A Deep Segmentation Network of Stent Structs Based on IoT for Interventional Cardiovascular Diagnosis

The Internet of Things (IoT) technology has been widely introduced to the existing medical system. An eHealth system based on IoT devices gained widespread popularity. In this article, we propose an framework provide autonomous solution for patients with interventional cardiovascular diseases. framework, wearable sensors are used collect a patient's health data, which is daily monitored by remote doctor. When monitoring data abnormal, doctor will ask image acquisition internal conditions. We leverage edge computing classify these training images local base classifier; thereafter, pseudo-labels generated according its output. Moreover, deep segmentation network leveraged stent structs in intravascular optical coherence tomography and intravenous ultrasound patients. experimental results demonstrate that doctors perform real-time visual communication complete telesurgery. experiments, adopt U-net backbone pretrained SeResNet34 as encoder segment structs. Meanwhile, series comparative experiments have conducted effectiveness our method accuracy, sensitivity, Jaccard, dice.