The accurate segmentation of breast ultrasound images is an important precondition for the lesion determination. The existing segmentation approaches embrace massive parameters, sluggish inference speed, and huge memory consumption. To tackle this problem, we propose T2KD Attention U-Net (dual-Teacher Knowledge Distillation Attention U-Net), a lightweight semantic segmentation method combined double-path joint distillation in breast ultrasound images. Primarily, we designed two teacher models to learn the fine-grained features from each class of images according to different feature representation and semantic information of benign and malignant breast lesions. Then we leveraged the joint distillation to train a lightweight student model. Finally, we constructed a novel weight balance loss to focus on the semantic feature of small objection, solving the unbalance problem of tumor and background. Specifically, the extensive experiments conducted on Dataset BUSI and Dataset B demonstrated that the T2KD Attention U-Net outperformed various knowledge distillation counterparts. Concretely, the accuracy, recall, precision, Dice, and mIoU of proposed method were 95.26%, 86.23%, 85.09%, 83.59%and 77.78% on Dataset BUSI, respectively. And these performance indexes were 97.95%, 92.80%, 88.33%, 88.40% and 82.42% on Dataset B, respectively. Compared with other models, the performance of this model was significantly improved. Meanwhile, compared with the teacher model, the number, size, and complexity of student model were significantly reduced (2.2×106 vs. 106.1×106, 8.4 MB vs. 414 MB, 16.59 GFLOPs vs. 205.98 GFLOPs, respectively). Indeedy, the proposed model guarantees the performances while greatly decreasing the amount of computation, which provides a new method for the deployment of clinical medical scenarios.
Attention level evaluation refers to the evaluation of people's attention level through observation or experimental testing, and its research results have great application value in education and teaching, intelligent driving, medical health and other fields. With its objective reliability and security, electroencephalogram signals have become one of the most important technical means to analyze and express attention level. At present, there is little review literature that comprehensively summarize the application of electroencephalogram signals in the field of attention evaluation. To this end, this paper first summarizes the research progress on attention evaluation; then the important methods for electroencephalogram attention evaluation are analyzed, including data preprocessing, feature extraction and selection, attention evaluation methods, etc.; finally, the shortcomings of the current development in the field of electroencephalogram attention evaluation are discussed, and the future development trend is prospected, to provide research references for researchers in related fields.
The conventional fault diagnosis of patient monitors heavily relies on manual experience, resulting in low diagnostic efficiency and ineffective utilization of fault maintenance text data. To address these issues, this paper proposes an intelligent fault diagnosis method for patient monitors based on multi-feature text representation, improved bidirectional gate recurrent unit (BiGRU) and attention mechanism. Firstly, the fault text data was preprocessed, and the word vectors containing multiple linguistic features was generated by linguistically-motivated bidirectional encoder representation from Transformer. Then, the bidirectional fault features were extracted and weighted by the improved BiGRU and attention mechanism respectively. Finally, the weighted loss function is used to reduce the impact of class imbalance on the model. To validate the effectiveness of the proposed method, this paper uses the patient monitor fault dataset for verification, and the macro F1 value has achieved 91.11%. The results show that the model built in this study can realize the automatic classification of fault text, and may provide assistant decision support for the intelligent fault diagnosis of the patient monitor in the future.
The processing mechanism of the human brain for speech information is a significant source of inspiration for the study of speech enhancement technology. Attention and lateral inhibition are key mechanisms in auditory information processing that can selectively enhance specific information. Building on this, the study introduces a dual-branch U-Net that integrates lateral inhibition and feedback-driven attention mechanisms. Noisy speech signals input into the first branch of the U-Net led to the selective feedback of time-frequency units with high confidence. The generated activation layer gradients, in conjunction with the lateral inhibition mechanism, were utilized to calculate attention maps. These maps were then concatenated to the second branch of the U-Net, directing the network’s focus and achieving selective enhancement of auditory speech signals. The evaluation of the speech enhancement effect was conducted by utilising five metrics, including perceptual evaluation of speech quality. This method was compared horizontally with five other methods: Wiener, SEGAN, PHASEN, Demucs and GRN. The experimental results demonstrated that the proposed method improved speech signal enhancement capabilities in various noise scenarios by 18% to 21% compared to the baseline network across multiple performance metrics. This improvement was particularly notable in low signal-to-noise ratio conditions, where the proposed method exhibited a significant performance advantage over other methods. The speech enhancement technique based on lateral inhibition and feedback-driven attention mechanisms holds significant potential in auditory speech enhancement, making it suitable for clinical practices related to artificial cochleae and hearing aids.
ObjectiveTo observe the effect of sensory integration training combined with methylphenidate hydrochloride on attention deficit hyperactivity disorder (ADHD). MethodsThe clinical data of 96 patients with ADHD diagnosed between January 2009 and March 2013 were retrospectively analyzed. The patients were divided into two groups by the table of random number. The trail group (n=48) received the combination therapy of sensory integration training combined with methylphenidate hydrochloride; while the control group (n=48) only received the medication of methylphenidate hydrochloride. The scores of sensory integration ability rating scale, integrated visual and auditory continuous performance test (IVA-CPT), Conner's behavior rating scale, Chinese Wechsler Intelligence Scale for Children (C-WISC) and adverse reactions were observed and compared between the two groups. ResultsThe scores of the sensory integration ability rating scale, FRCQ, FAQ (IVA-CPT), PIQ, VIQ, FIQ, C factor (C-WISC) in both of the two groups were significantly higher after the therapy; while the scores of the study, behavior, somatopsychic disturbance, impulsion, hyperactivity index and anxiety factor significantly decreased after the treatment (P<0.05). Compared with the control group, the trial group's scores of sensory integration ability rating scale, IVA-CPT, Conner's behavior rating scale, C-WISC were improved obviously, and the adverse reactions were significantly less (P<0.05). ConclusionThe sensory integration training combined with methylphenidate hydrochloride is sage and effective on children with attention deficit hyperactivity disorder.
Motor imagery electroencephalogram (EEG) signals are non-stationary time series with a low signal-to-noise ratio. Therefore, the single-channel EEG analysis method is difficult to effectively describe the interaction characteristics between multi-channel signals. This paper proposed a deep learning network model based on the multi-channel attention mechanism. First, we performed time-frequency sparse decomposition on the pre-processed data, which enhanced the difference of time-frequency characteristics of EEG signals. Then we used the attention module to map the data in time and space so that the model could make full use of the data characteristics of different channels of EEG signals. Finally, the improved time-convolution network (TCN) was used for feature fusion and classification. The BCI competition IV-2a data set was used to verify the proposed algorithm. The experimental results showed that the proposed algorithm could effectively improve the classification accuracy of motor imagination EEG signals, which achieved an average accuracy of 83.03% for 9 subjects. Compared with the existing methods, the classification accuracy of EEG signals was improved. With the enhanced difference features between different motor imagery EEG data, the proposed method is important for the study of improving classifier performance.
Deep learning-based automatic classification of diabetic retinopathy (DR) helps to enhance the accuracy and efficiency of auxiliary diagnosis. This paper presents an improved residual network model for classifying DR into five different severity levels. First, the convolution in the first layer of the residual network was replaced with three smaller convolutions to reduce the computational load of the network. Second, to address the issue of inaccurate classification due to minimal differences between different severity levels, a mixed attention mechanism was introduced to make the model focus more on the crucial features of the lesions. Finally, to better extract the morphological features of the lesions in DR images, cross-layer fusion convolutions were used instead of the conventional residual structure. To validate the effectiveness of the improved model, it was applied to the Kaggle Blindness Detection competition dataset APTOS2019. The experimental results demonstrated that the proposed model achieved a classification accuracy of 97.75% and a Kappa value of 0.971 7 for the five DR severity levels. Compared to some existing models, this approach shows significant advantages in classification accuracy and performance.
Manual segmentation of coronary arteries in computed tomography angiography (CTA) images is inefficient, and existing deep learning segmentation models often exhibit low accuracy on coronary artery images. Inspired by the Transformer architecture, this paper proposes a novel segmentation model, the double parallel encoder u-net with transformers (DUNETR). This network employed a dual-encoder design integrating Transformers and convolutional neural networks (CNNs). The Transformer encoder transformed three-dimensional (3D) coronary artery data into a one-dimensional (1D) sequential problem, effectively capturing global multi-scale feature information. Meanwhile, the CNN encoder extracted local features of the 3D coronary arteries. The complementary features extracted by the two encoders were fused through the noise reduction feature fusion (NRFF) module and passed to the decoder. Experimental results on a public dataset demonstrated that the proposed DUNETR model achieved a Dice similarity coefficient of 81.19% and a recall rate of 80.18%, representing improvements of 0.49% and 0.46%, respectively, over the next best model in comparative experiments. These results surpassed those of other conventional deep learning methods. The integration of Transformers and CNNs as dual encoders enables the extraction of rich feature information, significantly enhancing the effectiveness of 3D coronary artery segmentation. Additionally, this model provides a novel approach for segmenting other vascular structures.
ObjectiveTo systematically review the methodological quality of guidelines concerning attention-deficit/hyperactivity disorder (ADHD) in children and adolescents, and to compare differences and similarities of the drugs recommended, in order to provide guidance for clinical practice. MethodsGuidelines concerning ADHD were electronically retrieved in PubMed, EMbase, VIP, WanFang Data, CNKI, NGC (National Guideline Clearinghouse), GIN (Guidelines International Network), NICE (National Institute for Health and Clinical Excellence) from inception to December 2013. The methodological quality of included guidelines were evaluated according to the AGREE Ⅱ instrument, and the differences between recommendations were compared. ResultsA total of 9 guidelines concerning ADHD in children and adolescents were included, with development time ranging from 2004 to 2012. Among 9 guidelines, 4 were made by the USA, 3 in Europe and 2 by UK. The levels of recommendations were Level A for 2 guidelines, and Level B for 7 guidelines. The scores of guidelines according to the domains of AGREE Ⅱ decreased from "clarity of presentations", "scope and purpose", "participants", "applicability", "rigour of development" and "editorial independence". Three evidence-based guidelines scored the top three in the domain of "rigour of development". There were slightly differences in the recommendations of different guidelines. ConclusionThe overall methodological quality of ADHD guidelines is suboptimal in different countries or regions. The 6 domains involving 23 items in AGREE Ⅱ vary with scores, while the scores of evidence-base guidelines are higher than those of non-evidence-based guidelines. The guidelines on ADHD in children and adolescents should be improved in "rigour of development" and "applicability" in future. Conflicts of interest should be addressed. And the guidelines are recommended to be developed on the basis of methods of evidence-based medicine, and best evidence is recommended.
Accurate segmentation of whole slide images is of great significance for the diagnosis of pancreatic cancer. However, developing an automatic model is challenging due to the complex content, limited samples, and high sample heterogeneity of pathological images. This paper presented a multi-tissue segmentation model for whole slide images of pancreatic cancer. We introduced an attention mechanism in building blocks, and designed a multi-task learning framework as well as proper auxiliary tasks to enhance model performance. The model was trained and tested with the pancreatic cancer pathological image dataset from Shanghai Changhai Hospital. And the data of TCGA, as an external independent validation cohort, was used for external validation. The F1 scores of the model exceeded 0.97 and 0.92 in the internal dataset and external dataset, respectively. Moreover, the generalization performance was also better than the baseline method significantly. These results demonstrate that the proposed model can accurately segment eight kinds of tissue regions in whole slide images of pancreatic cancer, which can provide reliable basis for clinical diagnosis.