Deep learning framework for interpretable quality control of echocardiography video

The model achieved a mean average precision of 0.962 for AS detection, with PA yielding average frame errors of 1.603 <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:semantics><mml:mo>±</mml:mo> <mml:annotation>$ \pm $</mml:annotation></mml:semantics> </mml:math> 1.181 (end-diastolic) and 1.681 <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:semantics><mml:mo>±</mml:mo> <mml:annotation>$ \pm $</mml:annotation></mml:semantics> </mml:math> 1.332 (end-systolic). The gain classification model demonstrated robust performance (Area Under the Curve > 0.98), and the overall processing speed reached 112.4 frames per second. On 203 randomly collected echo videos, the model achieved a kappa coefficient of 0.79 for rating consistency compared to expert evaluations CONCLUSIONS: Given the model's performance on the clinical dataset and its consistency with expert evaluations, our results indicate that the model not only delivers real-time, interpretable quality scores but also demonstrates strong clinical reliability.