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.
This paper performs a comprehensive study on the computer-aided detection for the medical diagnosis with deep learning. Based on the region convolution neural network and the prior knowledge of target, this algorithm uses the region proposal network, the region of interest pooling strategy, introduces the multi-task loss function: classification loss, bounding box localization loss and object rotation loss, and optimizes it by end-to-end. For medical image it locates the target automatically, and provides the localization result for the next stage task of segmentation. For the detection of left ventricular in echocardiography, proposed additional landmarks such as mitral annulus, endocardial pad and apical position, were used to estimate the left ventricular posture effectively. In order to verify the robustness and effectiveness of the algorithm, the experimental data of ultrasonic and nuclear magnetic resonance images are selected. Experimental results show that the algorithm is fast, accurate and effective.
Objective To investigate the feasibility and effectiveness of high tibial osteotomy (HTO) in treatment of chronic multi-ligament knee injury (MLKI) associated with lower extremity malalignment. Methods A clinical data of 14 patients (14 knees) of chronic MLKI associated with lower extremity malalignment, who were treated with HTO between January 2016 and September 2020, was retrospectively analyzed. There were 10 males and 4 females, with an average age of 30.5 years (range, 22-48 years). The causes of injury included traffic accident in 8 cases, bruising by a heavy object in 3 cases, falling from height in 2 cases, and twisting in 1 case. According to Schenck classification of knee dislocation (KD), there were 4 cases of KD-Ⅰ [2 cases of anterior cruciate ligament (ACL) and posterolateral complex (PLC) injuries and 2 cases of posterior cruciate ligament (PCL) and PLC injuries], 7 cases of KD-Ⅲ (all of ACL, PCL, and PLC injuries), and 3 cases of KD-Ⅳ. The preoperative hip-knee-ankle angle (HKA) was (167.1±4.7)°, and the posterior tibial slope angle (PTSA) was (16.3±2.7)°. The knee joint was severely unstable and the patients could not stand and walk normally. Among them, 5 cases of medial compartment cartilage were severely worn out (3 cases of Kellgren-Lawrence grading Ⅱ, 2 cases of grading Ⅲ) causing pain. After admission, 2 cases of KD-Ⅰ underwent HTO and ligament reconstruction in the first stage, 1 case of KD-Ⅲ and 1 case of KD-Ⅳ underwent HTO in the first stage and ligament reconstruction in the second stage; the remaining 10 patients only underwent HTO. Results All patients were followed up 12-50 months, with an average of 30 months. The incisions healed by first intention after operation, and no complications such as infection and deep vein thrombosis of the lower extremities occurred. At 12 months after operation, knee range of extension was –5°-0° (mean, –1.2°) and range of flexion was 110°-140° (mean, 125.5°). The Lachman test was negative in 11 cases and positive in 3 cases. The posterior drawer test was negative in 9 cases and positive in 5 cases. The 0/30° varus stress test was negative in 10 cases and positive in 4 cases. The 0/30° valgus stress test was negative in 13 cases and positive in 1 case. The visual analogue scale (VAS) score was significantly lower than that before operation (P<0.05), and the International Knee Documentation Committee (IKDC) score, Lysholm score, and Tegner score were all significantly higher than those before operation (P<0.05). The X-ray film reexamination at 12 months after operation showed that the HKA was (178.2±3.8)° and the PTSA was (8.6±2.4)°, which were significantly different from those before operation (P<0.05). All osteotomies achieved bone union, and the healing time was 3-11 months, with an average of 6.8 months. Conclusion For chronic MLKI associated with lower extremity malalignment, HTO can restore normal lower extremity alignment and improve knee joint function, which is a feasible salvage operation.
Objective To explore the effectiveness of the transforming growth factor-β1(TGF-β1) and tumor necrosis factor-α(TNF-α) inducing human bronchial epithelial(HBE) cells to optimize epithelia-mesenchymal transformation(EMT) model. Methods Blank control, TGF-β1 10 ng/ml, TNF-α 10 ng/ml, TGF-β1 10 ng/ml+TNF-α 10 ng/ml induced human epithelial cells for 24 hours. Then the change of morphological alteration were observed by applying CCK8, cells migration assay and Western blot technique. Results When TGF-β1 plus TNF-α induced human epithelial cells for 24 hours, most of HBE cells traits changed including morphological alteration from cobblestone to fusiform, connection between cells vanishing, intercellular space broadening. In the experiments of checking cell migration capacity by the vitro scratch test, the group spacing was 420.06±10.38 μm in the blank control group, 499.86±34.00 μm in the TGF-β1 10 ng/ml group, 514.93±10.56 μm in the TNF-α 10 ng/ml group, 569.68±33.58 μm in the TGF-β1 10 ng/ml+TNF-α10 ng/ml group. TGF-β1 cooperated with TNF-α led to scratch spacing narrowing significantly. Western blot analysis showed that expression of E-cadherin and Vimentin varied significantly in the TGF-β1+TNF-α group. Conclusion Inducing human bronchial epithelial cell by TGF-β1 cooperated with TNF-α optimizes EMT model.
ObjectiveTo summarize the clinical experience of extracorporeal membrane oxygenation (ECMO) in adult patients with cardiac surgery, analyze the risk factors associated with the mortality and other severe complications and to discuss prevention methods of complications during ECMO treatment.MethodsThe clinical data of 26 patients with cardiac surgery, who underwent ECMO because of cardiopulmonary insufficiency ect in Zhongshan Hospital, Fudan University from January 2012 to September 2017, were retrospectively analyzed. There were 19 males and 7 females aged 24–80 (58.0±13.9) years.ResultsTwelve (42.3%) patients successfully weaned from ECMO and six (23.1%) were discharged from hospital. Among 26 patients, 24 received VA ECMO (veno-arterial ECMO), including 5 after heart transplantation, 9 after heart valve surgery, and 3 were successfully weaned from ECMO. Seven patients with valvular surgery underwent ECMO within 48 hours due to refractory low cardiac output syndrome (LCOS). Eight patients underwent major angioplasty, 3 of whom were successfully weaned from ECMO. Four patients underwent coronary artery bypass grafting and other cardiac surgeries. Patients with VA ECMO were treated with femoral vein-femoral artery cannulation except for 2 patients undergoing femoral vein-radial artery cannulation after major angioplasty. Patients with VV ECMO (veno-venous ECMO) underwent femoral vein-jugular vein cannulation. After ECMO support, 10 patients with bleeding occurred, and 5 patients were successfully weaned from ECMO. All patients had transfusion therapy during the assist period, 7 patients had infection after ECMO support, 4 patients suffered severe distal limb ischemia. There was no significant difference in the lactic acid between the survival and the dead patients before and after ECMO support. However, the decline of serum lactic acid in the survivors was faster than that of the dead patients. The trend was the most significant within 6 h after the operation.ConclusionECMO is one of the significant treatments for LCOS and refractory hypoxemia after cardiac surgery. The type of cardiac surgery and the timing of catheter placement are key factors for the success of ECMO. The different ways of ECMO intubation, prevention and control of bleeding during ECMO, monitoring and management of internal environment and the strategies of anti-infection are all important for success of ECMO.