Graph Neural Networks With Adaptive Confidence Discrimination.

Graph neural networks (GNNs) have demonstrated remarkable success for semisupervised node classification. However, these GNNs are still limited to the conventionally semisupervised framework and cannot fully leverage the potential value of large numbers of unlabeled samples. The pseudolabeling method in semisupervised learning (SSL) is widely recognized because it can clearly leverage unlabeled samples. Nevertheless, the existing pseudolabeling methods usually utilize a fixed threshold for all classes and only use a portion of unlabeled samples (ones with high prediction confidence), which leads to class imbalance and low data utilization. To solve these problems, we propose GNNs with adaptive confidence discrimination (ACDGNN) to fully utilize unlabeled samples for facilitating semisupervised node classification. Specifically, an adaptive confidence discrimination module is designed to divide all unlabeled nodes into two subsets by comparing their confidence scores with the adaptive confidence threshold at each training epoch. Then, different constraint strategies for two subset nodes are employed. Unlabeled nodes with high confidence are used to iteratively expand the label set, while ones with low confidence learn discriminative features by applying contrastive learning. Validated by extensive experiments, the proposed ACDGNN delivers significant accuracy gains over the previous SOTAs: an average improvement of 2.0% on all datasets and 5.7% on the Flickr dataset in particular.

Label-Aware Dual Graph Neural Networks for Multi-Label Fundus Image Classification.

Fundus disease is a complex and universal disease involving a variety of pathologies. Its early diagnosis using fundus images can effectively prevent further diseases and provide targeted treatment plans for patients. Recent deep learning models for classification of this disease are gradually emerging as a critical research field, which is attracting widespread attention. However, in practice, most of the existing methods only focus on local visual cues of a single image, and ignore the underlying explicit interaction similarity between subjects and correlation information among pathologies in fundus diseases. In this paper, we propose a novel label-aware dual graph neural networks for multi-label fundus image classification that consists of population-based graph representation learning and pathology-based graph representation learning modules. Specifically, we first construct a population-based graph by integrating image features and non-image information to learn patient's representations by incorporating associations between subjects. Then, we represent pathologies as a sparse graph where its nodes are associated with pathology-based feature vectors and the edges correspond to probability of the co-occurrence of labels to generate a set of classifier scores by the propagation of multi-layer graph information. Finally, our model can adaptively recalibrate multi-label outputs. Detailed experiments and analysis of our results show the effectiveness of our method compared with state-of-the-art multi-label fundus image classification methods.

Digital phase-shift method based on distance mapping for phase recovery of an ESPI fringe pattern.

In view of the limitation of the traditional method to recover the phase of the single fringe pattern, we propose a digital phase-shift method based on distance mapping for phase recovery of an electronic speckle pattern interferometry fringe pattern. First, the direction of each pixel point and the centerline of the dark fringe are extracted. Secondly, the normal curve of the fringe is calculated according to the fringe orientation to obtain the fringe moving direction. Thirdly, the distance between each pixel point and the next pixel point in the same phase is calculated by a distance mapping method according to the adjacent centerlines; then the moving distance of the fringes is obtained. Next, combining the moving direction and moving distance, the fringe pattern after the digital phase shift is obtained by full-field interpolation. Finally, the full-field phase corresponding to the original fringe pattern is recovered by four-step phase shifting. The method can extract the fringe phase from a single fringe pattern through digital image processing technology. The experiments show that the proposed method can effectively improve the phase recovery accuracy of a single fringe pattern.

HGBER: Heterogeneous Graph Neural Network With Bidirectional Encoding Representation.

Heterogeneous graphs with multiple types of nodes and link relationships are ubiquitous in many real-world applications. Heterogeneous graph neural networks (HGNNs) as an efficient technique have shown superior capacity of dealing with heterogeneous graphs. Existing HGNNs usually define multiple meta-paths in a heterogeneous graph to capture the composite relations and guide neighbor selection. However, these models only consider the simple relationships (i.e., concatenation or linear superposition) between different meta-paths, ignoring more general or complex relationships. In this article, we propose a novel unsupervised framework termed Heterogeneous Graph neural network with bidirectional encoding representation (HGBER) to learn comprehensive node representations. Specifically, the contrastive forward encoding is firstly performed to extract node representations on a set of meta-specific graphs corresponding to meta-paths. We then introduce the reversed encoding for the degradation process from the final node representations to each single meta-specific node representations. Moreover, to learn structure-preserving node representations, we further utilize a self-training module to discover the optimal node distribution through iterative optimization. Extensive experiments on five open public datasets show that the proposed HGBER model outperforms the state-of-the-art HGNNs baselines by 0.8%-8.4% in terms of accuracy on most datasets in various downstream tasks.

RNN-combined graph convolutional network with multi-feature fusion for tuberculosis cavity segmentation.

Tuberculosis is a common infectious disease in the world. Tuberculosis cavities are common and an important imaging signs in tuberculosis. Accurate segmentation of tuberculosis cavities has practical significance for indicating the activity of lesions and guiding clinical treatment. However, this task faces challenges such as blurred boundaries, irregular shapes, different location and size of lesions and similar structures on computed tomography (CT) to other lung diseases or tissues. To overcome these problems, we propose a novel RNN-combined graph convolutional network (R2GCN) method, which integrates the bidirectional recurrent network (BRN) and graph convolution network (GCN) modules. First, feature extraction is performed on the input image by VGG-16 or ResNet-50 to obtain the feature map. The feature map is then used as the input of the two modules. On the one hand, we adopt the BRN to retrieve contextual information from the feature map. On the other hand, we take the vector for each location in the feature map as input nodes and utilize GCN to extract node topology information. Finally, two types of features obtained fuse together. Our strategy can not only make full use of node correlations and differences, but also obtain more precise segmentation boundaries. Extensive experiments on CT images of cavitary patients with tuberculosis show that our proposed method achieves the best segmentation accuracy than compared segmentation methods. Our method can be used for the diagnosis of tuberculosis cavity and the evaluation of tuberculosis cavity treatment.

Structural Attention Graph Neural Network for Diagnosis and Prediction of COVID-19 Severity.

With rapid worldwide spread of Coronavirus Disease 2019 (COVID-19), jointly identifying severe COVID-19 cases from mild ones and predicting the conversion time (from mild to severe) is essential to optimize the workflow and reduce the clinician's workload. In this study, we propose a novel framework for COVID-19 diagnosis, termed as Structural Attention Graph Neural Network (SAGNN), which can combine the multi-source information including features extracted from chest CT, latent lung structural distribution, and non-imaging patient information to conduct diagnosis of COVID-19 severity and predict the conversion time from mild to severe. Specifically, we first construct a graph to incorporate structural information of the lung and adopt graph attention network to iteratively update representations of lung segments. To distinguish different infection degrees of left and right lungs, we further introduce a structural attention mechanism. Finally, we introduce demographic information and develop a multi-task learning framework to jointly perform both tasks of classification and regression. Experiments are conducted on a real dataset with 1687 chest CT scans, which includes 1328 mild cases and 359 severe cases. Experimental results show that our method achieves the best classification (e.g., 86.86% in terms of Area Under Curve) and regression (e.g., 0.58 in terms of Correlation Coefficient) performance, compared with other comparison methods.

Joint segmentation of retinal layers and macular edema in optical coherence tomography scans based on RLMENet.

PURPOSE: The segmentation of retinal layers and fluid lesions on retinal optical coherence tomography (OCT) images is an important component of screening and diagnosing retinopathy in clinical ophthalmic treatment. We designed a novel network for accurate segmentation of the seven tissue layers of the retina and lesion areas of diabetic macular edema (DME), which can assist doctors to quantitatively analyze the disease. METHODS: In this article, we propose the Retinal Layer Macular Edema Network (RLMENet) model to achieve end-to-end joint segmentation of retinal layers and fluids. The network employs dense multiscale attention to enhance the extraction of retinal layer and fluid detail information and achieve efficient long-range modeling, which improves the receptive field and obtains multiscale features. As the more complex decoder part is designed, which integrates more low-level feature information on the decoder side, more features are extracted to gradually restore the resolution of the feature map and improve the segmentation accuracy. RESULTS: We used part of the OCT2017 dataset to train and verify the model to divide the data into a training set, validation set, and test set and set it to a 7:2:1 ratio. We evaluated our method on the ISIC2017 dataset. Experimental results showed that the RLMENet model designed in this work can accurately segment seven retinal tissue layers and DME lesions on the retinal OCT dataset. Finally, the MIoU value in the test set reached 86.55%. The model can be extended to other medical image segmentation datasets to achieve better segmentation performance. CONCLUSIONS: The proposed method was superior to the existing segmentation methods, achieved a more refined segmentation effect and provided an auxiliary analysis tool for clinical diagnosis and treatment. This article is protected by copyright. All rights reserved.

Pathological Voice Detection and Classification Based on Multimodal Transmission Network.

OBJECTIVES: Describing pronunciation features from multiple perspectives can help doctors accurately diagnose the pathological type of a patient's voice. According to the two modal information of sound signal and electroglottography (EGG) signal, this paper proposes a pathological voice detection and classification algorithm based on multimodal transmission network. METHODS: Firstly, we used the short-time Fourier transform (STFT) to map the features of the two signals, and designed the Mel filter to obtain the Mel spectogram. Then, the constructed multimodal transmission network extracted features from Mel spectogram and applied Multimodal Transfer Module (MMTM) module. Finally, the fusion layer can integrate multimodal information, and the full connection layer diagnoses and classifies voice pathology according to the fused features. RESULTS: The experiment was based on 1179 subjects in Saarbrücken voice database (SVD), and the average accuracy, recall, specificity and F1 score of pathological voice classification reached 98.02%, 98.23%, 97.82% and 97.95% respectively. Compared with other algorithms, the classification accuracy is significantly improved. CONCLUSIONS: The proposed model can integrate multiple modal information to obtain more comprehensive and stable voice features and improve the accuracy of pathological voice classification. Future research will further explore in reducing the time-consuming and complexity of the model.

Artificial Intelligence-Assisted Terahertz Imaging for Rapid and Label-Free Identification of Efficient Light Formula in Laser Therapy.

Photodynamic therapy (PDT) is considered a promising noninvasive therapeutic strategy in biomedicine, especially by utilizing low-level laser therapy (LLLT) in visible and near-infrared spectra to trigger biological responses. The major challenge of PDT in applications is the complicated and time-consuming biological methodological measurements in identification of light formulas for different diseases. Here, we demonstrate a rapid and label-free identification method based on artificial intelligence (AI)-assisted terahertz imaging for efficient light formulas in LLLT of acute lung injury (ALI). The gray histogram of terahertz images is developed as the biophysical characteristics to identify the therapeutic effect. Label-free terahertz imaging is sequentially performed using rapid super-resolution imaging reconstruction and automatic identification algorithm based on a voting classifier. The results indicate that the therapeutic effect of LLLT with different light wavelengths and irradiation times for ALI can be identified using this method with a high accuracy of 91.22% in 33 s, which is more than 400 times faster than the biological methodology and more than 200 times faster than the scanning terahertz imaging technology. It may serve as a new tool for the development and application of PDT.

[Retracted] Knockdown of ADAM10 inhibits migration and invasion of fibroblast-like synoviocytes in rheumatoid arthritis.

Following the publication of this paper, an interested reader noted that certain of the western blotting assay data shown in Fig. 4 were strikingly similar to data appearing in different form in other articles by different authors. Owing to the fact that the contentious data in the above article had already been published elsewhere, or were already under consideration for publication, prior to its submission to Molecular Medicine Reports, the Editor has decided that this paper should be retracted from the Journal. After having been in contact with the authors, they agreed with the decision to retract the paper. The Editor apologizes to the readership for any inconvenience caused. [the original article was published in Molecular Medicine Reports 12: 5517-5523, 2015; DOI: 10.3892/mmr.2015.4011].

Voice pathology detection and classification from speech signals and EGG signals based on a multimodal fusion method.

Automatic voice pathology detection and classification plays an important role in the diagnosis and prevention of voice disorders. To accurately describe the pronunciation characteristics of patients with dysarthria and improve the effect of pathological voice detection, this study proposes a pathological voice detection method based on a multi-modal network structure. First, speech signals and electroglottography (EGG) signals are mapped from the time domain to the frequency domain spectrogram via a short-time Fourier transform (STFT). The Mel filter bank acts on the spectrogram to enhance the signal's harmonics and denoise. Second, a pre-trained convolutional neural network (CNN) is used as the backbone network to extract sound state features and vocal cord vibration features from the two signals. To obtain a better classification effect, the fused features are input into the long short-term memory (LSTM) network for voice feature selection and enhancement. The proposed system achieves 95.73% for accuracy with 96.10% F1-score and 96.73% recall using the Saarbrucken Voice Database (SVD); thus, enabling a new method for pathological speech detection.

Incomplete multi-modal representation learning for Alzheimer's disease diagnosis.

Alzheimers disease (AD) is a complex neurodegenerative disease. Its early diagnosis and treatment have been a major concern of researchers. Currently, the multi-modality data representation learning of this disease is gradually becoming an emerging research field, attracting widespread attention. However, in practice, data from multiple modalities are only partially available, and most of the existing multi-modal learning algorithms can not deal with the incomplete multi-modality data. In this paper, we propose an Auto-Encoder based Multi-View missing data Completion framework (AEMVC) to learn common representations for AD diagnosis. Specifically, we firstly map the original complete view to a latent space using an auto-encoder network framework. Then, the latent representations measuring statistical dependence learned from the complete view are used to complement the kernel matrix of the incomplete view in the kernel space. Meanwhile, the structural information of original data and the inherent association between views are maintained by graph regularization and Hilbert-Schmidt Independence Criterion (HSIC) constraints. Finally, a kernel based multi-view method is applied to the learned kernel matrix for the acquisition of common representations. Experimental results achieved on Alzheimers Disease Neuroimaging Initiative (ADNI) datasets validate the effectiveness of the proposed method.

Lung segmentation method with dilated convolution based on VGG-16 network.

Lung cancer has become one of the life-threatening killers. Lung disease need to be assisted by CT images taken doctor's diagnosis, and the segmented CT image of the lung parenchyma is the first step to help doctor diagnosis. For the problem of accurately segmenting the lung parenchyma, this paper proposes a segmentation method based on the combination of VGG-16 and dilated convolution. First of all, we use the first three parts of VGG-16 network structure to convolution and pooling the input image. Secondly, using multiple sets of dilated convolutions make the network has a large enough receptive field. Finally, the multi-scale convolution features are fused, and each pixel is predicted using MLP to segment the parenchymal region. Experimental results were produced over state of the art on 137 images which key metrics Dice similarity coefficient (DSC) is 0.9867. Experimental results show that this method can effectively segment the lung parenchymal area, and compared to other conventional methods better.

Encoder-decoder with dense dilated spatial pyramid pooling for prostate MR images segmentation.

Automatic segmentation of prostate magnetic resonance (MR) images has great significance for the diagnosis and clinical application of prostate diseases. It faces enormous challenges because of the low contrast of the tissue boundary and the small effective area of the prostate MR images. In order to solve these problems, we propose a novel end-to-end professional network which consists of an Encoder-Decoder structure with dense dilated spatial pyramid pooling (DDSPP) for prostate segmentation based on deep learning. First, the DDSPP module is used to extract the multi-scale convolution features in the prostate MR images, and then the decoder is used to capture the clear boundary of prostate. Competitive results are produced over state of the art on 130 MR images which key metrics Dice similarity coefficient (DSC) and Hausdorff distance (HD) are 0.954 and 1.752 mm respectively. Experimental results show that our method has high accuracy and robustness.

Acoustic Field of a Linear Phased Array: A Simulation Study of Ultrasonic Circular Tube Material.

As ultrasonic wave field radiated by an ultrasonic transducer influences the results of ultrasonic nondestructive testing, simulation and emulation are widely used in nondestructive testing. In this paper, a simulation study is proposed to detect defects in a circular tube material. Firstly, the ultrasonic propagation behavior was analyzed, and a formulation of the Multi-Gaussian beam model (MGB) based on a superposition of Gaussian beams is described. The expression of the acoustic field from a linear phased-array ultrasonic transducer in the condition of a convex interface on the circular tube material is proposed. Secondly, in order to make the tapered probe wedge better fit the curved circular tube material and carry out the ultrasonic inspection of the curved surface, it was necessary to pare the angle probe wedge. Finally, acoustic field simulations in a circular tube were carried out and analyzed. The simulation results indicated that the method of ultrasonic phased-array inspection is feasible in circular tube testing. Tube materials with different curvatures need different array element lengths and widths to get the desired focused beam.

[Segmentation of retinal image vessels based on fully convolutional network with depthwise separable convolution and channel weighting].

Diseases such as diabetes and hypertension can lead to change the shape of the retinal blood vessels. Segmentation of fundus images is a key step in the process of quantitative analysis of the disease, which is instructive in the analysis and diagnosis of clinical diseases. In this paper, a method for the segmentation of retinal image vessels based on fully convolutional network (FCN) with depthwise separable convolution and channel weighting is presented. Firstly, CLAHE and Gamma correction of the green channel of the fundus image are used to enhance the contrast. Then, in order to adapt to network training, the enhanced image is divided into patches to expand the data. Finally, the depthwise separable convolution instead of the standard convolution method is used to increase the network width. Meanwhile, the channel weighting module is introduced to explicitly model the relationship between the characteristic channels in order to improve the distinguishability of the features. The combination of them is applied to the FCN and the results of expert manual identification are used to supervise the experiment on the DRIVE database. The results show that the segmentation accuracy of the proposed method in DRIVE database reached 0.963 0 and AUC reached 0.983 1. The segmentation accuracy in STARE database reached 0.962 0 and AUC achieved 0.983 0. To some extent, the proposed method has better feature resolution and better segmentation performance.

Super resolution reconstruction for medical image based on adaptive multi-dictionary learning and structural self-similarity.

To improve the quality of the super-resolution (SR) reconstructed medical images, an improved adaptive multi-dictionary learning method is proposed, which uses the combined information of medical image itself and the natural images database. In training dictionary section, it uses the upper layer images of pyramid which are generated by the self-similarity of low resolution images. In reconstruction section, the top layer image of pyramid is taken as the initial reconstruction image, and medical image's SR reconstruction is achieved by regularization term which is the non-local structure self-similarity of the image. This method can make full use of the same scale and different scale similar information of medical images. Simulation experiments are carried out on natural images and medical images, and the experimental results show the proposed method is effective for improving the effect of medical image SR reconstruction.

Automatic non-proliferative diabetic retinopathy screening system based on color fundus image.

BACKGROUND: Non-proliferative diabetic retinopathy is the early stage of diabetic retinopathy. Automatic detection of non-proliferative diabetic retinopathy is significant for clinical diagnosis, early screening and course progression of patients. METHODS: This paper introduces the design and implementation of an automatic system for screening non-proliferative diabetic retinopathy based on color fundus images. Firstly, the fundus structures, including blood vessels, optic disc and macula, are extracted and located, respectively. In particular, a new optic disc localization method using parabolic fitting is proposed based on the physiological structure characteristics of optic disc and blood vessels. Then, early lesions, such as microaneurysms, hemorrhages and hard exudates, are detected based on their respective characteristics. An equivalent optical model simulating human eyes is designed based on the anatomical structure of retina. Main structures and early lesions are reconstructed in the 3D space for better visualization. Finally, the severity of each image is evaluated based on the international criteria of diabetic retinopathy. RESULTS: The system has been tested on public databases and images from hospitals. Experimental results demonstrate that the proposed system achieves high accuracy for main structures and early lesions detection. The results of severity classification for non-proliferative diabetic retinopathy are also accurate and suitable. CONCLUSIONS: Our system can assist ophthalmologists for clinical diagnosis, automatic screening and course progression of patients.

Evidence for an Association of ERCC1 Expression and Mismatch Repair Status with Overall Survival in Colorectal Cancer Patients.

BACKGROUND: The aim in this study was to determine if an association of excision repair cross-complementing group 1 (ERCC1) gene and mismatch repair (MMR) status with overall survival (OS) could be found from our analysis of a large cohort of Chinese colorectal cancer patients (CRC). METHODS: In total, 2,233 tissue samples isolated from individual CRC tumors were assessed by immunohistochemistry for the expression of ERCC1 and 4 MMR genes. RESULTS: The rates of proficient MMR (pMMR) and ERCC1 expression were 89.6 and 90.7%, respectively. We found that patients with positive ERCC1 expression and deficient (d)MMR status had higher overall survival (OS) than those with either positive ERCC1 and pMMR, negative ERCC1 and dMMR, or negative ERCC1 expression and pMMR status (OS 79 vs. 69 vs. 66 vs. 61%, hazard ratio (HR) 0.90, 95% confidence interval (CI) 0.80-1.00; p = 0.043). Despite this finding, we found no statistical difference in OS between ERCC1-positive and -negative CRC patients when ERCC1 expression was considered alone (OS 70 vs. 62%, HR 0.82, 95% CI 0.65-1.04; p = 0.11). CONCLUSION: Our results indicate that the combined examination of ERCC1 expression and dMMR status can be used to aid OS assessment in CRC patients.