ABSTRACT

As ultrasound (US) is a cheap, unharmful, and handy bedside imaging tool that provides instantaneous images, it is the most frequently used imaging modality in clinical routine. On the other hand, its operator dependability introduces variations in image acquisition and evaluation. To reduce this variability, there is an increased demand for an operator and interpreter independent US system that is powered with artificial intelligence (AI), which has been advancing and coming closer to be used in routine clinical applications. Recent advances in AI applications in computer vision have enabled us to identify conceptual and complex imaging features with the self-learning ability of AI models and efficient GPU computing power. This has resulted in vast opportunities such as providing AI models that are robust to variations with generalization ability for instantaneous image quality control, aiding to acquire optimal images, diagnosis of complex diseases, and improving the clinical workflow of US. In this chapter, we give an overview of AI-powered US applications in radiology and cardiology and research directions in rapidly evolving US that is powered with AI technology and present our viewpoint on future trends for the AI-powered US technology that aids physicians in diagnosing diseases, optimizes US workflow in clinics, and cuts healthcare cost.