Echocardiography image quality assessment is not a trivial issue in transthoracic examination. As the in vivo examination of heart structures gained prominence in cardiac diagnosis, it has been affirmed that accurate diagnosis of the left ventricle functions is hugely dependent on the quality of echo images. Up till now, visual assessment of echo images is highly subjective and requires specific definition under clinical pathologies. While poor-quality images impair quantifications and diagnosis, the inherent variations in echocardiographic image quality standards indicates the complexity faced among different observers and provides apparent evidence for incoherent assessment under clinical trials, especially with less experienced cardiologists. In this research, our aim was to analyse and define specific quality attributes mostly discussed by experts and present a fully trained convolutional neural network model for assessing such quality features objectively. A total of 1,650 anonymized B-Mode images with dissimilar frame lengths were stratified from most popular ultrasound vendors equipment and clinical quality scores were provided for each echo cine by Cardiologists at England's Hammersmith Hospital which fed our multi-stream architecture model. The regression model assesses the quality features for depth-gain, chamber clarity, interventricular (on-Axis) orientation and foreshortening of the left ventricle. Four independent scores are thus displayed on each frame which compares against cardiologists' manually assigned scores to validate the degree of objective accuracy or its absolute errors. Absolute errors were found to be ±0.02 and ±0.12 for model and inter observer variability, respectively. We achieved a computation speed of 0.0095 ms per frame on GeForce 970, with feasibility for 2D/3D real-time deployment. The research outcome establishes the modality for the objective standardization of 2D echocardiographic image quality and provides a consistent objective scoring mechanism for echo image reliability and diagnosis.

Purpose: Echocardiography is the most commonly used modality for assessing the heart in clinical practice. In an echocardiographic exam, an ultrasound probe samples the heart from different orientations and positions, thereby creating different viewpoints for assessing the cardiac function. The determination of the probe viewpoint forms an essential step in automatic echocardiographic image analysis. Approach: In this study, convolutional neural networks are used for the automated identification of 14 different anatomical echocardiographic views (larger than any previous study) in a dataset of 8732 videos acquired from 374 patients. Differentiable architecture search approach was utilized to design small neural network architectures for rapid inference while maintaining high accuracy. The impact of the image quality and resolution, size of the training dataset, and number of echocardiographic view classes on the efficacy of the models were also investigated. Results: In contrast to the deeper classification architectures, the proposed models had significantly lower number of trainable parameters (up to 99.9% reduction), achieved comparable classification performance (accuracy 88.4% to 96%, precision 87.8% to 95.2%, recall 87.1% to 95.1%) and real-time performance with inference time per image of 3.6 to 12.6 ms. Conclusion: Compared with the standard classification neural network architectures, the proposed models are faster and achieve comparable classification performance. They also require less training data. Such models can be used for real-time detection of the standard views. (C) 2021 Society of Photo-Optical Instrumentation Engineers (SPIE)