Application of machine learning and deep learning to thyroid imaging: where do we stand?

Researchers

Journal

Modalities

Models

Abstract

Ultrasonography (US) is a primary diagnostic tool for assessing the risk of malignancy and informing decisions regarding the use of fine-needle aspiration (FNA) as well as management decisions after FNA in patients with thyroid nodules. However, since US image interpretation is operator-dependent and interobserver variability is moderate-to-substantial, unnecessary FNAs and/or diagnostic surgery are common in practice. Artificial intelligence (AI)-based computer-aided diagnosis (CAD) systems have been introduced to help with the accurate and consistent interpretation of US features, ultimately leading to a decrease in unnecessary FNAs. This review provides a developmental overview of the current AI-based CAD system used for thyroid nodules and describes the future developmental direction of this system for the personalized and optimized management of thyroid nodules.