Automated characterization of different vessel wall tissues including atherosclerotic plaques, branchings and stents from intravascular ultrasound (IVUS) gray-scale images was addressed. The texture features of each frame were firstly detected with local binary pattern (LBP), Haar-like and Gabor filter in the present study. Then, a Gentle Adaboost classifier was designed to classify tissue features. The methods were validated with clinically acquired image data. The manual characterization results obtained by experienced physicians were adopted as the golden standard to evaluate the accuracy. Results indicated that the recognition accuracy of lipidic plaques reached 94.54%, while classification precision of fibrous and calcified plaques reached 93.08%. High recognition accuracy can be reached up to branchings 93.20% and stents 93.50%, respectively.
Emotion plays an important role in people's cognition and communication. By analyzing electroencephalogram (EEG) signals to identify internal emotions and feedback emotional information in an active or passive way, affective brain-computer interactions can effectively promote human-computer interaction. This paper focuses on emotion recognition using EEG. We systematically evaluate the performance of state-of-the-art feature extraction and classification methods with a public-available dataset for emotion analysis using physiological signals (DEAP). The common random split method will lead to high correlation between training and testing samples. Thus, we use block-wise K fold cross validation. Moreover, we compare the accuracy of emotion recognition with different time window length. The experimental results indicate that 4 s time window is appropriate for sampling. Filter-bank long short-term memory networks (FBLSTM) using differential entropy features as input was proposed. The average accuracy of low and high in valance dimension, arousal dimension and combination of the four in valance-arousal plane is 78.8%, 78.4% and 70.3%, respectively. These results demonstrate the advantage of our emotion recognition model over the current studies in terms of classification accuracy. Our model might provide a novel method for emotion recognition in affective brain-computer interactions.
Myocardial infarction (MI) has the characteristics of high mortality rate, strong suddenness and invisibility. There are problems such as the delayed diagnosis, misdiagnosis and missed diagnosis in clinical practice. Electrocardiogram (ECG) examination is the simplest and fastest way to diagnose MI. The research on MI intelligent auxiliary diagnosis based on ECG is of great significance. On the basis of the pathophysiological mechanism of MI and characteristic changes in ECG, feature point extraction and morphology recognition of ECG, along with intelligent auxiliary diagnosis method of MI based on machine learning and deep learning are all summarized. The models, datasets, the number of ECG, the number of leads, input modes, evaluation methods and effects of different methods are compared. Finally, future research directions and development trends are pointed out, including data enhancement of MI, feature points and dynamic features extraction of ECG, the generalization and clinical interpretability of models, which are expected to provide references for researchers in related fields of MI intelligent auxiliary diagnosis.
Objective To automatically segment diabetic retinal exudation features from deep learning color fundus images. Methods An applied study. The method of this study is based on the U-shaped network model of the Indian Diabetic Retinopathy Image Dataset (IDRID) dataset, introduces deep residual convolution into the encoding and decoding stages, which can effectively extract seepage depth features, solve overfitting and feature interference problems, and improve the model's feature expression ability and lightweight performance. In addition, by introducing an improved context extraction module, the model can capture a wider range of feature information, enhance the perception ability of retinal lesions, and perform excellently in capturing small details and blurred edges. Finally, the introduction of convolutional triple attention mechanism allows the model to automatically learn feature weights, focus on important features, and extract useful information from multiple scales. Accuracy, recall, Dice coefficient, accuracy and sensitivity were used to evaluate the ability of the model to detect and segment the automatic retinal exudation features of diabetic patients in color fundus images. Results After applying this method, the accuracy, recall, dice coefficient, accuracy and sensitivity of the improved model on the IDRID dataset reached 81.56%, 99.54%, 69.32%, 65.36% and 78.33%, respectively. Compared with the original model, the accuracy and Dice index of the improved model are increased by 2.35% , 3.35% respectively. Conclusion The segmentation method based on U-shaped network can automatically detect and segment the retinal exudation features of fundus images of diabetic patients, which is of great significance for assisting doctors to diagnose diseases more accurately.
The feature extraction and feature selection are the important issues in pattern recognition. Based on the geometric algebra representation of vector, a new feature extraction method using blade coefficient of geometric algebra was proposed in this study. At the same time, an improved differential evolution (DE) feature selection method was proposed to solve the elevated high dimension issue. The simple linear discriminant analysis was used as the classifier. The result of the 10-fold cross-validation (10 CV) classification of public breast cancer biomedical dataset was more than 96% and proved superior to that of the original features and traditional feature extraction method.
Objective To evaluate the relevant systematic reviews/meta-analyses that focused on the prevention and treatment of complications after impacted tooth extraction. Methods The systematic reviews/meta-analyses on the prevention and treatment of complications after impacted tooth extraction were searched in PubMed, The Cochrane Library, CBM, CNKI and WanFang Data from inception to September 30th, 2012, and a total of 15 professional journals and the references of included studies were also retrieved manually. Two reviewers screened the literature according to the inclusion criteria and extracted the data. Then the AMSTAR was used to evaluate the quality of the included studies, and the GRADE system was used to evaluate the quality of evidence. Results A total of twelve relevant systematic reviews/meta-analyses were included, of which five focused on the prevention and treatment of dry socket, six on the prevention of swelling, seven on the prevention and treatment of pain, six on the prevention of limitation of mouth opening, two on the prevention of infection, three on the prevention of bleeding, and one on the treatment of nerve damage after tooth extraction. Based on AMSTAR, seven studies were minor limitations and five studies were moderate limitations. Based on GRADE system, two was high quality of evidence, twelve were moderate, nine were low, and seven were very low. Conclusion Currently, the systematic reviews/meta-analyses on the prevention and treatment of complications after impacted tooth extraction can provide some references for clinical practice, which should be combined with the real condition by clinical doctors when making an evidence-based decision. However, it also suggests performing more high quality and large sample studies to prove this conclusion.
Neurofeedback, as an alternative treatment method of behavioral medicine, is a technique which translates the electroencephalogram (EEG) signals to styles as sounds or animation to help people understand their own physical status and learn to enhance or suppress certain EEG signals to regulate their own brain functions after several repeated trainings. This paper develops a neurofeedback system on the foundation of brain-computer interface technique. The EEG features are extracted through real-time signal process and then translated to feedback information. Two feedback screens are designed for relaxation training and attention training individually. The veracity and feasibility of the neurofeedback system are validated through system simulation and preliminary experiment.
Objective To observe the histomorphology and the biocompatibil ity of acellular nerve prepared by different methods, to provide the experimental evidence for the selection of preparation of acellular nerve scaffold. Methods Forty-eight adult Sprague Dawley rats, male or female, weighing 180-220 g, were selected. The sciatic nerves were obtained from 30 rats and were divided into groups A, B, and C (each group had 20 nerves). The acellular sciatic nerves were prepared by the chemical methods of Dumont (group A), Sondell (group B), and Haase (group C). The effect to remove cells was estimated by the degree of decellularization, degree of demyel ination, and intergrity of nerve fiber tube. The histocompatibil ity was observed by subcutaneous implant test in another 18 rats. Three points were selected along both sides of centre l ine on the back of rats, and the points were randomly divided into groups A1, B1, and C1; the acellular nerve of groups A, B, and C were implanted in the corresponding groups A1, B1, and C1. At 1, 2, and 4 weeks after operation, the rats were sacrificed to perform the general observation and histological observation. Results The histomorphology: apart of cells and the dissolved scraps of axon could be seen in acellular never in the group A, and part of Schwann cell basilar membrane was broken. In group B, the cells in the acellular never were not removed completely, the Schwann cell basilar membrane formed bigger irregular hollows, part of the Schwann cell basilar membrane was broken obviously. But in the group C, the cells were completely removed, the Schwann cell basilar membrane remained intactly. Group C was better than group A and group B in the degree of decellularization, degree of demyel ination, integrity of nerve fiber tube and total score, showing significant differences (P lt; 0.05). The subcutaneous implant test: there were neutrophils and lymphocytes around the acellular nerve in 3 groups at 1 week after implant. A few of lymphocytes were observed around the acellular nerve in 3 groups at 2 weeks after implant. The inflammation was less in groups A1, B1, and C1 at 4 weeks after implant, part of the cells grew into the acellular nerve and arranged along the Schwann cell basilar membrane. The reaction indexes of the inflammational cells in group A1 and group B1 were higher than that in group C1 at 1, 2, and 4 weeks after implant, showing significant differences (P lt; 0.01), but there was no significant difference between group A1 and group B1 (P gt; 0.05). Conclusion The acellular sciatic nerves prepared by Haase method has better acellular effect and the histocompatibil ity than those by the methods of Dumont and Sondell.
Skin aging is the most intuitive and obvious sign of the human aging processes. Qualitative and quantitative determination of skin aging is of particular importance for the evaluation of human aging and anti-aging treatment effects. To solve the problem of subjectivity of conventional skin aging grading methods, the self-organizing map (SOM) network was used to explore an automatic method for skin aging grading. First, the ventral forearm skin images were obtained by a portable digital microscope and two texture parameters, i.e., mean width of skin furrows and the number of intersections were extracted by image processing algorithm. Then, the values of texture parameters were taken as inputs of SOM network to train the network. The experimental results showed that the network achieved an overall accuracy of 80.8%, compared with the aging grading results by human graders. The designed method appeared to be rapid and objective, which can be used for quantitative analysis of skin images, and automatic assessment of skin aging grading.
Brain-computer interface (BCI) systems based on steady-state visual evoked potential (SSVEP) have become one of the major paradigms in BCI research due to their high signal-to-noise ratio and short training time required by users. Fast and accurate decoding of SSVEP features is a crucial step in SSVEP-BCI research. However, the current researches lack a systematic overview of SSVEP decoding algorithms and analyses of the connections and differences between them, so it is difficult for researchers to choose the optimum algorithm under different situations. To address this problem, this paper focuses on the progress of SSVEP decoding algorithms in recent years and divides them into two categories—trained and non-trained—based on whether training data are needed. This paper also explains the fundamental theories and application scopes of decoding algorithms such as canonical correlation analysis (CCA), task-related component analysis (TRCA) and the extended algorithms, concludes the commonly used strategies for processing decoding algorithms, and discusses the challenges and opportunities in this field in the end.