Key result
Deep neural networks enabled fully automated real-time cardiac ultrasound measurements at 43 frames per second, yielding an accuracy of (-13.7 ± 8.6)% for EF and (-0.9 ± 4.6) mm for MAPSE.
Why the study?
Can deep neural networks be used to fully automate cardiac ultrasound measurements of EF and MAPSE in real-time?
Can deep neural networks be used to fully automate cardiac ultrasound measurements of EF and MAPSE in real-time?
Deep learning can enable fully automated, real-time echocardiographic measurements of EF and MAPSE at 43 frames per second, though accuracy requires further improvement.
Answers are grounded in this paper and cite their sources.
Accuracy shortfalls preclude routine use; hypothesis-generating for deep learning refinement in echocardiography.
Cardiac ultrasound measurements such as left ventricular volume, ejection fraction (EF) and mitral annular plane systolic excursion (MAPSE) are time consuming and highly observer dependent. In this work, we investigate if deep neural networks can be used to fully automate cardiac ultrasound measurements in real-time while scanning. One neural network was used for identifying and separate the cardiac views while a second neural network performed segmentation of the left ventricle. By using TensorFlow, FAST and the highly optimized cuDNN backend real-time runtime of the entire pipeline was achieved with an average frames per second of 43, thus enabling these measurements to be performed while an operator is scanning. The measurement accuracy was evaluated using a Bland-Altmann analysis on a dataset of 75 patients resulting in (-13.7 ± 8.6)% for EF and (-0.9 ± 4.6) mm for MAPSE. It is concluded that deep learning can be used to fully automate these measurements, however more work remains to improve the accuracy.
No takes yet. Share an insight, caveat, or question.
Smistad et al. (2018) studied this question. Deep neural networks was evaluated on Measurement accuracy for EF and MAPSE. Deep neural networks enabled fully automated real-time cardiac ultrasound measurements at 43 frames per second, yielding an accuracy of (-13.7 ± 8.6)% for EF and (-0.9 ± 4.6) mm for MAPSE.
Synapse has enriched 10 related papers. Consider them for comparative context: