Chinese medicine (CM) diagnosis intellectualization is one of the hotspots in the research of CM modernization. The traditional CM intelligent diagnosis models transform the CM diagnosis issues into classification issues, however, it is difficult to solve the problems such as excessive or similar categories. With the development of natural language processing techniques, text generation technique has become increasingly mature. In this study, we aimed to establish the CM diagnosis generation model by transforming the CM diagnosis issues into text generation issues. The semantic context characteristic learning capacity was enhanced referring to Bidirectional Long Short-Term Memory (BILSTM) with Transformer as the backbone network. Meanwhile, the CM diagnosis generation model Knowledge Graph Enhanced Transformer (KGET) was established by introducing the knowledge in medical field to enhance the inferential capability. The KGET model was established based on 566 CM case texts, and was compared with the classic text generation models including Long Short-Term Memory sequence-to-sequence (LSTM-seq2seq), Bidirectional and Auto-Regression Transformer (BART), and Chinese Pre-trained Unbalanced Transformer (CPT), so as to analyze the model manifestations. Finally, the ablation experiments were performed to explore the influence of the optimized part on the KGET model. The results of Bilingual Evaluation Understudy (BLEU), Recall-Oriented Understudy for Gisting Evaluation 1 (ROUGE1), ROUGE2 and Edit distance of KGET model were 45.85, 73.93, 54.59 and 7.12, respectively in this study. Compared with LSTM-seq2seq, BART and CPT models, the KGET model was higher in BLEU, ROUGE1 and ROUGE2 by 6.00-17.09, 1.65-9.39 and 0.51-17.62, respectively, and lower in Edit distance by 0.47-3.21. The ablation experiment results revealed that introduction of BILSTM model and prior knowledge could significantly increase the model performance. Additionally, the manual assessment indicated that the CM diagnosis results of the KGET model used in this study were highly consistent with the practical diagnosis results. In conclusion, text generation technology can be effectively applied to CM diagnostic modeling. It can effectively avoid the problem of poor diagnostic performance caused by excessive and similar categories in traditional CM diagnostic classification models. CM diagnostic text generation technology has broad application prospects in the future.
Humans ; Medicine, Chinese Traditional ; Pattern Recognition, Automated ; Asian People ; Language ; Learning

OBJECTIVE: To propose an deep learning-based algorithm for automatic prediction of dose distribution in radiotherapy planning for head and neck cancer. METHODS: We propose a novel beam dose decomposition learning (BDDL) method designed on a cascade network. The delivery matter of beam through the planning target volume (PTV) was fitted with the pre-defined beam angles, which served as an input to the convolution neural network (CNN). The output of the network was decomposed into multiple sub-fractions of dose distribution along the beam directions to carry out a complex task by performing multiple simpler sub-tasks, thus allowing the model more focused on extracting the local features. The subfractions of dose distribution map were merged into a distribution map using the proposed multi-voting mechanism. We also introduced dose distribution features of the regions-of-interest (ROIs) and boundary map as the loss function during the training phase to serve as constraining factors of the network when extracting features of the ROIs and areas of dose boundary. Public datasets of radiotherapy planning for head and neck cancer were used for obtaining the accuracy of dose distribution of the BDDL method and for implementing the ablation study of the proposed method. RESULTS: The BDDL method achieved a Dose score of 2.166 and a DVH score of 1.178 (P < 0.05), demonstrating its superior prediction accuracy to that of current state-ofthe-art (SOTA) methods. Compared with the C3D method, which was in the first place in OpenKBP-2020 Challenge, the BDDL method improved the Dose score and DVH score by 26.3% and 30%, respectively. The results of the ablation study also demonstrated the effectiveness of each key component of the BDDL method. CONCLUSION The BDDL method utilizes the prior knowledge of the delivery matter of beam and dose distribution in the ROIs to establish a dose prediction model. Compared with the existing methods, the proposed method is interpretable and reliable and can be potentially applied in clinical radiotherapy.
Humans ; Deep Learning ; Head and Neck Neoplasms/radiotherapy* ; Algorithms ; Neural Networks, Computer

To explore the methods of the explicitation of implicit knowledge and the construction of knowledge graph on moxibustion in medical case records of ZHOU Mei-sheng's Jiusheng. The medical case records data of Jiusheng was collected, the frequency statistic was analyzed based on Python3.8.6, complex network analysis was performed using Gephi9.2 software, community analysis was performed by the ancient and modern medical case cloud platform V2.3.5, and analysis and verification of correlation graph and weight graph were proceed by Neo4j3.5.25 image database. The disease systems with frequency≥10 % were surgery, ophthalmology and otorhinolaryngology, locomotor, digestive and respiratory systems. The diseases under the disease system were mainly carbuncle, arthritis, lumbar disc herniation and headache. The commonly used moxibustion methods were fumigating moxibustion, blowing moxibustion, direct moxibustion and warming acupuncture. The core prescription of points obtained by complex network analysis included Yatong point, Zhiyang(GV 9), Sanyinjiao(SP 6), Dazhui(GV 14), Zusanli(ST 36), Lingtai(GV 10), Xinshu(BL 15), Zhijian point and Hegu(LI 4), which were basically consistent with high-frequency points. A total of 6 communities were obtained by community analysis, corresponding to different diseases. Through the analysis of correlation graph, 13 pairs of strong association rule points were obtained. The correlation between Zhiyang(GV 9)-Dazhui(GV 14) and Yatong point-Lingtai(GV 10) was the strongest. The acupoints with high correlation with Yatong point were Zhiyang(GV 9), Lingtai(GV 10), Dazhui(GV 14), Zusanli(ST 36) and Sanyinjiao(SP 6). In the weight graph of the high-frequency disease system, the relationship of the first weight of the surgery system disease was fumigating moxibustion-carbuncle-Yatong point, and the relationship of the first weight of the ophthalmology and otorhinolaryngology system disease was blowing moxibustion-laryngitis-Hegu (LI 4). The results of correlation graph and weight graph are consistent with the results of data mining, which can be used as an effective way to study the knowledge base of moxibustion diagnosis and treatment in the future.
Humans ; Moxibustion ; Carbuncle ; Pattern Recognition, Automated ; Acupuncture Therapy ; Acupuncture Points

OBJECTIVES: This study aims to predict the risk of deep caries exposure in radiographic images based on the convolutional neural network model, compare the prediction results of the network model with those of senior dentists, evaluate the performance of the model for teaching and training stomatological students and young dentists, and assist dentists to clarify treatment plans and conduct good doctor-patient communication before surgery. METHODS: A total of 206 cases of pulpitis caused by deep caries were selected from the Department of Stomatological Hospital of Tianjin Medical University from 2019 to 2022. According to the inclusion and exclusion criteria, 104 cases of pulpitis were exposed during the decaying preparation period and 102 cases of pulpitis were not exposed. The 206 radiographic images collected were randomly divided into three groups according to the proportion: 126 radiographic images in the training set, 40 radiographic images in the validation set, and 40 radiographic images in the test set. Three convolutional neural networks, visual geometry group network (VGG), residual network (ResNet), and dense convolutional network (DenseNet) were selected to analyze the rules of the radiographic images in the training set. The radiographic images of the validation set were used to adjust the super parameters of the network. Finally, 40 radiographic images of the test set were used to evaluate the performance of the three network models. A senior dentist specializing in dental pulp was selected to predict whether the deep caries of 40 radiographic images in the test set were exposed. The gold standard is whether the pulp is exposed after decaying the prepared hole during the clinical operation. The prediction effect of the three network models (VGG, ResNet, and DenseNet) and the senior dentist on the pulp exposure of 40 radiographic images in the test set were compared using receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score to select the best network model. RESULTS: The best network model was DenseNet model, with AUC of 0.97. The AUC values of the ResNet model, VGG model, and the senior dentist were 0.89, 0.78, and 0.87, respectively. Accuracy was not statistically different between the senior dentist (0.850) and the DenseNet model (0.850)(P>0.05). Kappa consistency test showed moderate reliability (Kappa=0.6>0.4, P<0.05). CONCLUSIONS Among the three convolutional neural network models, the DenseNet model has the best predictive effect on whether deep caries are exposed in imaging. The predictive effect of this model is equivalent to the level of senior dentists specializing in dental pulp.
Humans ; Deep Learning ; Neural Networks, Computer ; Pulpitis/diagnostic imaging* ; Reproducibility of Results ; ROC Curve ; Random Allocation

Aiming at the problems of missing important features, inconspicuous details and unclear textures in the fusion of multimodal medical images, this paper proposes a method of computed tomography (CT) image and magnetic resonance imaging (MRI) image fusion using generative adversarial network (GAN) and convolutional neural network (CNN) under image enhancement. The generator aimed at high-frequency feature images and used double discriminators to target the fusion images after inverse transform; Then high-frequency feature images were fused by trained GAN model, and low-frequency feature images were fused by CNN pre-training model based on transfer learning. Experimental results showed that, compared with the current advanced fusion algorithm, the proposed method had more abundant texture details and clearer contour edge information in subjective representation. In the evaluation of objective indicators, Q ^AB/F, information entropy (IE), spatial frequency (SF), structural similarity (SSIM), mutual information (MI) and visual information fidelity for fusion (VIFF) were 2.0%, 6.3%, 7.0%, 5.5%, 9.0% and 3.3% higher than the best test results, respectively. The fused image can be effectively applied to medical diagnosis to further improve the diagnostic efficiency.
Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Tomography, X-Ray Computed ; Magnetic Resonance Imaging/methods* ; Algorithms

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. Neuroimaging based on magnetic resonance imaging (MRI) is one of the most intuitive and reliable methods to perform AD screening and diagnosis. Clinical head MRI detection generates multimodal image data, and to solve the problem of multimodal MRI processing and information fusion, this paper proposes a structural and functional MRI feature extraction and fusion method based on generalized convolutional neural networks (gCNN). The method includes a three-dimensional residual U-shaped network based on hybrid attention mechanism (3D HA-ResUNet) for feature representation and classification for structural MRI, and a U-shaped graph convolutional neural network (U-GCN) for node feature representation and classification of brain functional networks for functional MRI. Based on the fusion of the two types of image features, the optimal feature subset is selected based on discrete binary particle swarm optimization, and the prediction results are output by a machine learning classifier. The validation results of multimodal dataset from the AD Neuroimaging Initiative (ADNI) open-source database show that the proposed models have superior performance in their respective data domains. The gCNN framework combines the advantages of these two models and further improves the performance of the methods using single-modal MRI, improving the classification accuracy and sensitivity by 5.56% and 11.11%, respectively. In conclusion, the gCNN-based multimodal MRI classification method proposed in this paper can provide a technical basis for the auxiliary diagnosis of Alzheimer's disease.
Humans ; Alzheimer Disease/diagnostic imaging* ; Neurodegenerative Diseases ; Magnetic Resonance Imaging/methods* ; Neural Networks, Computer ; Neuroimaging/methods* ; Cognitive Dysfunction/diagnosis*

Cardiovascular disease is the leading cause of death worldwide, accounting for 48.0% of all deaths in Europe and 34.3% in the United States. Studies have shown that arterial stiffness takes precedence over vascular structural changes and is therefore considered to be an independent predictor of many cardiovascular diseases. At the same time, the characteristics of Korotkoff signal is related to vascular compliance. The purpose of this study is to explore the feasibility of detecting vascular stiffness based on the characteristics of Korotkoff signal. First, the Korotkoff signals of normal and stiff vessels were collected and preprocessed. Then the scattering features of Korotkoff signal were extracted by wavelet scattering network. Next, the long short-term memory (LSTM) network was established as a classification model to classify the normal and stiff vessels according to the scattering features. Finally, the performance of the classification model was evaluated by some parameters, such as accuracy, sensitivity, and specificity. In this study, 97 cases of Korotkoff signal were collected, including 47 cases from normal vessels and 50 cases from stiff vessels, which were divided into training set and test set according to the ratio of 8 : 2. The accuracy, sensitivity and specificity of the final classification model was 86.4%, 92.3% and 77.8%, respectively. At present, non-invasive screening method for vascular stiffness is very limited. The results of this study show that the characteristics of Korotkoff signal are affected by vascular compliance, and it is feasible to use the characteristics of Korotkoff signal to detect vascular stiffness. This study might be providing a new idea for non-invasive detection of vascular stiffness.
Humans ; Vascular Stiffness ; Neural Networks, Computer ; Cardiovascular Diseases/diagnosis* ; Sensitivity and Specificity

When performing eye movement pattern classification for different tasks, support vector machines are greatly affected by parameters. To address this problem, we propose an algorithm based on the improved whale algorithm to optimize support vector machines to enhance the performance of eye movement data classification. According to the characteristics of eye movement data, this study first extracts 57 features related to fixation and saccade, then uses the ReliefF algorithm for feature selection. To address the problems of low convergence accuracy and easy falling into local minima of the whale algorithm, we introduce inertia weights to balance local search and global search to accelerate the convergence speed of the algorithm and also use the differential variation strategy to increase individual diversity to jump out of local optimum. In this paper, experiments are conducted on eight test functions, and the results show that the improved whale algorithm has the best convergence accuracy and convergence speed. Finally, this paper applies the optimized support vector machine model of the improved whale algorithm to the task of classifying eye movement data in autism, and the experimental results on the public dataset show that the accuracy of the eye movement data classification of this paper is greatly improved compared with that of the traditional support vector machine method. Compared with the standard whale algorithm and other optimization algorithms, the optimized model proposed in this paper has higher recognition accuracy and provides a new idea and method for eye movement pattern recognition. In the future, eye movement data can be obtained by combining it with eye trackers to assist in medical diagnosis.
Animals ; Support Vector Machine ; Whales ; Eye Movements ; Algorithms

The brain-computer interface (BCI) based on motor imagery electroencephalography (MI-EEG) enables direct information interaction between the human brain and external devices. In this paper, a multi-scale EEG feature extraction convolutional neural network model based on time series data enhancement is proposed for decoding MI-EEG signals. First, an EEG signals augmentation method was proposed that could increase the information content of training samples without changing the length of the time series, while retaining its original features completely. Then, multiple holistic and detailed features of the EEG data were adaptively extracted by multi-scale convolution module, and the features were fused and filtered by parallel residual module and channel attention. Finally, classification results were output by a fully connected network. The application experimental results on the BCI Competition IV 2a and 2b datasets showed that the proposed model achieved an average classification accuracy of 91.87% and 87.85% for the motor imagery task, respectively, which had high accuracy and strong robustness compared with existing baseline models. The proposed model does not require complex signals pre-processing operations and has the advantage of multi-scale feature extraction, which has high practical application value.
Humans ; Time Factors ; Brain ; Electroencephalography ; Imagery, Psychotherapy ; Neural Networks, Computer

The recurrent neural network architecture improves the processing ability of time-series data. However, issues such as exploding gradients and poor feature extraction limit its application in the automatic diagnosis of mild cognitive impairment (MCI). This paper proposed a research approach for building an MCI diagnostic model using a Bayesian-optimized bidirectional long short-term memory network (BO-BiLSTM) to address this problem. The diagnostic model was based on a Bayesian algorithm and combined prior distribution and posterior probability results to optimize the BO-BiLSTM network hyperparameters. It also used multiple feature quantities that fully reflected the cognitive state of the MCI brain, such as power spectral density, fuzzy entropy, and multifractal spectrum, as the input of the diagnostic model to achieve automatic MCI diagnosis. The results showed that the feature-fused Bayesian-optimized BiLSTM network model achieved an MCI diagnostic accuracy of 98.64% and effectively completed the diagnostic assessment of MCI. In conclusion, based on this optimization, the long short-term neural network model has achieved automatic diagnostic assessment of MCI, providing a new diagnostic model for intelligent diagnosis of MCI.
Humans ; Bayes Theorem ; Neural Networks, Computer ; Algorithms ; Brain ; Cognitive Dysfunction/diagnosis*