Organoids are an in vitro model that can simulate the complex structure and function of tissues in vivo. Functions such as classification, screening and trajectory recognition have been realized through organoid image analysis, but there are still problems such as low accuracy in recognition classification and cell tracking. Deep learning algorithm and organoid image fusion analysis are the most advanced organoid image analysis methods. In this paper, the organoid image depth perception technology is investigated and sorted out, the organoid culture mechanism and its application concept in depth perception are introduced, and the key progress of four depth perception algorithms such as organoid image and classification recognition, pattern detection, image segmentation and dynamic tracking are reviewed respectively, and the performance advantages of different depth models are compared and analyzed. In addition, this paper also summarizes the depth perception technology of various organ images from the aspects of depth perception feature learning, model generalization and multiple evaluation parameters, and prospects the development trend of organoids based on deep learning methods in the future, so as to promote the application of depth perception technology in organoid images. It provides an important reference for the academic research and practical application in this field.
Medical visual question answering (MVQA) plays a crucial role in the fields of computer-aided diagnosis and telemedicine. Due to the limited size and uneven annotation quality of the MVQA datasets, most existing methods rely on additional datasets for pre-training and use discriminant formulas to predict answers from a predefined set of labels. This approach makes the model prone to overfitting in low resource domains. To cope with the above problems, we propose an image-aware generative MVQA method based on image caption prompts. Firstly, we combine a dual visual feature extractor with a progressive bilinear attention interaction module to extract multi-level image features. Secondly, we propose an image caption prompt method to guide the model to better understand the image information. Finally, the image-aware generative model is used to generate answers. Experimental results show that our proposed method outperforms existing models on the MVQA task, realizing efficient visual feature extraction, as well as flexible and accurate answer outputs with small computational costs in low-resource domains. It is of great significance for achieving personalized precision medicine, reducing medical burden, and improving medical diagnosis efficiency.
The method of directly using speed information and angle information to drive attractors model of grid cells to encode environment has poor anti-interference ability and is not bionic. In response to the problem, this paper proposes a grid field calculation model based on perceived speed and perceived angle. The model has the following characteristics. Firstly, visual stream is decoded to obtain visual speed, and speed cell is modeled and decoded to obtain body speed. Visual speed and body speed are integrated to obtain perceived speed information. Secondly, a one-dimensional circularly connected cell model with excitatory connection is used to simulate the firing mechanism of head direction cells, so that the robot obtains current perception angle information in a biomimetic manner. Finally, the two kinds of perceptual information of speed and angle are combined to realize the driving of grid cell attractors model. The proposed model was experimentally verified. The results showed that this model could realize periodic hexagonal firing field mode of grid cells and precise path integration function. The proposed algorithm may provide a foundation for the research on construction method of robot cognitive map based on hippocampal cognition mechanism.
The medical magnetic resonance (MR) image reconstruction is one of the key technologies in the field of magnetic resonance imaging (MRI). The compressed sensing (CS) theory indicates that the image can be reconstructed accurately from highly undersampled measurements by using the sparsity of the MR image. However, how to improve the image reconstruction quality by employing more sparse priors of the image becomes a crucial issue for MRI. In this paper, an adaptive image reconstruction model fusing the double dictionary learning is proposed by exploiting sparse priors of the MR image in the image domain and transform domain. The double sparse model which combines synthesis sparse model with sparse transform model is applied to the CS MR image reconstruction according to the complementarity of synthesis sparse and sparse transform model. Making full use of the two sparse priors of the image under the synthesis dictionary and transform dictionary learning, the proposed model is tackled in stages by the iterative alternating minimization algorithm. The solution procedure needs to utilize the synthesis and transform K-singular value decomposition (K-SVD) algorithms. Compared with the existing MRI models, the experimental results show that the proposed model can more efficiently improve the quality of the image reconstruction, and has faster convergence speed and better robustness to noise.
Ultrasound diffraction tomography (UDT) possesses the characteristics of high resolution, sensitive to dense tissue, and has high application value in clinics. To suppress the artifact and improve the quality of reconstructed image, classical interpolation method needs to be improved by increasing the number of projections and channels, which will increase the scanning time and the complexity of the imaging system. In this study, we tried to accurately reconstruct the object from limited projection based on compressed sensing. Firstly, we illuminated the object from random angles with limited number of projections. Then we obtained spatial frequency samples through Fourier diffraction theory. Secondly, we formulated the inverse problem of UDT by exploring the sparsity of the object. Thirdly, we solved the inverse problem by conjugate gradient method to reconstruct the object. We accurately reconstructed the object using the proposed method. Not only can the proposed method save scanning time to reduce the distortion by respiratory movement, but also can reduce cost and complexity of the system. Compared to the interpolation method, our method can reduce the reconstruction error and improve the structural similarity.
Electric and electronic products are required to pass through the certification on electrical safety performance before entering into the market in order to reduce electrical shock and electrical fire so as to protect the safety of people and property. The leakage current is the most important factor in testing the electrical safety performance and the test theory is based on the perception current effect and threshold. The traditional method testing the current threshold for perception only depends on the sensing of the human body and is affected by psychological factors. Some authors filter the effect of subjective sensation by using physiological and psychological statistical algorithm in recent years and the reliability and consistency of the experiment data are improved. We established an experiment system of testing the human body's current threshold for perception based on EEG feature analysis, and obtained 967 groups of data. We used wavelet packet analysis to detect α wave from EEG, and used FFT to do spectral analysis on α wave before and after the current flew through the human body. The study has shown that about 97.72% α wave energy changes significantly when electrical stimulation occurs. It is well proved that when the EEG feature identification is applied to test the human body current threshold for perception, and meanwhile α wave energy change and human body sensing are used together to confirm if the current flowing through the human body reaches the perception threshold, the measurement of the human body current threshold for perception could be carried out objectively and accurately.
Evolutionary psychology holds such an opinion that negative situation may threaten survival, trigger avoidance motive and have poor effects on the human body function and the psychological quality. Both disgusted and sad situations can induce negative emotions. However, differences between the two situations on attention capture and emotion cognition during the emotion induction are still not well known. Typical disgusted and sad situation images were used in the present study to induce two negative emotions, and 15 young students (7 males and 8 females, aged 27±3) were recruited in the experiments. Electroencephalogram of 32 leads was recorded when the subjects were viewing situation images, and event-related potentials (ERP) of all leads were obtained for future analysis. Paired sample t tests were carried out on two ERP signals separately induced by disgusted and sad situation images to get time quantum with significant statistical differences between the two ERP signals. Root-mean-square deviations of two ERP signals during each time quantum were calculated and the brain topographic map based on root-mean-square deviations was drawn to display differences of two ERP signals in spatial. Results showed that differences of ERP signals induced by disgusted and sad situation images were mainly manifested in T1 (120-450 ms) early and T2 (800-1 000 ms) later. During the period of T1, the occipital lobe reflecting attention capture was activated by both disgusted and sad situation images, but the prefrontal cortex reflecting emotion sense was activated only by disgusted situation images. During the period of T2, the prefrontal cortex was activated by both disgusted and sad situation images. However, the parietal lobe was activated only by disgusted situation images, which showed stronger emotional perception. The research results would have enlightenment to deepen understanding of negative emotions and to explore deep cognitive neuroscience mechanisms of negative emotion induction.
Emotion can reflect the psychological and physiological health of human beings, and the main expression of human emotion is voice and facial expression. How to extract and effectively integrate the two modes of emotion information is one of the main challenges faced by emotion recognition. In this paper, a multi-branch bidirectional multi-scale time perception model is proposed, which can detect the forward and reverse speech Mel-frequency spectrum coefficients in the time dimension. At the same time, the model uses causal convolution to obtain temporal correlation information between different scale features, and assigns attention maps to them according to the information, so as to obtain multi-scale fusion of speech emotion features. Secondly, this paper proposes a two-modal feature dynamic fusion algorithm, which combines the advantages of AlexNet and uses overlapping maximum pooling layers to obtain richer fusion features from different modal feature mosaic matrices. Experimental results show that the accuracy of the multi-branch bidirectional multi-scale time sensing dual-modal emotion recognition model proposed in this paper reaches 97.67% and 90.14% respectively on the two public audio and video emotion data sets, which is superior to other common methods, indicating that the proposed emotion recognition model can effectively capture emotion feature information and improve the accuracy of emotion recognition.