The use of echocardiography ventricle segmentation can obtain ventricular volume parameters, and it is helpful to evaluate cardiac function. However, the ultrasound images have the characteristics of high noise and difficulty in segmentation, bringing huge workload to segment the object region manually. Meanwhile, the automatic segmentation technology cannot guarantee the segmentation accuracy. In order to solve this problem, a novel algorithm framework is proposed to segment the ventricle. Firstly, faster region-based convolutional neural network is used to locate the object to get the region of interest. Secondly, K-means is used to pre-segment the image; then a mean shift with adaptive bandwidth of kernel function is proposed to segment the region of interest. Finally, the region growing algorithm is used to get the object region. By this framework, ventricle is obtained automatically without manual localization. Experiments prove that this framework can segment the object accurately, and the algorithm of adaptive mean shift is more stable and accurate than the mean shift with fixed bandwidth on quantitative evaluation. These results show that the method in this paper is helpful for automatic segmentation of left ventricle in echocardiography.
Objective To summarize the characteristics and management of pregnancy complicated with aortic dissection, and to explore the reasonable diagnosis and treatment plan. Methods The clinical data of 10 patients of pregnancy complicated with aortic dissection in Wuhan Tongji Hospital from January 2011 to June 2017 were collected. Their age was 25.2 (21-29) years. Results In the 10 patients, the majority (8 patients) were primipara, and most of them were in the late stages of pregnancy (5 patients) and puerperal (4 patients). Among them, 1 patient had gestational hypertension, and the blood pressure of the left and right upper extremities was significantly abnormal (initial blood pressure: left upper limb blood pressure: 90/60 mm Hg, right upper limb blood pressure: 150/90 mm Hg). The major clinical manifestations were severe chest and back pain which happened suddenly, with D-dimmer and C-creative protein increased which may be associated with inflammatory reaction. All patients were diagnosed by thoracoabdominal aortic CTA, including 5 patients of Stanford type A dissection and 5 patients of Stanford type B dissection. In the 10 patients, 1 patient refused surgery and eventually died of aortic rupture with the death of fetus before birth. And the remaining 9 patients underwent surgical treatment, 3 patients of endovascular graft exclusion for thoracic aortic stent graft, 2 patients underwent Bentall operation, 1 patient with Bentall + total aortic arch replacement + vascular thoracic aortic stent graft, 1 patient with Bentall operation combined with endovascular graft exclusion for thoracic aortic stent graft, 1 patient with Bentall + coronary artery bypass grafting, 1 patient of thoracoabdominal aortic vascular replacement. Among them, 1 patient underwent endovascular graft exclusion for thoracic aortic stent graft died of severe postoperative infection, and the remaining 8 patients were discharged from hospital. Nine patients were single birth, among them 5 newborn patients had severe asphyxia, 4 patients had mild asphyxia. Finally, 3 neonates died of severe complications, and the remaining 6 survived. Conclusion The ratio of pregnancy with Stanford type A aortic dissection is far higher than in the general population, the possibility of fetal intrauterine asphyxia is larger, but through active and effective surgical and perioperative treatment, we can effectively save the life of mother and fetus.