TY - JOUR
T1 - A Survey of Deep-Learning Applications in Ultrasound
T2 - Artificial Intelligence–Powered Ultrasound for Improving Clinical Workflow
AU - Akkus, Zeynettin
AU - Cai, Jason
AU - Boonrod, Arunnit
AU - Zeinoddini, Atefeh
AU - Weston, Alexander D.
AU - Philbrick, Kenneth A.
AU - Erickson, Bradley J.
N1 - Publisher Copyright:
© 2019 American College of Radiology
PY - 2019/9
Y1 - 2019/9
N2 - Ultrasound is the most commonly used imaging modality in clinical practice because it is a nonionizing, low-cost, and portable point-of-care imaging tool that provides real-time images. Artificial intelligence (AI)–powered ultrasound is becoming more mature and getting closer to routine clinical applications in recent times because of an increased need for efficient and objective acquisition and evaluation of ultrasound images. Because ultrasound images involve operator-, patient-, and scanner-dependent variations, the adaptation of classical machine learning methods to clinical applications becomes challenging. With their self-learning ability, deep-learning (DL) methods are able to harness exponentially growing graphics processing unit computing power to identify abstract and complex imaging features. This has given rise to tremendous opportunities such as providing robust and generalizable AI models for improving image acquisition, real-time assessment of image quality, objective diagnosis and detection of diseases, and optimizing ultrasound clinical workflow. In this report, the authors review current DL approaches and research directions in rapidly advancing ultrasound technology and present their outlook on future directions and trends for DL techniques to further improve diagnosis, reduce health care cost, and optimize ultrasound clinical workflow.
AB - Ultrasound is the most commonly used imaging modality in clinical practice because it is a nonionizing, low-cost, and portable point-of-care imaging tool that provides real-time images. Artificial intelligence (AI)–powered ultrasound is becoming more mature and getting closer to routine clinical applications in recent times because of an increased need for efficient and objective acquisition and evaluation of ultrasound images. Because ultrasound images involve operator-, patient-, and scanner-dependent variations, the adaptation of classical machine learning methods to clinical applications becomes challenging. With their self-learning ability, deep-learning (DL) methods are able to harness exponentially growing graphics processing unit computing power to identify abstract and complex imaging features. This has given rise to tremendous opportunities such as providing robust and generalizable AI models for improving image acquisition, real-time assessment of image quality, objective diagnosis and detection of diseases, and optimizing ultrasound clinical workflow. In this report, the authors review current DL approaches and research directions in rapidly advancing ultrasound technology and present their outlook on future directions and trends for DL techniques to further improve diagnosis, reduce health care cost, and optimize ultrasound clinical workflow.
KW - Artificial intelligence in ultrasound
KW - breast lesion
KW - deep learning in ultrasound
KW - liver lesion
KW - thyroid nodule
UR - http://www.scopus.com/inward/record.url?scp=85071017712&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071017712&partnerID=8YFLogxK
U2 - 10.1016/j.jacr.2019.06.004
DO - 10.1016/j.jacr.2019.06.004
M3 - Article
C2 - 31492410
AN - SCOPUS:85071017712
SN - 1546-1440
VL - 16
SP - 1318
EP - 1328
JO - Journal of the American College of Radiology
JF - Journal of the American College of Radiology
IS - 9
ER -