Explicit and automatic ejection fraction assessment on 2D cardiac ultrasound with a deep learning-based approach.

BACKGROUND: Ejection fraction (EF) is a key parameter for assessing cardiovascular functions in cardiac ultrasound, but its manual assessment is time-consuming and subject to high inter and intra-observer variability. Deep learning-based methods have the potential to perform accurate fully automatic EF predictions but suffer from a lack of explainability and interpretability. This study proposes a fully automatic method to reliably and explicitly evaluate the biplane left ventricular EF on 2D echocardiography following the recommended modified Simpson's rule. METHODS: A deep learning model was trained on apical 4 and 2-chamber echocardiography to segment the left ventricle and locate the mitral valve. Predicted segmentations are then validated with a statistical shape model, which detects potential failures that could impact the EF evaluation. Finally, the end-diastolic and end-systolic frames are identified based on the remaining LV segmentations' areas and EF is estimated on all available cardiac cycles. RESULTS: Our approach was trained on a dataset of 783 patients. Its performances were evaluated on an internal and external dataset of respectively 200 and 450 patients. On the internal dataset, EF assessment achieved a mean absolute error of 6.10% and a bias of 1.56 ± 7.58% using multiple cardiac cycles. The approach evaluated EF with a mean absolute error of 5.39% and a bias of -0.74 ± 7.12% on the external dataset. CONCLUSION: Following the recommended guidelines, we proposed an end-to-end fully automatic approach that achieves state-of-the-art performance in biplane EF evaluation while giving explicit details to clinicians.

Beta and Theta Oscillations Correlate With Subjective Time During Musical Improvisation in Ecological and Controlled Settings: A Single Subject Study.

In this paper, we describe the results of a single subject study attempting at a better understanding of the subjective mental state during musical improvisation. In a first experiment, we setup an ecological paradigm measuring EEG on a musician in free improvised concerts with an audience, followed by retrospective rating of the mental state of the improviser. We introduce Subjective Temporal Resolution (STR), a retrospective rating assessing the instantaneous quantization of subjective timing of the improviser. We identified high and low STR states using Hidden Markov Models in two performances, and were able to decode those states using supervised learning on instantaneous EEG power spectrum, showing increases in theta and alpha power with high STR values. In a second experiment, we found an increase of theta and beta power when experimentally manipulating STR in a musical improvisation imagery experiment. These results are interpreted with respect to previous research on flow state in creativity, as well as with the temporal processing literature. We suggest that a component of the subjective state of musical improvisation may be reflected in an underlying mechanism related to the subjective quantization of time. We also demonstrate the feasibility of single case studies of musical improvisation using brain activity measurements and retrospective reports, by obtaining consistent results across multiple sessions.