Inferior myocardial infarction is an acute ischemic heart disease with high mortality, which is easy to induce life-threatening complications such as arrhythmia, heart failure and cardiogenic shock. Therefore, it is of great clinical value to carry out accurate and efficient early diagnosis of inferior myocardial infarction. Electrocardiogram is the most sensitive means for early diagnosis of inferior myocardial infarction. This paper proposes a method for detecting inferior myocardial infarction based on densely connected convolutional neural network. The method uses the original electrocardiogram (ECG) signals of serially connected Ⅱ, Ⅲ and aVF leads as the input of the model and extracts the robust features of the ECG signals by using the scale invariance of the convolutional layers. The characteristic transmission of ECG signals is enhanced by the dense connectivity between different layers, so that the network can automatically learn the effective features with strong robustness and high recognition, so as to achieve accurate detection of inferior myocardial infarction. The Physikalisch Technische Bundesanstalt diagnosis public ECG database was used for verification. The accuracy, sensitivity and specificity of the model reached 99.95%, 100% and 99.90%, respectively. The accuracy, sensitivity and specificity of the model are also over 99% even though the noise exists. Based on the results of this study, it is expected that the method can be introduced in the clinical environment to help doctors quickly diagnose inferior myocardial infarction in the future.
Atrial fibrillation (AF) is a common arrhythmia, which can lead to thrombosis and increase the risk of a stroke or even death. In order to meet the need for a low false-negative rate (FNR) of the screening test in clinical application, a convolutional neural network with a low false-negative rate (LFNR-CNN) was proposed. Regularization coefficients were added to the cross-entropy loss function which could make the cost of positive and negative samples different, and the penalty for false negatives could be increased during network training. The inter-patient clinical database of 21 077 patients (CD-21077) collected from the large general hospital was used to verify the effectiveness of the proposed method. For the convolutional neural network (CNN) with the same structure, the improved loss function could reduce the FNR from 2.22% to 0.97% compared with the traditional cross-entropy loss function. The selected regularization coefficient could increase the sensitivity (SE) from 97.78% to 98.35%, and the accuracy (ACC) was 96.62%, which was an increase from 96.49%. The proposed algorithm can reduce the FNR without losing ACC, and reduce the possibility of missed diagnosis to avoid missing the best treatment period. Meanwhile, it provides a universal loss function for the clinical auxiliary diagnosis of other diseases.
Sleep apnea (SA) detection method based on traditional machine learning needs a lot of efforts in feature engineering and classifier design. We constructed a one-dimensional convolutional neural network (CNN) model, which consists in four convolution layers, four pooling layers, two full connection layers and one classification layer. The automatic feature extraction and classification were realized by the structure of the proposed CNN model. The model was verified by the whole night single-channel sleep electrocardiogram (ECG) signals of 70 subjects from the Apnea-ECG dataset. Our results showed that the accuracy of per-segment SA detection was ranged from 80.1% to 88.0%, using the input signals of single-channel ECG signal, RR interval (RRI) sequence, R peak sequence and RRI sequence + R peak sequence respectively. These results indicated that the proposed CNN model was effective and can automatically extract and classify features from the original single-channel ECG signal or its derived signal RRI and R peak sequence. When the input signals were RRI sequence + R peak sequence, the CNN model achieved the best performance. The accuracy, sensitivity and specificity of per-segment SA detection were 88.0%, 85.1% and 89.9%, respectively. And the accuracy of per-recording SA diagnosis was 100%. These findings indicated that the proposed method can effectively improve the accuracy and robustness of SA detection and outperform the methods reported in recent years. The proposed CNN model can be applied to portable screening diagnosis equipment for SA with remote server.
The application of minimally invasive surgical tool detection and tracking technology based on deep learning in minimally invasive surgery is currently a research hotspot. This paper firstly expounds the relevant technical content of the minimally invasive surgery tool detection and tracking, which mainly introduces the advantages based on deep learning algorithm. Then, this paper summarizes the algorithm for detection and tracking surgical tools based on fully supervised deep neural network and the emerging algorithm for detection and tracking surgical tools based on weakly supervised deep neural network. Several typical algorithm frameworks and their flow charts based on deep convolutional and recurrent neural networks are summarized emphatically, so as to enable researchers in relevant fields to understand the current research progress more systematically and provide reference for minimally invasive surgeons to select navigation technology. In the end, this paper provides a general direction for the further research of minimally invasive surgical tool detection and tracking technology based on deep learning.
Coronavirus disease 2019 (COVID-19) has spread rapidly around the world. In order to diagnose COVID-19 more quickly, in this paper, a depthwise separable DenseNet was proposed. The paper constructed a deep learning model with 2 905 chest X-ray images as experimental dataset. In order to enhance the contrast, the contrast limited adaptive histogram equalization (CLAHE) algorithm was used to preprocess the X-ray image before network training, then the images were put into the training network and the parameters of the network were adjusted to the optimal. Meanwhile, Leaky ReLU was selected as the activation function. VGG16, ResNet18, ResNet34, DenseNet121 and SDenseNet models were used to compare with the model proposed in this paper. Compared with ResNet34, the proposed classification model of pneumonia had improved 2.0%, 2.3% and 1.5% in accuracy, sensitivity and specificity respectively. Compared with the SDenseNet network without depthwise separable convolution, number of parameters of the proposed model was reduced by 43.9%, but the classification effect did not decrease. It can be found that the proposed DWSDenseNet has a good classification effect on the COVID-19 chest X-ray images dataset. Under the condition of ensuring the accuracy as much as possible, the depthwise separable convolution can effectively reduce number of parameters of the model.
Attention deficit/hyperactivity disorder (ADHD) is a behavioral disorder syndrome found mainly in school-age population. At present, the diagnosis of ADHD mainly depends on the subjective methods, leading to the high rate of misdiagnosis and missed-diagnosis. To solve these problems, we proposed an algorithm for classifying ADHD objectively based on convolutional neural network. At first, preprocessing steps, including skull stripping, Gaussian kernel smoothing, et al., were applied to brain magnetic resonance imaging (MRI). Then, coarse segmentation was used for selecting the right caudate nucleus, left precuneus, and left superior frontal gyrus region. Finally, a 3 level convolutional neural network was used for classification. Experimental results showed that the proposed algorithm was capable of classifying ADHD and normal groups effectively, the classification accuracies obtained by the right caudate nucleus and the left precuneus brain regions were greater than the highest classification accuracy (62.52%) in the ADHD-200 competition, and among 3 brain regions in ADHD and the normal groups, the classification accuracy from the right caudate nucleus was the highest. It is well concluded that the method for classification of ADHD and normal groups proposed in this paper utilizing the coarse segmentation and deep learning is a useful method for the purpose. The classification accuracy of the proposed method is high, and the calculation is simple. And the method is able to extract the unobvious image features better, and can overcome the shortcomings of traditional methods of MRI brain area segmentation, which are time-consuming and highly complicate. The method provides an objective diagnosis approach for ADHD.
When applying deep learning to the automatic segmentation of organs at risk in medical images, we combine two network models of Dense Net and V-Net to develop a Dense V-network for automatic segmentation of three-dimensional computed tomography (CT) images, in order to solve the problems of degradation and gradient disappearance of three-dimensional convolutional neural networks optimization as training samples are insufficient. This algorithm is applied to the delineation of pelvic endangered organs and we take three representative evaluation parameters to quantitatively evaluate the segmentation effect. The clinical result showed that the Dice similarity coefficient values of the bladder, small intestine, rectum, femoral head and spinal cord were all above 0.87 (average was 0.9); Jaccard distance of these were within 2.3 (average was 0.18). Except for the small intestine, the Hausdorff distance of other organs were less than 0.9 cm (average was 0.62 cm). The Dense V-Network has been proven to achieve the accurate segmentation of pelvic endangered organs.
Alzheimer’s disease (AD) is an irreversible neurodegenerative disorder that damages patients’ memory and cognitive abilities. Therefore, the diagnosis of AD holds significant importance. The interactions between regions of interest (ROIs) in the brain often involve multiple areas collaborating in a nonlinear manner. Leveraging these nonlinear higher-order interaction features to their fullest potential contributes to enhancing the accuracy of AD diagnosis. To address this, a framework combining nonlinear higher-order feature extraction and three-dimensional (3D) hypergraph neural networks is proposed for computer-assisted diagnosis of AD. First, a support vector machine regression model based on the radial basis function kernel was trained on ROI data to obtain a base estimator. Then, a recursive feature elimination algorithm based on the base estimator was applied to extract nonlinear higher-order features from functional magnetic resonance imaging (fMRI) data. These features were subsequently constructed into a hypergraph, leveraging the complex interactions captured in the data. Finally, a four-dimensional (4D) spatiotemporal hypergraph convolutional neural network model was constructed based on the fMRI data for classification. Experimental results on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database demonstrated that the proposed framework outperformed the Hyper Graph Convolutional Network (HyperGCN) framework by 8% and traditional two-dimensional (2D) linear feature extraction methods by 12% in the AD/normal control (NC) classification task. In conclusion, this framework demonstrates an improvement in AD classification compared to mainstream deep learning methods, providing valuable evidence for computer-assisted diagnosis of AD.
A method was proposed to detect pulmonary nodules in low-dose computed tomography (CT) images by two-dimensional convolutional neural network under the condition of fine image preprocessing. Firstly, CT image preprocessing was carried out by image clipping, normalization and other algorithms. Then the positive samples were expanded to balance the number of positive and negative samples in convolutional neural network. Finally, the model with the best performance was obtained by training two-dimensional convolutional neural network and constantly optimizing network parameters. The model was evaluated in Lung Nodule Analysis 2016(LUNA16) dataset by means of five-fold cross validation, and each group's average model experiment results were obtained with the final accuracy of 92.3%, sensitivity of 92.1% and specificity of 92.6%.Compared with other existing automatic detection and classification methods for pulmonary nodules, all indexes were improved. Subsequently, the model perturbation experiment was carried out on this basis. The experimental results showed that the model is stable and has certain anti-interference ability, which could effectively identify pulmonary nodules and provide auxiliary diagnostic advice for early screening of lung cancer.
Auscultation of heart sounds is an important method for the diagnosis of heart conditions. For most people, the audible component of heart sound are the first heart sound (S1) and the second heart sound (S2). Different diseases usually generate murmurs at different stages in a cardiac cycle. Segmenting the heart sounds precisely is the prerequisite for diagnosis. S1 and S2 emerges at the beginning of systole and diastole, respectively. Locating S1 and S2 accurately is beneficial for the segmentation of heart sounds. This paper proposed a method to classify the S1 and S2 based on their properties, and did not take use of the duration of systole and diastole. S1 and S2 in the training dataset were transformed to spectra by short-time Fourier transform and be feed to the two-stream convolutional neural network. The classification accuracy of the test dataset was as high as 91.135%. The highest sensitivity and specificity were 91.156% and 92.074%, respectively. Extracting the features of the input signals artificially can be avoid with the method proposed in this article. The calculation is not complicated, which makes this method effective for distinguishing S1 and S2 in real time.