ABSTRACT
Much attention has been given to machine learning and its perceived impact in radiology, particularly in light of recent success with image classification in international competitions. However, machine learning is likely to impact radiology outside of image interpretation long before a fully functional "machine radiologist" is implemented in practice. Here, we describe an overview of machine learning, its application to radiology and other domains, and many cases of use that do not involve image interpretation. We hope that better understanding of these potential applications will help radiology practices prepare for the future and realize performance improvement and efficiency gains.
Subject(s)
Image Enhancement/methods , Image Interpretation, Computer-Assisted/methods , Machine Learning , Pattern Recognition, Automated/methods , Radiology , Algorithms , Humans , WorkflowABSTRACT
We present the sonographic features of a second-trimester fetus diagnosed with a bradyarrhythmia at 19 weeks' gestation. The mother carried a diagnosis of Sjögren syndrome, including the presence of SSA and SSB antibodies. Ultrasound M-mode and fetal echocardiogram revealed the etiology of the bradycardia to be a complete fetal congenital heart block, likely due to transplacental passage of autoimmune anti-Ro/SSA and anti-La/SSB antibodies. Consequential to the congenital heart block, the fetus developed hydrops fetalis at 21 weeks' gestational age. We discuss the 2 major etiologies of congenital heart block and the implications in subsequent pregnancies.
