Objective To investigate the biocompatibility of diamond-like carbon(DLC) coated NickelTitanium shape memory alloy with osteoblasts cultured invitro. Methods Rabbit’s osteoblasts were incubated with DLCcoated NickelTitanium shape memory alloy disks and uncoated ones of equal size for 5 days. The control group（without shape memory alloy in culture media） was performed simultaneously. The cultured cells were counted and graphed. The samples from culture media were collected and the concentrations of alkaline phosphatase (ALP) and nickel（Ni2+） were measured from the 1st to 5th day respectively. Results The proliferation of osteoblasts and the concentration of ALP in both DLC-coated group and control gruop was higher than uncoated group. The proliferation of osteoblasts on the 3rd, 4th, and 5th day in both DLC-coatedgroup and control group was significantly higher than that in the uncoated group(P＜0.05). The concentration of ALP in DLC-coated group on the 2nd, 3rd, and 5th day and in the control group on the 3rd, 4th, and 5th day was significantly higher than that in the uncoated group(P＜0.05). The concentration of Ni2+ on the 3rd, 4th, and 5th day was significantly lower than that in the uncoated group(P＜0.05). Conclusion DLC- coated NickelTitanium shape memory alloys appears to have better biocompatibility with osteoblast cultured in vitro compared to uncoated ones.
Aiming at the problem that the unbalanced distribution of data in sleep electroencephalogram(EEG) signals and poor comfort in the process of polysomnography information collection will reduce the model's classification ability, this paper proposed a sleep state recognition method using single-channel EEG signals (WKCNN-LSTM) based on one-dimensional width kernel convolutional neural networks(WKCNN) and long-short-term memory networks (LSTM). Firstly, the wavelet denoising and synthetic minority over-sampling technique-Tomek link (SMOTE-Tomek) algorithm were used to preprocess the original sleep EEG signals. Secondly, one-dimensional sleep EEG signals were used as the input of the model, and WKCNN was used to extract frequency-domain features and suppress high-frequency noise. Then, the LSTM layer was used to learn the time-domain features. Finally, normalized exponential function was used on the full connection layer to realize sleep state. The experimental results showed that the classification accuracy of the one-dimensional WKCNN-LSTM model was 91.80% in this paper, which was better than that of similar studies in recent years, and the model had good generalization ability. This study improved classification accuracy of single-channel sleep EEG signals that can be easily utilized in portable sleep monitoring devices.
ObjectiveTo evaluate the effectiveness of nitinol memory alloy two foot fixator combined with Kirschner wire in the treatment of trans-scaphoid perilunate dislocation.MethodsBetween September 2011 and October 2018, 17 patients with trans-scaphoid perilunate dislocation were treated with nitinol memory alloy two foot fixator and Kirschner wire. There were 12 males and 5 females, with an average age of 32.6 years (range, 23-52 years). The disease duration was 8 hours to 9 days, with an average of 6.5 days. The causes of injury included 6 cases of falling injury, 4 cases of traffic accident injury, 3 cases of stress injury of wrist caused by sports, 2 cases of violent injury of wrist caused by machine impact, 1 case of military training injury, and 1 case of other injury. One case was complicated with nerve injury. According to Herbert’s classification, all the fractures were type B4. At 1 week before operation, 3 months, 6 months after operation and last follow-up, the wrist function was evaluated according to the Krimmer scale score.ResultsAll the 17 patients were followed up 10.5-48 months, with an average of 18.6 months. There was no loosening or infection of the internal fixator, no necrosis of the scaphoid and lunate. The periosteal dislocations of the patients were well reduced and the scaphoid fractures all healed. The healing time was 4-18 months, with an average of 11.3 months. The Krimmer wrist scores were 37.5±4.4, 61.3±7.2, 83.3±9.3, 87.3±8.2 at 1 week before operation, 3 months, 6 months after operation and last follow-up, respectively. The Krimmer wrist score at each time point after operation was significantly improved when compared with that before operation (P<0.05), and at 6 months after operation and last follow-up than at 3 months after operation (P<0.05). There was no significant difference between at 6 months and last follow-up (P>0.05). At last follow-up, the Krimmer wrist function was excellent in 13 cases, good in 2 cases, fair in 1 case, poor in 1 case, and the excellent and good rate was 88.23%.ConclusionNitinol memory alloy two foot fixator combined with Kirschner wire in the treatment of trans-scaphoid periosteal dislocation has definite effectiveness, simple operation, and good recovery of wrist function after operation.
ObjectiveTo compare the biomechanical characteristics of self-made nickel-titanium shape memory alloy stepped plate with calcaneal plate and cannulated compression screws in fixing calcaneal osteotomy.MethodsCalcaneal osteotomy was operated on 6 fresh-frozen lower limbs collected from donors. Then three kinds of fixation materials were applied in random, including the self-made nickel-titanium shape memory alloy stepped plate (group A), calcaneal plate (group B), and cannulated compression screws (group C). Immediately after fixation, axial loading of 20-600 N and 20 N/s in speed was introduced to record the biomechanical data including maximum displacement, elastic displacement, and maximum load. Then fatigue test was performed (5 Hz in frequency and repeat 3 000 times) and the same axial loading was introduced to collect the biomechanical data. Finally, the axial compression stiffness before and after fatigue test were calculated.ResultsThere was no significant difference in the axial compression stiffness between pre- and post-fatigue test in each group (P>0.05). However, the axial compression stiffness was significant higher in group A than that in groups B and C both before and after fatigue test (P<0.05). No significant difference was found between group B and group C (P>0.05).ConclusionSelf-made nickel-titanium shape memory alloy stepped plate is better than calcaneal plate and cannulated compression screws in axial load stiffness after being used to fix calcaneal osteotomy.
Objective To evaluate initial experience with shape memory alloy stent as an alterative to colostomy in patients with intestinal obstruction of rectal cancer. Methods Twenty-one patients with acute and chronic rectal obstructions from malignant causes underwent stent placement. After rectal stent was slenderized in ice water, it was inserted into the strictured rectum by hand or sigmoidoscope. Nitinol mesh stent were deployed in hot water. Results Eighteen patients who had underwent rectal stent placement achieved clinical decompression within 5 hours. Colostomy underwent in 3 patients due to stent failure. Eighteen patients with stent were followed-up, 14 cases died in 56-720 days and 4 other cases were still alive without intestinal obstruction in 2-15 months. Conclusion Nitinol mesh stent may be useful in the management of terminal or high-risk surgical patients for palliative purposes shuning colostomy. Palliation of stent combined with chemotherapy and immunotherapy can be performed to improve survival.
Electrocardiogram (ECG) can visually reflect the physiological electrical activity of human heart, which is important in the field of arrhythmia detection and classification. To address the negative effect of label imbalance in ECG data on arrhythmia classification, this paper proposes a nested long short-term memory network (NLSTM) model for unbalanced ECG signal classification. The NLSTM is built to learn and memorize the temporal characteristics in complex signals, and the focal loss function is used to reduce the weights of easily identifiable samples. Then the residual attention mechanism is used to modify the assigned weights according to the importance of sample characteristic to solve the sample imbalance problem. Then the synthetic minority over-sampling technique is used to perform a simple manual oversampling process on the Massachusetts institute of technology and Beth Israel hospital arrhythmia (MIT-BIH-AR) database to further increase the classification accuracy of the model. Finally, the MIT-BIH arrhythmia database is applied to experimentally verify the above algorithms. The experimental results show that the proposed method can effectively solve the issues of imbalanced samples and unremarkable features in ECG signals, and the overall accuracy of the model reaches 98.34%. It also significantly improves the recognition and classification of minority samples and has provided a new feasible method for ECG-assisted diagnosis, which has practical application significance.
Aiming at the problem that the small samples of critical disease in clinic may lead to prognostic models with poor performance of overfitting, large prediction error and instability, the long short-term memory transferring algorithm (transLSTM) was proposed. Based on the idea of transfer learning, the algorithm leverages the correlation between diseases to transfer information of different disease prognostic models, constructs the effictive model of target disease of small samples with the aid of large data of related diseases, hence improves the prediction performance and reduces the requirement for target training sample quantity. The transLSTM algorithm firstly uses the related disease samples to pretrain partial model parameters, and then further adjusts the whole network with the target training samples. The testing results on MIMIC-Ⅲ database showed that compared with traditional LSTM classification algorithm, the transLSTM algorithm had 0.02-0.07 higher AUROC and 0.05-0.14 larger AUPRC, while its number of training iterations was only 39%-64% of the traditional algorithm. The results of application on sepsis revealed that the transLSTM model of only 100 training samples had comparable mortality prediction performance to the traditional model of 250 training samples. In small sample situations, the transLSTM algorithm has significant advantages with higher prediciton accuracy and faster training speed. It realizes the application of transfer learning in the prognostic model of critical disease with small samples.
The task of automatic generation of medical image reports faces various challenges, such as diverse types of diseases and a lack of professionalism and fluency in report descriptions. To address these issues, this paper proposes a multimodal medical imaging report based on memory drive method (mMIRmd). Firstly, a hierarchical vision transformer using shifted windows (Swin-Transformer) is utilized to extract multi-perspective visual features of patient medical images, and semantic features of textual medical history information are extracted using bidirectional encoder representations from transformers (BERT). Subsequently, the visual and semantic features are integrated to enhance the model's ability to recognize different disease types. Furthermore, a medical text pre-trained word vector dictionary is employed to encode labels of visual features, thereby enhancing the professionalism of the generated reports. Finally, a memory driven module is introduced in the decoder, addressing long-distance dependencies in medical image data. This study is validated on the chest X-ray dataset collected at Indiana University (IU X-Ray) and the medical information mart for intensive care chest x-ray (MIMIC-CXR) released by the Massachusetts Institute of Technology and Massachusetts General Hospital. Experimental results indicate that the proposed method can better focus on the affected areas, improve the accuracy and fluency of report generation, and assist radiologists in quickly completing medical image report writing.