, Department of Electrical and Electronics Engineering, Osmaniye, Kahramanmaraş Sütçü İmam University, Department of Electrical and Electronics Engineering, Kahramanmaraş.
  • Ahmet Alkan
    Department of Electrical and Electronics Engineering.
  • Hasan Gündoğdu
    Radiology, Recep Tayyip Erdoğan Education and Research Hospital, Rize, TUR.
  • Fatma Beyazal Çeliker
    Department of Radiology, Recep Tayyip Erdogan University, Rize 53100, Turkey.
  • Mehmet Beyazal
    Recep Tayyip Erdogan University, Department of Radiology, Rize.