Spatio-Temporal Partitioning And Description Of Full-Length Routine Fetal Anomaly Ultrasound Scans

Harshita Sharma, Richard Droste, Pierre Chatelain, Lior Drukker, Aris T. Papageorghiou, J.Alison Noble
December 2019
DOI ORA IEEE BibTeX

Abstract

This paper considers automatic clinical workflow description of full-length routine fetal anomaly ultrasound scans using deep learning approaches for spatio-temporal video analysis. Multiple architectures consisting of 2D and 2D + t CNN, LSTM, and convolutional LSTM are investigated and compared. The contributions of short-term and long-term temporal changes are studied, and a multi-stream framework analysis is found to achieve the best top-l accuracy =0.77 and top-3 accuracy =0.94. Automated partitioning and characterisation on unlabelled full-length video scans show high correlation (ρ=0.95, p=0.0004) with workflow statistics of manually labelled videos, suggesting practicality of proposed methods.

Type
Conference paper
Publication
IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

BibTex

@inproceedings{sharma_spatio-temporal_2019,
title = {Spatio-Temporal Partitioning And Description Of Full-Length Routine Fetal Anomaly Ultrasound Scans},
author = {Sharma, H. and Droste, R. and Chatelain, P. and Drukker, L. and Papageorghiou, A.T. and Noble, J.A.},
booktitle = {2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)},
doi = {10.1109/ISBI.2019.8759149},
note = {ISSN: 1945-7928},
pages = {987--990},
year = {2019}
}
2D + t CNN automatic clinical workflow description biomedical ultrasonics clinical workflow Computational modeling Computer architecture convolutional LSTM convolutional neural nets Deep learning deep learning approaches Feature extraction Fetal anomaly scan full-length routine fetal anomaly ultrasound scans learning (artificial intelligence) long-term temporal changes manually labelled videos medical image processing multiple architectures multistream framework analysis obstetrics short-term temporal changes spatio-temporal analysis spatio-temporal partitioning spatio-temporal video analysis spatiotemporal phenomena statistical analysis Three-dimensional displays Two dimensional displays Ultrasonic imaging ultrasound unlabelled full-length video scans video classification video signal processing workflow statistics

Related