A novel diagnosis method combined dual-channel SE-ResNet with expert features for inter-patient heartbeat classification.

As the number of patients with cardiovascular diseases (CVDs) increases annually, a reliable and automated system for detecting electrocardiogram (ECG) abnormalities is becoming increasingly essential. Scholars have developed numerous methods of arrhythmia classification using machine learning or deep learning. However, the issue of low classification rates of individual classes in inter-patient heartbeat classification remains a challenge. This study proposes a method for inter-patient heartbeat classification by fusing dual-channel squeeze-and-excitation residual neural networks (SE-ResNet) and expert features. In the preprocessing stage, ECG heartbeats extracted from both leads of ECG signals are filtered and normalized. Additionally, nine features representing waveform morphology and heartbeat contextual information are selected to be fused with the deep neural networks. Using different filter and kernel sizes for each block, the SE-residual block-based model can effectively learn long-term features between heartbeats. The divided ECG heartbeats and extracted features are then input to the improved SE-ResNet for training and testing according to the inter-patient scheme. The focal loss is utilized to handle the heartbeat of the imbalance category. The proposed arrhythmia classification method is evaluated on three open-source databases, and it achieved an overall F1-score of 83.39 % in the MIT-BIH database. This system can be applied in the scenario of daily monitoring of ECG and plays a significant role in diagnosing arrhythmias.

DoubleSG-DTA: Deep Learning for Drug Discovery: Case Study on the Non-Small Cell Lung Cancer with EGFRT790M Mutation.

Drug-targeted therapies are promising approaches to treating tumors, and research on receptor-ligand interactions for discovering high-affinity targeted drugs has been accelerating drug development. This study presents a mechanism-driven deep learning-based computational model to learn double drug sequences, protein sequences, and drug graphs to project drug-target affinities (DTAs), which was termed the DoubleSG-DTA. We deployed lightweight graph isomorphism networks to aggregate drug graph representations and discriminate between molecular structures, and stacked multilayer squeeze-and-excitation networks to selectively enhance spatial features of drug and protein sequences. What is more, cross-multi-head attentions were constructed to further model the non-covalent molecular docking behavior. The multiple cross-validation experimental evaluations on various datasets indicated that DoubleSG-DTA consistently outperformed all previously reported works. To showcase the value of DoubleSG-DTA, we applied it to generate promising hit compounds of Non-Small Cell Lung Cancer harboring EGFRT790M mutation from natural products, which were consistent with reported laboratory studies. Afterward, we further investigated the interpretability of the graph-based "black box" model and highlighted the active structures that contributed the most. DoubleSG-DTA thus provides a powerful and interpretable framework that extrapolates for potential chemicals to modulate the systemic response to disease.

A Video Sequence Face Expression Recognition Method Based on Squeeze-and-Excitation and 3DPCA Network.

Expression recognition is a very important direction for computers to understand human emotions and human-computer interaction. However, for 3D data such as video sequences, the complex structure of traditional convolutional neural networks, which stretch the input 3D data into vectors, not only leads to a dimensional explosion, but also fails to retain structural information in 3D space, simultaneously leading to an increase in computational cost and a lower accuracy rate of expression recognition. This paper proposes a video sequence face expression recognition method based on Squeeze-and-Excitation and 3DPCA Network (SE-3DPCANet). The introduction of a 3DPCA algorithm in the convolution layer directly constructs tensor convolution kernels to extract the dynamic expression features of video sequences from the spatial and temporal dimensions, without weighting the convolution kernels of adjacent frames by shared weights. Squeeze-and-Excitation Network is introduced in the feature encoding layer, to automatically learn the weights of local channel features in the tensor features, thus increasing the representation capability of the model and further improving recognition accuracy. The proposed method is validated on three video face expression datasets. Comparisons were made with other common expression recognition methods, achieving higher recognition rates while significantly reducing the time required for training.

Deep arrhythmia classification based on SENet and lightweight context transform.

Arrhythmia is one of the common cardiovascular diseases. Nowadays, many methods identify arrhythmias from electrocardiograms (ECGs) by computer-aided systems. However, computer-aided systems could not identify arrhythmias effectively due to various the morphological change of abnormal ECG data. This paper proposes a deep method to classify ECG samples. Firstly, ECG features are extracted through continuous wavelet transform. Then, our method realizes the arrhythmia classification based on the new lightweight context transform blocks. The block is proposed by improving the linear content transform block by squeeze-and-excitation network and linear transformation. Finally, the proposed method is validated on the MIT-BIH arrhythmia database. The experimental results show that the proposed method can achieve a high accuracy on arrhythmia classification.

Automated pulmonary nodule detection in CT images using 3D deep squeeze-and-excitation networks.

PURPOSE: Pulmonary nodule detection has great significance for early treating lung cancer and increasing patient survival. This work presents a novel automated computer-aided detection scheme for pulmonary nodules based on deep convolutional neural networks (DCNNs). METHODS: The proposed approach employs 3D DCNNs based on squeeze-and-excitation network and residual network (SE-ResNet) for pulmonary nodule candidate detection and false-positive reduction. Specifically, a 3D region proposal network with a U-Net-like structure is designed for detecting pulmonary nodule candidates. For the subsequent false-positive reduction, a 3D SE-ResNet-based classifier is presented to accurately discriminate the true nodules from candidates. The 3D SE-ResNet modules boost the representational power of the network by adaptively recalibrating channel-wise residual feature responses. Both models utilize 3D SE-ResNet modules to learn nodule features effectively and improve nodule detection performance. RESULTS: On the public available lung nodule analysis 2016 dataset with 888 scans included, the proposed method reaches high detection sensitivities of 93.6% and 95.7% at one and four false positives per scan, respectively. Meanwhile, the competition performance metric score of 0.904 is achieved. The proposed method has the capability to detect multi-size nodules, especially the extremely small nodules. CONCLUSION: In this paper, a 3D DCNNs framework based on 3D SE-ResNet modules is proposed to detect pulmonary nodules in chest CT images accurately. Experimental results demonstrate superior effectiveness of the proposed approach in pulmonary nodule detection task.