Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
The development of the Internet of Things (IoT) plays an important role in smart health. The combination of IoT and ultrasound has great potential applications in telemedicine. The medical information in the echocardiogram stimulates the image analysis of ultrasound IoT devices. Medical image segmentation is a fundamental step in medical image analysis for providing help to the subsequent tasks. However, accurate left ventricular (LV) segmentation in echocardiography is a challenging task due to the cross-vendor and cross-center, multiview ultrasound image characteristics. We introduce an intermediate supervision deep neural networks method in this article, named as deep atrous pyramid intermediate supervision (DAPIS). The SAD block is used as a fixed feature extractor, pyramid pooling module is used to extract context semantic information, global attention upsampling is used for feature fusion module, and intermediate supervision is used to learn a better semantic representation. The performance of the model is evaluated using two echocardiographic data: 1) public data set (CAMUS) and 2) self-made data set (total 18906 images from 160 patients). Sufficient experiments show that DAPIS is prominent generalization and robustness, surpassing other state-of-the-art methods. The correlation graph and Bland-Altman analysis show good clinical correlation, proving the clinical potential of the model.