BLCov: A novel collaborative-competitive broad learning system for COVID-19 detection from radiology images.

With the global outbreak of COVID-19, there is an urgent need to develop an effective and automated detection approach as a faster diagnostic alternative to avoid the spread of COVID-19. Recently, broad learning system (BLS) has been viewed as an alternative method of deep learning which has been applied to many areas. Nevertheless, the sparse autoencoder in classical BLS just considers the representations to reconstruct the input data but ignores the relationship among the extracted features. In this paper, inspired by the effectiveness of the collaborative-competitive representation (CCR) mechanism, a novel collaborative-competitive representation-based autoencoder (CCRAE) is first proposed, and then collaborative-competitive broad learning system (CCBLS) is proposed based on CCRAE to effectively address the issues mentioned above. Moreover, an automated CCBLS-based approach is proposed for COVID-19 detection from radiology images such as CT scans and chest X-ray images. In the proposed approach, a feature extraction module is utilized to extract features from CT scans or chest X-ray images, then we use these features for COVID-19 detection with CCBLS. The experimental results demonstrated that our proposed approach can achieve superior or comparable performance in comparison with ten other state-of-the-art methods.

Multifocus image fusion using superpixel segmentation and superpixel-based mean filtering.

To achieve better performance in multifocus image fusion problems, a new regional approach based on superpixels and superpixel-based mean filtering is proposed in this paper. First, a fast and effective segmentation method is adopted to generate the superpixels over a clarity-enhanced average image. By averaging the clarity information in each superpixel, we make the initial decision map of fusion by regionally selecting sharper superpixels in different source images. Then a novel superpixel-based mean filtering technique is introduced to make full use of spatial consistency in images and the final post-processed decision map is produced. The fused image is constructed by selecting pixels from different source images according to the final decision map. Experimental results demonstrate the proposed method's competitive performance in comparison with state-of-the-art multifocus image fusion approaches.

The Brunner adenoma of the duodenum with positive fecal occult blood and anemia: A case report.

RATIONALE: Brunner gland adenoma (BGA) is a rare benign duodenal tumor that is an adenomatoid lesion in nature rather than an actual tumor. Patients with different adenoma sizes have various clinical manifestations with nonspecific clinical symptoms. Here, We report a case of BGA with black stool and anemia as the primary manifestations. PATIENT CONCERNS: A young female patient was admitted to the hospital because of black stool and anemia. Endoscopic surgery was performed to a definitive diagnosis, and endoscopic tumor-like lesions were resected. DIAGNOSIS: The patient was diagnosed with duodenal Brunner adenoma and received related treatment. OUTCOMES: After treatment, the patient symptoms improved, and he was discharged. LESSONS: Brunner adenoma of the duodenum is a rare benign duodenum tumor. This report paper describes a case of BGA with black stool and anemia as the primary manifestations, followed by endoscopic resection and treatment. The literature on Brunner adenoma of the duodenum has been analyzed and discussed. Clinicians should pay attention to differentiating the disease based on atypical symptoms.

Employing broad learning and non-invasive risk factor to improve the early diagnosis of metabolic syndrome.

Metabolic syndrome (MetS) as a multifactorial disease is highly prevalent in countries and individuals. Monitoring the conventional risk factors (CRFs) would be a cost-effective strategy to target the increasing prevalence of MetS and the potential of noninvasive CRF for precisely detection of MetS in the early stage remains to be explored. From large-scale multicenter MetS clinical dataset, we discover 15 non-invasive CRFs which have strong relevance with MetS and first propose a broad learning-based approach named Genetic Programming Collaborative-competitive Broad Learning System (GP-CCBLS) with noninvasive CRF for early detection of MetS. The proposed GP-CCBLS model can significantly boost the detection performance and achieve the accuracy of 80.54%. This study supports the potential clinical validity of noninvasive CRF to complement general diagnostic criteria for early detecting the MetS and also illustrates possible strength of broad learning in disease diagnosis comparing with other machine learning approaches.

Extreme Fuzzy Broad Learning System: Algorithm, Frequency Principle, and Applications in Classification and Regression.

As an effective alternative to deep neural networks, broad learning system (BLS) has attracted more attention due to its efficient and outstanding performance and shorter training process in classification and regression tasks. Nevertheless, the performance of BLS will not continue to increase, but even decrease, as the number of nodes reaches the saturation point and continues to increase. In addition, the previous research on neural networks usually ignored the reason for the good generalization of neural networks. To solve these problems, this article first proposes the Extreme Fuzzy BLS (E-FBLS), a novel cascaded fuzzy BLS, in which multiple fuzzy BLS blocks are grouped or cascaded together. Moreover, the original data is input to each FBLS block rather than the previous blocks. In addition, we use residual learning to illustrate the effectiveness of E-FBLS. From the frequency domain perspective, we also discover the existence of the frequency principle in E-FBLS, which can provide good interpretability for the generalization of the neural network. Experimental results on classical classification and regression datasets show that the accuracy of the proposed E-FBLS is superior to traditional BLS in handling classification and regression tasks. The accuracy improves when the number of blocks increases to some extent. Moreover, we verify the frequency principle of E-FBLS that E-FBLS can obtain the low-frequency components quickly, while the high-frequency components are gradually adjusted as the number of FBLS blocks increases.

Development and Validation of a Feature-Based Broad-Learning System for Opportunistic Osteoporosis Screening Using Lumbar Spine Radiographs.

RATIONALE AND OBJECTIVES: Osteoporosis is primarily diagnosed using dual-energy X-ray absorptiometry (DXA); yet, DXA is significantly underutilized, causing osteoporosis, an underdiagnosed condition. We aimed to provide an opportunistic approach to screen for osteoporosis using artificial intelligence based on lumbar spine X-ray radiographs. MATERIALS AND METHODS: In this institutional review board-approved retrospective study, female patients aged ≥50 years who received both X-ray scans and DXA of the lumbar vertebrae, in three centers, were included. A total of 1180 cases were used for training and 145 cases were used for testing. We proposed a novel broad-learning system (BLS) and then compared the performance of BLS models using radiomic features and deep features as a source of input. The deep features were extracted using ResNet18 and VGG11, respectively. The diagnostic performances of these BLS models were evaluated with the area under the curve (AUC), sensitivity, and specificity. RESULTS: The incidence rate of osteoporosis in the training and test sets was 35.9% and 37.9%, respectively. The radiomic feature-based BLS model achieved higher testing AUC (0.802 vs. 0.654 vs. 0.632, both P = .002), sensitivity (78.2% vs. 56.4% vs. 50.9%), and specificity (82.2% vs. 74,4% vs. 75.6%) than the two deep feature-based BLS models. CONCLUSION: Our proposed radiomic feature-based BLS model has the potential to expand osteoporosis screening to a broader population by identifying osteoporosis on lumbar spine X-ray radiographs.

Development and validation of a deep-broad ensemble model for early detection of Alzheimer's disease.

Introduction: Alzheimer's disease (AD) is a chronic neurodegenerative disease of the brain that has attracted wide attention in the world. The diagnosis of Alzheimer's disease is faced with the difficulties of insufficient manpower and great difficulty. With the intervention of artificial intelligence, deep learning methods are widely used to assist clinicians in the early recognition of Alzheimer's disease. And a series of methods based on data input with different dimensions have been proposed. However, traditional deep learning models rely on expensive hardware resources and consume a lot of training time, and may fall into the dilemma of local optima. Methods: In recent years, broad learning system (BLS) has provided researchers with new research ideas. Based on the three-dimensional residual convolution module and BLS, a novel broad-deep ensemble model based on BLS is proposed for the early detection of Alzheimer's disease. The Alzheimer's Disease Neuroimaging Initiative (ADNI) MRI image dataset is used to train the model and then we compare the performance of proposed model with previous work and clinicians' diagnosis. Results: The result of experiments demonstrate that the broad-deep ensemble model is superior to previously proposed related works, including 3D-ResNet and VoxCNN, in accuracy, sensitivity, specificity and F1. Discussion: The proposed broad-deep ensemble model is effective for early detection of Alzheimer's disease. In addition, the proposed model does not need the pre-training process of its depth module, which greatly reduces the training time and hardware dependence.

Broad learning for early diagnosis of Alzheimer's disease using FDG-PET of the brain.

Alzheimer's disease (AD) is a progressive neurodegenerative disease, and the development of AD is irreversible. However, preventive measures in the presymptomatic stage of AD can effectively slow down deterioration. Fluorodeoxyglucose positron emission tomography (FDG-PET) can detect the metabolism of glucose in patients' brains, which can help to identify changes related to AD before brain damage occurs. Machine learning is useful for early diagnosis of patients with AD using FDG-PET, but it requires a sufficiently large dataset, and it is easy for overfitting to occur in small datasets. Previous studies using machine learning for early diagnosis with FDG-PET have either involved the extraction of elaborately handcrafted features or validation on a small dataset, and few studies have explored the refined classification of early mild cognitive impairment (EMCI) and late mild cognitive impairment (LMCI). This article presents a broad network-based model for early diagnosis of AD (BLADNet) through PET imaging of the brain; this method employs a novel broad neural network to enhance the features of FDG-PET extracted via 2D CNN. BLADNet can search for information over a broad space through the addition of new BLS blocks without retraining of the whole network, thus improving the accuracy of AD classification. Experiments conducted on a dataset containing 2,298 FDG-PET images of 1,045 subjects from the ADNI database demonstrate that our methods are superior to those used in previous studies on early diagnosis of AD with FDG-PET. In particular, our methods achieved state-of-the-art results in EMCI and LMCI classification with FDG-PET.

Efficient graph convolutional networks for seizure prediction using scalp EEG.

Epilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorithms such as Convolutional Neural Networks and Recurrent Neural Networks have been used to predict epileptic seizures and have obtained better performance than traditional machine learning methods. However, these methods usually transform the Electroencephalogram (EEG) signal into a Euclidean grid structure. The conversion suffers from loss of adjacent spatial information, which results in deep learning models requiring more storage and computational consumption in the process of information fusion after information extraction. This study proposes a general Graph Convolutional Networks (GCN) model architecture for predicting seizures to solve the problem of oversized seizure prediction models based on exploring the graph structure of EEG signals. As a graph classification task, the network architecture includes graph convolution layers that extract node features with one-hop neighbors, pooling layers that summarize abstract node features; and fully connected layers that implement classification, resulting in superior prediction performance and smaller network size. The experiment shows that the model has an average sensitivity of 96.51%, an average AUC of 0.92, and a model size of 15.5 k on 18 patients in the CHB-MIT scalp EEG dataset. Compared with traditional deep learning methods, which require a large number of parameters and computational effort and are demanding in terms of storage space and energy consumption, this method is more suitable for implementation on compact, low-power wearable devices as a standard process for building a generic low-consumption graph network model on similar biomedical signals. Furthermore, the edge features of graphs can be used to make a preliminary determination of locations and types of discharge, making it more clinically interpretable.

A Digital Microfluidic RT-qPCR Platform for Multiple Detections of Respiratory Pathogens.

The coronavirus disease 2019 pandemic has spread worldwide and caused more than six million deaths globally. Therefore, a timely and accurate diagnosis method is of pivotal importance for controlling the dissemination and expansions. Nucleic acid detection by the reverse transcription-polymerase chain reaction (RT-PCR) method generally requires centralized diagnosis laboratories and skilled operators, significantly restricting its use in rural areas and field settings. The digital microfluidic (DMF) technique provides a better option for simultaneous detections of multiple pathogens with fewer specimens and easy operation. In this study, we developed a novel digital microfluidic RT-qPCR platform for multiple detections of respiratory pathogens. This method can simultaneously detect eleven respiratory pathogens, namely, mycoplasma pneumoniae (MP), chlamydophila pneumoniae (CP), streptococcus pneumoniae (SP), human respiratory syncytial virus A (RSVA), human adenovirus (ADV), human coronavirus (HKU1), human coronavirus 229E (HCoV-229E), human metapneumovirus (HMPV), severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), influenza A virus (FLUA) and influenza B virus (FLUB). The diagnostic performance was evaluated using positive plasmids samples and clinical specimens compared with off-chip individual RT-PCR testing. The results showed that the limit of detections was around 12 to 150 copies per test. The true positive rate, true negative rate, positive predictive value, negative predictive value, and accuracy of DMF on-chip method were 93.33%, 100%, 100%, 99.56%, and 99.85%, respectively, as validated by the off-chip RT-qPCR counterpart. Collectively, this study reported a cost-effective, high sensitivity and specificity on-chip DMF RT-qPCR system for detecting multiple respiratory pathogens, which will greatly contribute to timely and effective clinical management of respiratory infections in medical resource-limited settings.

Effects of early hyperbaric oxygen therapy on clinical outcome in postoperative patients with intracranial aneurysm.

OBJECTIVE: To investigate the effects of hyperbaric oxygen (HBO2) in postoperative patients with intracranial aneurysm. METHODS: A total of 120 patients who underwent clipping of intracranial aneurysm of the anterior circulation were randomized into the HBO2 group (n = 60) or the Control group (n = 60). Compared with the Control group, patients in the HBO2 group received additional HBO2 therapy, which was initiated within one to three days as soon as they were deemed clinically stable, for at least 20 sessions (one session per day). Mean flow velocities of the middle cerebral artery (MCA) on the operative approach side were measured on Days 1, 3, 7, 14 and 21 after operation. CT scans were performed on Days 1, 7, 14 and 21 after surgery to determine the abnormal density volume in the operative area. Cases associated with symptomatic cerebral vasospasm (CVS) were assessed on Days 3, 7 as well as 14, and the functional state determined by Karnofsky Performance Scale (KPS) score was evaluated on Days 3 and 21 after operation. Finally, Glasgow Outcome Scale (GOS) scores were obtained at six months after surgery. RESULTS: There were no differences between groups in terms of the mean flow velocities of MCA on the operative approach side, the cases with symptomatic CVS, and the KPS scores within three days after surgery (P > 0.05). Compared with those of the Control group, the mean flow velocities of MCA on the operative approach side were significantly lower in the HBO2 group on Days 7 and 14 (P < 0.05 or P < 0.01). On Days 7, 14 and 21, patients in the HBO2 group had smaller HBO2 density volume in the operative region than those in the Control group (P < 0.05). The HBO2 group developed less cases of symptomatic CVS than the Control group did on Days 7 (chi2 = 4.04, P < 0.05) and 14 (chi2 = 4.18, P < 0.05). The KPS scores were higher on Day 21 after surgery in the HBO2 group (P < 0.05). More patients in the HBO2 group achieved GOS scores of 4 and 5 at six months after surgery (chi2 = 6.032, P < 0.05). CONCLUSIONS: Early HBO2 appears to be beneficial asan adjunctive treatment of postoperative intracranial aneurysm. Attenuating postoperative CVS, brain edema, and cerebral ischemia contributes to the effectiveness of HBO2.

An Image-Based Benchmark Dataset and a Novel Object Detector for Water Surface Object Detection.

Water surface object detection is one of the most significant tasks in autonomous driving and water surface vision applications. To date, existing public large-scale datasets collected from websites do not focus on specific scenarios. As a characteristic of these datasets, the quantity of the images and instances is also still at a low level. To accelerate the development of water surface autonomous driving, this paper proposes a large-scale, high-quality annotated benchmark dataset, named Water Surface Object Detection Dataset (WSODD), to benchmark different water surface object detection algorithms. The proposed dataset consists of 7,467 water surface images in different water environments, climate conditions, and shooting times. In addition, the dataset comprises a total of 14 common object categories and 21,911 instances. Simultaneously, more specific scenarios are focused on in WSODD. In order to find a straightforward architecture to provide good performance on WSODD, a new object detector, named CRB-Net, is proposed to serve as a baseline. In experiments, CRB-Net was compared with 16 state-of-the-art object detection methods and outperformed all of them in terms of detection precision. In this paper, we further discuss the effect of the dataset diversity (e.g., instance size, lighting conditions), training set size, and dataset details (e.g., method of categorization). Cross-dataset validation shows that WSODD significantly outperforms other relevant datasets and that the adaptability of CRB-Net is excellent.

Histone deacetylase 1 promotes glioblastoma cell proliferation and invasion via activation of PI3K/AKT and MEK/ERK signaling pathways.

Histone deacetylase 1 (HDAC1) plays a crucial role in cancer progression and development. This enzyme has been confirmed to be a key regulator of tumor biology functions, such as tumor cell proliferation, migration and invasion. However, HDAC1 expression in glioma remains controversial, and its specific function and molecular mechanism in glioblastoma is poorly understood. In this study, our findings demonstrated that protein and mRNA levels of HDAC1 were increased in glioma cell lines and glioma tissues compared to normal glial cell lines and non-neoplastic brain tissues, respectively. Furthermore, HDAC1 knockdown cells displayed decreased proliferation and invasion capabilities, whereas HDAC1 overexpressing glioblastoma cells displayed more proliferation and invasion capabilities in vitro. These novel outcomes suggested that knockdown of HDAC1 possibly suppressed the expression of phosphorylated AKT (p-AKT) and phosphorylated ERK (p-ERK) proteins, while overexpression of HDAC1 significantly increased p-AKT and p-ERK protein in glioblastoma cells. In addition, knockdown of HDAC1 repressed subcutaneous tumor growth in vivo, and led to down-regulation of p-AKT and p-ERK protein in U87 MG xenograft tumors. For the first time, we have demonstrated that HDAC1 promotes proliferation and invasion in glioblastoma cells by activating PI3K/AKT and MEK/ERK signaling pathways in vitro and in vivo. These results suggest that HDAC1 may be a novel biomarker and potential therapeutic target in glioblastoma.

MicroRNA-200b inhibits pituitary tumor cell proliferation and invasion by targeting PKCα.

The present study aimed to investigate the expression of miR-200b and protein kinase Cα (PKCα) in pituitary tumors and to determine whether miR-200b may inhibit proliferation and invasion of pituitary tumor cells. The regulation of PKCα expression was targeted in order to find novel targets for the treatment of pituitary tumors. In total, 53 pituitary tumor tissue samples were collected; these included 28 cases of invasive pituitary tumors and 25 cases of non-invasive tumors, in addition to 5 normal pituitaries. The expression level of miR-200b in the pituitary tumor tissue was detected by quantitative polymerase chain reaction (qPCR) and the expression of PKCα protein was detected by immunohistochemistry. A PKCα 3'untranslated region (UTR) luciferase vector was constructed and a dual luciferase reporter gene assay was employed in order to examine the effect of miR-200b on the PKCα 3'UTR luciferase activity. AtT-20 cells were transfected with miR-200b mimics, PKCα siRNA and miR-200b mimics + PKCα, and the changes in cellular proliferation, invasion and apoptosis were observed via MTT, Transwell assay and flow cytometric analysis. Furthermore, PKCα mRNA expression was determined by qPCR, and Western blotting was performed to detect the expression of PKCα protein. miR-200b revealed downregulation in invasive pituitary tumor tissue, and the expression level was significantly down-regulated compared with normal and non-invasive pituitary tumor tissue (P<0.01). In addition, the positive rate of PKCα protein expression in invasive pituitary tumor tissues was significantly higher than in normal and non-invasive tissues (P<0.01). PKCα protein levels are inversely correlated with miR-200b levels in invasive pituitary tumor tissues (r=-0.436, P=0.021). The dual luciferase reporter gene assay revealed that miR-200b could specifically bind to the 3'UTR of PKCα and significantly inhibit the luciferase activity by 39% (P<0.01). Upregulation of miR-200b or downregulation of PKCα could suppress cell proliferation and invasion, and increase apoptosis of AtT-20 cells. It was revealed that PKCα siRNA could suppress both proliferation and invasion of AtT-20 cells and partially simulate the function of miR-200b. Expression of PKCα mRNA and protein decreased significantly in AtT-20 cells overexpressing miR-200b. Additionally, miR-200b was significantly down-regulated in invasive pituitary tumor tissue and inversely correlated with PKCα protein levels. In conclusion, miR-200b inhibited proliferation and invasiveness and promoted the apoptosis of pituitary tumor cells by targeting PKCα. The observations of the present study indicate that miR-200b and PKCα may serve as promising therapeutic targets for invasive pituitary tumors.

MicroRNA-34a inhibits cell proliferation and induces cell apoptosis of glioma cells via targeting of Bcl-2.

Glioblastoma is a highly malignant brain tumor, characterized by the poor prognosis and high recurrence rates. Despite therapeutic strategies including surgery, radiotherapy and chemotherapy, the median survival of patients is only 14.6 months. MicroRNAs (miRNAs) have been considered as a novel type of gene regulator. Previous studies have demonstrated that the expression of miRNA­34a (miR­34a) is significantly associated with the grade and prognosis of glioma. However, the exact function of miR­34a on glioma progression and underlying mechanisms remain to be elucidated. The present study investigated the function of miR­34a in U87 human glioma cells by exogenously transfecting cells with an miR­34a mimic. Overexpression of miR­34a inhibited proliferation, and induced apoptosis of U87 cells. The current study also demonstrated that B­cell lymphoma 2 (Bcl­2) was the target gene of miR­34a, as demonstrated by luciferase assays. Furthermore, restoring the expression of Bcl­2 was indicated to partially block the miR­34a­induced apoptosis. Thus, data from the present study identified miR­34a as a tumor suppressor in glioma by, at least partially, targeting Bcl­2. This may provide future novel diagnostic and therapeutic strategies for human glioma.

[Effects of probiotics on blood glucose levels and clinical outcomes in patients with severe craniocerebral trauma].

OBJECTIVE: To investigate the effects of probiotics on blood glucose levels and clinical outcomes in patients suffering from severe craniocerebral trauma. METHODS: A prospective randomized control study was conducted. Fifty-two severe craniocerebral trauma patients admitted to intensive care unit (ICU) were randomized into experimental or control group (each n=26). All patients received conventional treatment according to Guidelines for the Clinical Management of Traumatic Brain Injury and enteral nutrition within 24-48 hours after admission through nasogastric tube. In addition, the experimental group received 1×10(9) bacteria of viable probiotics (Golden Bifid, 3.5 g for 3 times per day) per day for 21 days. The fasting blood glucose levels were determined in the morning before intervention and on day 4, 8, 15, 21 after intervention. Amount of insulin used during hospitalization, Glasgow coma scale (GCS) scores, length of ICU stay, and 28-day mortality rate were studied. RESULTS: There was no difference in term of the blood glucose levels between two groups before intervention. On day 8 and 15 after intervention, significantly lower levels of fasting blood glucose were observed in the experimental group compared with those of the control group (8 days: 6.6±1.2 mmol/L vs. 8.0±2.7 mmol/L, t=-2.500, P=0.017; 15 days: 6.1±1.4 mmol/L vs. 7.2±2.2 mmol/L, t=-2.269, P=0.028). There were significantly less patients treated with insulin or shorter days of insulin therapy in experimental group than in control group [19.2% (5/26) vs. 46.2% (12/26), χ(2)=4.282, P=0.039; 1.6±0.9 vs. 4.3±3.1, t=-2.698, P=0.017]. The length of ICU stay was significantly shorter in the experimental group than that of control group (6.8±3.8 days vs. 10.7±7.3 days, t=-2.123, P=0.034). No significant differences were found about the GCS scores (before intervention: 6.3±1.0 vs. 6.4±1.0, t=-0.408, P=0.685; 21 days after intervention: 10.1±4.0 vs. 9.6±4.3, t=0.435, P=0.665) and 28-day mortality rate [11.5% (3/26) vs. 19.2% (5/26), χ(2)=0.148, P=0.701] between experimental group and control group. CONCLUSIONS: Probiotics could facilitate blood glucose control in patients with severe craniocerebral injury. The underlying mechanisms and its long-term efficacy in this category of patients, however, need to be further investigated.