The application of artificial intelligence (AI) technology to medical imaging has recently brought about tremendous excitement, and AI is making its way into clinical practice, thanks to the technical prowess of current deep learning technology compared with the machine learning methods of the past, the wide availability of digital medical images, and the increased capabilities of computing hardware [1-4]. AI has been tried for ultrasonography in various organs and systems, such as the thyroid, musculoskeletal system, breast, and abdomen, as discussed in detail in the focused review articles of this special issue [5-8], albeit not as extensively as some other radiological imaging modalities such as chest X-rays [9]. The potential role of AI is anticipated to enhance the quality of ultrasonographic images, to provide various forms of diagnostic support (e.g., automated characterization of findings on ultrasonographic images; extraction of quantitative or predictive information from ultrasonographic images, which is difficult for a human examiner to do based on visual observations; and automated detection or segmentation of various structures on ultrasonographic images), and to improve workflow efficiency [10]. The list of specific examples of AI applications to ultrasonography is expected to grow in the future.
展开▼
