Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency

• Published in: Ultrasonography (Seoul, Korea) Vol. 40; no. 1; pp. 7 - 22
• Main Authors: Yi, Jonghyon, Kang, Ho Kyung, Kwon, Jae-Hyun, Kim, Kang-Sik, Park, Moon Ho, Seong, Yeong Kyeong, Kim, Dong Woo, Ahn, Byungeun, Ha, Kilsu, Lee, Jinyong, Hah, Zaegyoo, Bang, Won-Chul
• Format: Journal Article
• Language: English
• Published: Korea (South) Korean Society of Ultrasound in Medicine 01.01.2021; 대한초음파의학회
• Subjects: Algorithms; Artificial intelligence; Classification; computer-aided diagnosis; convolutional neural network; Datasets; Deep learning; Random variables; Real time; Signal processing; Special Review of Artifical Intelligence (Part 1); Thyroid gland; Trends; Ultrasonic imaging; workflow efficiency; 방사선과학; Deep learning; Artificial intelligence; Workflow efficiency; Convolutional neural network; Computer-aided diagnosis
• ISSN: 2288-5919; 2288-5943
• DOI: 10.14366/usg.20102

In this review of the most recent applications of deep learning to ultrasound imaging, the architectures of deep learning networks are briefly explained for the medical imaging applications of classification, detection, segmentation, and generation. Ultrasonography applications for image processing and diagnosis are then reviewed and summarized, along with some representative imaging studies of the breast, thyroid, heart, kidney, liver, and fetal head. Efforts towards workflow enhancement are also reviewed, with an emphasis on view recognition, scanning guide, image quality assessment, and quantification and measurement. Finally some future prospects are presented regarding image quality enhancement, diagnostic support, and improvements in workflow efficiency, along with remarks on hurdles, benefits, and necessary collaborations.