An Accurate and Fast Cardio-views Classification System Based on Fused Deep Features and LSTM

A.I. Shahin, Sultan Almotairi
2020 IEEE Access  
Echocardiography is an ultrasound-based imaging modality that helps the physician to visualize heart chambers and valves motion activity. Recently, deep learning plays an important role in several clinical computer-assisted diagnostic systems. There is a real need to employ deep learning methodologies to increase such systems. In this paper, we proposed a deep learning system to classify several echocardiography views and identify its physiological location. Firstly, the spatial CNN features
more » ... ial CNN features are extracted from each frame in the echo-motion. Secondly, we proposed novel temporal features based on neutrosophic sets. The neutrosophic temporal motion features are extracted from echo-motion activity. To extract the deep CNN features, we activated a pre-trained deep ResNet model. Then, both spatial and neutrosophic temporal CNN features were fused based on features concatenation technique. Finally, the fused CNN features were fed into deep long short-term memory network to classify echo-cardio views and identify their location. During our experiments, we employed a public echocardiography dataset that consisted of 432 videos for eight cardio-views. We have investigated several pre-trained network activation performance. ResNet architecture activation achieved the best accuracy score among several pre-trained networks. The Proposed system based on fused spatial neutrosophic temporal deep features achieved 96.3% accuracy and 95.75% sensitivity. For the classification of cardio-views location, the proposed system achieved 99.1% accuracy. The proposed system achieved more accuracy than previous deep learning methods with a significant decrease in the training time cost. The experimental results showed promising results for our proposed approach. INDEX TERMS Ultrasound, echocardiography, cardio-views, deep learning, neutrosophic temporal desriptors, CNN features fusion, LSTM. 135184 This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ VOLUME 8, 2020 SULTAN ALMOTAIRI received the B.Sc., M.Sc.,
doi:10.1109/access.2020.3010326 fatcat:x4h4x7sfwnfntavf2r2y2tjipi