Knowledge representation and learning of operator clinical workflow from full-length routine fetal ultrasound scan videos

• Published in: Medical image analysis Vol. 69; p. 101973
• Main Authors: Sharma, Harshita, Drukker, Lior, Chatelain, Pierre, Droste, Richard, Papageorghiou, Aris T., Noble, J. Alison
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.04.2021; Elsevier BV
• Subjects: Accuracy; Annotations; Artificial neural networks; Clinical workflow; Computer applications; Computer Simulation; Convolutional neural networks; Data analysis; Deep learning; Female; Fetal ultrasonography; Fetuses; Humans; Image quality; Interfaces; Knowledge representation; Learning algorithms; Machine learning; Model accuracy; Neural networks; Neural Networks, Computer; Pregnancy; Retrospective Studies; Scanning; Segments; Skill assessment; Skills; Spatio-temporal analysis; Statistical analysis; Training; Ultrasonic imaging; Ultrasonography, Prenatal; Ultrasound; Ultrasound image analysis; Video data; Video understanding; Workflow; Deep learning; Ultrasound image analysis; Knowledge representation; Spatio-temporal analysis; Fetal ultrasonography; Clinical workflow; Skill assessment; Video understanding; Convolutional neural networks

•A fully-automatic framework analysed operator clinical workflow in fetal ultrasound.•More than 200 hours of routine second-trimester scan video recordings were analysed.•Knowledge representation scheme was developed solely from full-length scan videos.•Dimensionality and complexity of raw video dat...