I7 - Echocardiographic Phase Detection Using Neural Networks
Elisabeth Sarah Lane, Neda Azarmehr, Jevgeni Jevsikov, James P Howard, Matthew Shun-shin, Darrel P Francis, Massoud Zolgharni
Accurate identification of end-diastolic and end-systolic frames in echocardiographic cine loops is essential when measuring cardiac function. Manual selection by human experts is challenging and error prone. This paper presents a deep neural network trained and tested on multi-centre patient data for accurate phase detection in apical four-chamber videos of arbitrary length, spanning several heartbeats, with performance indistinguishable from that of human experts.
Friday 9th July
I4-12 (short): Transfer Learning and Domain Adaptation - 13:45 - 14:30 (UTC+2)