Introduction: The echocardiographic measurement of left ventricular ejection fraction (LVEF) is fundamental to the diagnosis and classification of patients with heart failure (HF).
Methods: This paper aimed to quantify LVEF automatically and accurately with the proposed pipeline method based on deep neural networks and ensemble learning. Within the pipeline, an Atrous Convolutional Neural Network (ACNN) was first trained to segment the left ventricle (LV), before employing the area-length formulation based on the ellipsoid single-plane model to calculate LVEF values. This formulation required inputs of LV area, derived from segmentation using an improved Jeffrey’s method, as well as LV length, derived from a novel ensemble learning model. To further improve the pipeline’s accuracy, an automated peak detection algorithm was used to identify end-diastolic and end-systolic frames, avoiding issues with human error. Subsequently, single-beat LVEF values were averaged across all cardiac cycles to obtain the final LVEF.
Results: This method was developed and internally validated in an open-source dataset containing 10,030 echocardiograms. The Pearson’s correlation coefficient was 0.83 for LVEF prediction compared to expert human analysis (p < 0.001), with a subsequent area under the receiver operator curve (AUROC) of 0.98 (95% confidence interval 0.97 to 0.99) for categorisation of HF with reduced ejection (HFrEF; LVEF<40%). In an external dataset with 200 echocardiograms, this method achieved an AUC of 0.90 (95% confidence interval 0.88 to 0.91) for HFrEF assessment.
Conclusion: The automated neural network-based calculation of LVEF is comparable to expert clinicians performing time-consuming, frame-by-frame manual evaluations of cardiac systolic function.
Introduction: To develop a novel deep learning model to automatically grade adenoid hypertrophy, based on nasal endoscopy, and asses its performance with that of E.N.T. clinicians.
Methods: A total of 3,179 nasoendoscopic images, including 4-grade adenoid hypertrophy (Parikh grading standard, 2006), were collected to develop and test deep neural networks. MIB-ANet, a novel multi-scale grading network, was created for adenoid hypertrophy grading. A comparison between MIB-ANet and E.N.T. clinicians was conducted.
Results: In the SYSU-SZU-EA Dataset, the MIB-ANet achieved 0.76251 F1 score and 0.76807 accuracy, and showed the best classification performance among all of the networks. The visualized heatmaps show that MIB-ANet can detect whether adenoid contact with adjacent tissues, which was interpretable for clinical decision. MIB-ANet achieved at least 6.38% higher F1 score and 4.31% higher accuracy than the junior E.N.T. clinician, with much higher (80× faster) diagnosing speed.
Discussion: The novel multi-scale grading network MIB-ANet, designed for adenoid hypertrophy, achieved better classification performance than four classical CNNs and the junior E.N.T. clinician. Nonetheless, further studies are required to improve the accuracy of MIB-ANet.