To enhance the accuracy of computer-aided diagnosis of adolescent depression based on electroencephalogram signals, this study collected signals of 32 female adolescents (16 depressed and 16 healthy, age: 16.3 ± 1.3) with eyes colsed for 4 min in a resting state. First, based on the phase synchronization between the signals, the phase-locked value (PLV) method was used to calculate brain functional connectivity in the θ and α frequency bands, respectively. Then based on the graph theory method, the network parameters, such as strength of the weighted network, average characteristic path length, and average clustering coefficient, were calculated separately (P < 0.05). Next, using the relationship between multiple thresholds and network parameters, the area under the curve (AUC) of each network parameter was extracted as new features (P < 0.05). Finally, support vector machine (SVM) was used to classify the two groups with the network parameters and their AUC as features. The study results show that with strength, average characteristic path length, and average clustering coefficient as features, the classification accuracy in the θ band is increased from 69% to 71%, 66% to 77%, and 50% to 68%, respectively. In the α band, the accuracy is increased from 72% to 79%, 69% to 82%, and 65% to 75%, respectively. And from overall view, when AUC of network parameters was used as a feature in the α band, the classification accuracy is improved compared to the network parameter feature. In the θ band, only the AUC of average clustering coefficient was applied to classification, and the accuracy is improved by 17.6%. The study proved that based on graph theory, the method of feature optimization of brain function network could provide some theoretical support for the computer-aided diagnosis of adolescent depression.
The goal of this paper is to solve the problems of large volume, slow dynamic response and poor intelligent controllability of traditional gait rehabilitation training equipment by using the characteristic that the shear yield strength of magnetorheological fluid changes with the applied magnetic field strength. Based on the extended Bingham model, the main structural parameters of the magnetorheological fluid damper and its output force were simulated and optimized by using scientific computing software, and the three-dimensional modeling of the damper was carried out after the size was determined. On this basis and according to the design and use requirements of the damper, the finite element analysis software was used for force analysis, strength check and topology optimization of the main force components. Finally, a micro magnetorheological fluid damper suitable for wearable rehabilitation training system was designed, which has reference value for the design of lightweight, portable and intelligent rehabilitation training equipment.
Percutaneous pulmonary puncture guided by computed tomography (CT) is one of the most effective tools for obtaining lung tissue and diagnosing lung cancer. Path planning is an important procedure to avoid puncture complications and reduce patient pain and puncture mortality. In this work, a path planning method for lung puncture is proposed based on multi-level constraints. A digital model of the chest is firstly established using patient's CT image. A Fibonacci lattice sampling is secondly conducted on an ideal sphere centered on the tumor lesion in order to obtain a set of candidate paths. Finally, by considering clinical puncture guidelines, an optimal path can be obtained by a proposed multi-level constraint strategy, which is combined with oriented bounding box tree (OBBTree) algorithm and Pareto optimization algorithm. Results of simulation experiments demonstrated the effectiveness of the proposed method, which has good performance for avoiding physical and physiological barriers. Hence, the method could be used as an aid for physicians to select the puncture path.
Thoracic trauma has the characteristics of complexity, specificity, urgency and severity. Therefore, the treatment is particularly important. Thoracic Traumatology Group, Trauma Medicine Branch of Zhejiang Medical Association organized the writing of the thoracic trauma and further optimization consensus of Zhejiang thoracic surgery industry Treatment and diagnosis of rib and sternum trauma: A consensus statement by Zhejiang Association for Thoracic Surgery (version 2021), compiled the popular science book Emergency Treatment and Risk Avoidance Strategy of Thoracic Trauma and Illustration of Real Scene Treatment of Trauma, actively prepared to build the trauma database of Zhejiang Province, and participated in the construction of trauma group in the Yangtze River Delta. Although Zhejiang Province has carried out many related works in the diagnosis and treatment of chest trauma, it is still inconsistent with the development requirements of the times. Standardization of chest trauma treatment, popularization of relevant knowledge, management of trauma big data, grass-roots radiation promotion tour and further optimization of industry consensus are the requirements and objectives of this era.
In order to realize brain-computer interface (BCI), optimal features of single trail motor imagery electroencephalogram (EEG) were extracted and classified. Mu rhythm of EEG was obtained by preprocessing, and the features were optimized by spatial filtering, which are estimated from a set of data by method of common spatial pattern. Classification decision can be made by Fisher criterion, and classification performance can be evaluated by cross validation and receiver operating characteristic (ROC) curve. Optimal feature dimension determination projected by spatial filter was discussed deeply in cross-validation way. The experimental results show that the high discriminate accuracy can be guaranteed, meanwhile the program running speed is improved. Motor imagery intention classification based on optimized EEG feature provides difference of states and simplifies the recognition processing, which offers a new method for the research of intention recognition.
Online hashing methods are receiving increasing attention in cross modal medical image retrieval research. However, existing online methods often lack the learning ability to maintain semantic correlation between new and existing data. To this end, we proposed online semantic similarity cross-modal hashing (OSCMH) learning framework to incrementally learn compact binary hash codes of medical stream data. Within it, a sparse representation of existing data based on online anchor datasets was designed to avoid semantic forgetting of the data and adaptively update hash codes, which effectively maintained semantic correlation between existing and arriving data and reduced information loss as well as improved training efficiency. Besides, an online discrete optimization method was proposed to solve the binary optimization problem of hash code by incrementally updating hash function and optimizing hash code on medical stream data. Compared with existing online or offline hashing methods, the proposed algorithm achieved average retrieval accuracy improvements of 12.5% and 14.3% on two datasets, respectively, effectively enhancing the retrieval efficiency in the field of medical images.
ObjectiveTo investigate the effect of pulmonary ultrasound on pulmonary complications in ultra-fast-track anesthesia for congenital heart disease surgery.MethodsIn 2019, 60 patients with congenital heart diseases underwent ultra-fast-track anesthesia in Shenzhen Children's Hospital, including 34 males and 26 females with the age ranging from 1 month to 6 years. They were randomly divided into a normal group (group N, n=30) and a lung ultrasound optimization group (group L, n=30). Both groups were used the same anesthesia method and anesthetic compatibility. The group N was anesthetized by ultra-fast-track, the tracheal tube was removed after operation and then the patients were sent to the cardiac intensive care unit (CCU). After operation in the group L, according to the contrast of pre- and post-operational lung ultrasonic examination results, for the patients with fusion of B line, atelectasis and pulmonary bronchus inflating sign which caused the increase of lung ultrasound score (LUS), targeted optimization treatment was performed, including sputum suction in the tracheal tube, bronchoscopy alveolar lavage, manual lung inflation suction, ultrasound-guided lung recruitment and other optimization treatments, and then the patients were extubated after lung ultrasound assessment and sent to CCU. The occurrence of pulmonary complications, LUS, oxygenation index (OI), extubation time, etc were compared between the two groups.ResultsCompared with the induction of anesthesia and 1 hour after extubation of the two groups, the incidence of pulmonary complications in the group L (18 patients, 60.0%) was lower than that in the group N (26 patients, 86.7%, χ2= 4.17, P=0.040) and the rate of patients with LUS score reduction was higher in the group L (15 patients, 50.0%) than that in the group N (7 patients, 23.3%, χ2=4.59, P=0.032). The correlation analysis between the LUS and OI value of all patients at each time point showed a good negative correlation (P<0.05). Extubation time in the group L was longer than that in the group N (18.70±5.42 min vs. 13.47±4.73 min, P=0.001).ConclusionUltra-fast-track anesthesia for congenital heart disease can be optimized by pulmonary ultrasound examination before extubation, which can significantly reduce postoperative pulmonary complications, improve postoperative lung imaging performance, and help patients recover after surgery, and has clinical application value.
Heart failure is one kind of cardiovascular disease with high risk and high incidence. As an effective treatment of heart failure, artificial heart is gradually used in clinical treatment. Blood compatibility is an important parameter or index of artificial heart, and how to evaluate it through hemodynamic design and in vitro hemolysis test is a research hotspot in the industry. This paper first reviews the research progress in hemodynamic optimization and in vitro hemolysis evaluation of artificial heart, and then introduces the research achievements and progress of the team in related fields. The hemodynamic performance of the blood pump optimized in this paper can meet the needs of use. The normalized index of hemolysis obtained by in standard vitro hemolysis test is less than 0.1 g/100 L, which has good hemolysis performance in vitro. The optimization method described in this paper is suitable for most of the development of blood pump and can provide reference for related research work.
In order to calibrate the hand-eye transformation of the surgical robot and laser range finder (LRF), a calibration algorithm based on a planar template was designed. A mathematical model of the planar template had been given and the approach to address the equations had been derived. Aiming at the problems of the measurement error in a practical system, we proposed a new algorithm for selecting coplanar data. This algorithm can effectively eliminate considerable measurement error data to improve the calibration accuracy. Furthermore, three orthogonal planes were used to improve the calibration accuracy, in which a nonlinear optimization for hand-eye calibration was used. With the purpose of verifying the calibration precision, we used the LRF to measure some fixed points in different directions and a cuboid’s surfaces. Experimental results indicated that the precision of a single planar template method was (1.37±0.24) mm, and that of the three orthogonal planes method was (0.37±0.05) mm. Moreover, the mean FRE of three-dimensional (3D) points was 0.24 mm and mean TRE was 0.26 mm. The maximum angle measurement error was 0.4 degree. Experimental results show that the method presented in this paper is effective with high accuracy and can meet the requirements of surgical robot precise location.
Consultation is an important form for the diagnosis and treatment of severe diseases, and consultation management is an important content of medical management work, which directly affects the medical quality and treatment efficiency of the hospital. With the help of information network platform, our hospital has realized electronic consultation system online through scientific development, training enhancement, and safeguard mechanism improvement. The system can optimize consultation work process effectively, improve the consultation work, save manpower cost and help construction of hospital informatization.