TY - GEN
T1 - Automated Description and Workflow Analysis of Fetal Echocardiography in First-Trimester Ultrasound Video Scans
AU - Yasrab, Robail
AU - Alsharid, Mohammad
AU - Sarker, Md Mostafa Kamal
AU - Zhao, He
AU - Papageorghiou, Aris T.
AU - Noble, J. Alison
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - This paper presents a novel, fully-automatic framework for fetal echocardiography analysis of full-length routine first-trimester fetal ultrasound scan video. In this study, a new deep learning architecture, which considers spatio-temporal information and spatial attention, is designed to temporally partition ultrasound video into semantically meaningful segments. The resulting automated semantic annotation is used to analyse cardiac examination workflow. The proposed 2D+t convolution neural network architecture achieves an A1 accuracy of 96.37%, F1 of 95.61%, and precision of 96.18% with 21.49% fewer parameters than the smallest ResNet-based architecture. Automated deep-learning based semantic annotation of unlabelled video scans (n=250) shows a high correlation with expert cardiac annotations (ρ = 0.96, p = 0.0004), thereby demonstrating the applicability of the proposed annotation model for echocardiography workflow analysis.
AB - This paper presents a novel, fully-automatic framework for fetal echocardiography analysis of full-length routine first-trimester fetal ultrasound scan video. In this study, a new deep learning architecture, which considers spatio-temporal information and spatial attention, is designed to temporally partition ultrasound video into semantically meaningful segments. The resulting automated semantic annotation is used to analyse cardiac examination workflow. The proposed 2D+t convolution neural network architecture achieves an A1 accuracy of 96.37%, F1 of 95.61%, and precision of 96.18% with 21.49% fewer parameters than the smallest ResNet-based architecture. Automated deep-learning based semantic annotation of unlabelled video scans (n=250) shows a high correlation with expert cardiac annotations (ρ = 0.96, p = 0.0004), thereby demonstrating the applicability of the proposed annotation model for echocardiography workflow analysis.
KW - echocardiography
KW - fetal heart
KW - first trimester
KW - spatio-temporal analysis
KW - ultrasound
UR - http://www.scopus.com/inward/record.url?scp=85172129708&partnerID=8YFLogxK
U2 - 10.1109/ISBI53787.2023.10230422
DO - 10.1109/ISBI53787.2023.10230422
M3 - Conference contribution
AN - SCOPUS:85172129708
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023
PB - IEEE Computer Society
T2 - 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023
Y2 - 18 April 2023 through 21 April 2023
ER -