Theoretical Study on Ethylamine Dissociation Reactions Using VRC-VTST and SS-QRRK Methods

Barrierless bond dissociation reactions play an important role in fuel combustion. In this work, the pressure-dependent dissociation rate constants of ethylamine (EA) are accurately determined using variable-reaction-coordinate variational transition-state theory combined with the system-specific quantum Rice-Ramsperger-Kassel method. Before the kinetics calculations, the performances of four density functional theory methods in describing the bond dissociation of EA are evaluated against the benchmark method, FIC-MRCISD(T)+Q/cc-pVTZ, and the MN15-L/cc-pVTZ method is the best choice. By comparison of the Gibbs free energies and the rate constants for the bond dissociation reactions of EA, ethanol, and propane, the influence of functional groups on the reaction kinetics is discussed. The kinetics calculations show that the dissociation rate constants of EA are sensitive to pressure at low pressures and high temperatures, and the dominant channel is the reaction that yields C2H5 and NH2 radicals. A literature combustion model of EA is updated with our calculations, and the satisfactory agreement between the model predictions and reported ignition delay times of EA suggests the reliability of our calculations.

[Research of miR-29a on TGF-β1/Smad3 pathway in pulmonary fibrosis induced by neodymium oxide]

Objective: To exploring the regulatory effect of miR-29a on the transforming growth factor-β1 (TGF-β1) /Smad homolog 3 (Smad3) pathway during the process of rare earth neodymium oxide (Nd(2)O(3)) induced pulmonary fibrosis in mice. Methods: In March 2021, 72 SPF grade C57/BL6J male mice were selected and randomly divided into a control group, Nd(2)O(3) group, Nd(2)O(3)+miR-29a agomir group, and Nd(2)O(3)+NC agomir group, with 18 mice in each group. The Nd(2)O(3) group, Nd(2)O(3)+miR-29a agomir group, and Nd(2)O(3)+NC agomir group were treated with non exposed tracheal instillation, with a dust concentration of 250 mg/ml and a dust volume of 0.1 ml. The control group was given the same volume of physiological saline. After exposure to Nd(2)O(3), 0.1 ml (5 nmol) of miR-29a agomir was injected into the tail vein of mice in the Nd(2)O(3)+miR-29a agomir group every 3 days, while 0.1 ml of NC agomir was injected into the tail vein of mice in the Nd(2)O(3)+NC agomir group. On the 7 th, 14 th, and 28 th days after dust exposure, 6 mice were killed in each group, and the lung tissue of the mice was taken out. HE staining was used to observe the pathological status of the mouse lung tissue; ELISA method was used to detect the levels of TGF-β1 and connective tissue growth factor (CTGF) in lung tissue; Use qRT-PCR detection method to detect the expression level of TGF-β1 mRNA; Using immunofluorescence assay to detect the expression level of Smad3 in mouse lung tissue; Use bioinformatics websites such as TargetScan7 and miRDB to predict the target gene of miR-29a. When the metrological date were satisfied with normal distribution, Mean±SD was used for comparison between groups, t test was used for two indepent samples, and LSD method was used when the variance was homogeneity in pairwise comparison. Results: HE staining showed that the Nd(2)O(3) group of mice showed obvious infiltration of inflammatory cells and structural disorder of alveoli in the early stage of lung tissue. At 28 days, the collagen fibers in the mouse lung tissue increased and the lung tissue showed fibrotic honeycomb like changes. The degree of pulmonary fibrosis in the Nd(2)O(3)+miR-29a agomir group of mice was significantly reduced; The content of TGF-β1 and CTGF in the lung tissue of mice in the Nd(2)O(3)+miR-29a agomir group was lower than that in the Nd(2)O(3)+NC agomir group (P<0.05) ; The relative expression level of TGF-β1 in the lung tissue of mice in the Nd(2)O(3)+miR-29a agomir group was lower than that in the Nd(2)O(3)+NC agomir group (P<0.05) ; The expression level of Smad3 in the nucleus of the Nd(2)O(3)+miR-29a agomir group was lower than that of the Nd(2)O(3)+NC agomir group (P<0.05). The prediction results of bioinformatics websites have found 152 downstream target genes related to miR-29a, among which FBN1, MAP2K6, KPNB1, COL1A2, SNIP1, LAMC1, and SP1 genes may be related to the regulatory effect of miR-29a on TGF-β1/Smad3 signaling pathway. Conclusion: miR-29a may affect lung fibrosis induced by rare earth Nd(2)O(3) exposure in mice by regulating TGF-β1/Smad3 signaling pathway. Overexpression of miR-29a may inhibit TGF-β1/Smad3 signaling pathway and reduce the degree of pulmonary fibrosis in mice.

Tuberculosis Diagnosis Using Deep Transferred EfficientNet

Tuberculosis is a very deadly disease, with more than half of all tuberculosis cases dead in countries and regions with relatively poor health care resources. Fortunately, the disease is curable, and early diagnosis and medication can go a long way toward curing TB patients. Unfortunately, traditional methods of TB diagnosis rely on specialist doctors, which is lacking in areas with high TB mortality rates. Diagnostic methods based on artificial intelligence technology are one of the solutions to this problem. We propose a Deep Transferred EfficientNet with SVM (DTE-SVM), which replaces the pre-trained EfficientNet classification layer with an SVM classifier and achieves auspicious performance on a small dataset. After ten runs of 10-fold Cross-Validation, the DTE-SVM has a sensitivity of 93.89±1.96, a specificity of 95.35±1.31, a precision of 95.30±1.24, an accuracy of 94.62±1.00, and an F1-score of 94.62±1.00. In addition, our study conducted ablation studies on the effect of the SVM classifier on model performance and briefly discussed the results.

[In vitro activity of β-lactamase inhibitors avibanvctam and relebactam in combination with β-lactams against multidrug-resistant Mycobacterium tuberculosis and mutations of resistance genes]

Objective: To evaluate the activity of six β-lactams in combination with three β-lactamase inhibitors against mycobacterium tuberculosis(MTB) in vitro. Methods: A total of 105 multidrug-resistant tuberculosis (MDR-TB) strains from different regions of Henan province from January to September 2020 were included in this study. Drug activity of six β-lactams (biapenem, meropenem, imipenem, doripenem, ertapenem and tebipenem) alone or in combination with β-lactamase inhibitors (clavulanic acid, avibactam and relebactam) was examined by minimum inhibitory concentration method (MICs) against 105 clinical isolates. Mutations of blaC, ldtmt1 and ldtmt2 were analyzed by PCR and DNA sequencing. Chi-square test was used to compare the antimicrobial activities of different β-lactam drugs. Results: Out of the β-lactams used herein, tebipenem was the most effective against MDR-TB and had an MIC50 value of 8 mg/L(χ2=123.70,P=0.001). Besides, after the addition of β-lactamase inhibitors, the MICs of most β-lactam drugs were reduced more evidently in the presence of avibactam and relebactam compared to clavulanic acid.Especially, relebactam decreased both the MIC50 and MIC90 of telbipenem by 16-fold, and diluted the MIC of 23 (21.90%) and 41 (39.04%) isolatesby 32-fold and 16-fold.In addition, a total of 13.33% (14/105) of isolates harbored mutations in the blaC gene, with three different nucleotide substitutions: AGT333AGG, AAC638ACC and ATC786ATT. For the strains with Ser111Arg and Asn213Thr substitution in BlaC, the MIC values of the meropenem-clavulanate combination were reduced compared with a synonymous single nucleotide polymorphism (SNP) group. Conclusions: Both avibactam and relebactam had better synergistic effects on β-lactams than clavulanic acid. The combination of tebipenem and relebactam showed the most potent activity against MDR-TB isolates. In addition, the Ser111Arg and Asn213Thr substitution of BlaC may be associated with an increased susceptibility of MDR-TB isolates to meropenem in the presence of clavulanate.

[Historical review of schistosomiasis prevention and treatment in southern Anhui from 1950 to 1970]

From 1950 to 1970, under the leadership of the central government, workstations for the prevention and control of schistosomiasis were established in the southern Anhui region. In terms of controlling the source of the disease, light and severe epidemic areas were scientifically divided. By opening new ditches to replace old ones, changing paddy fields to dry fields, and using traditional Chinese medicine and Western medicine to prevent the intermediate host of schistosomiasis, oncomelania from surviving. By managing the feces from human and animals and controlling the water source, the transmission route of schistosome eggs has been effectively cut off. At the same time, the education of hygiene awareness among susceptible populations were strengthened. In terms of diagnosis, modern physical and biochemical detection were used to improve the accuracy of diagnosis. In terms of treatment, by combining traditional Chinese medicine and Western medicine, together with the splenectomy, the cure rates were improved. In the process of preventing and controlling schistosomiasis, the governments of Anhui Province and the southern region of Anhui Province achieved good results, providing useful reference for the prevention and control of other diseases.

Automated diagnosis of cardiovascular diseases from cardiac magnetic resonance imaging using deep learning models: A review

In recent years, cardiovascular diseases (CVDs) have become one of the leading causes of mortality globally. At early stages, CVDs appear with minor symptoms and progressively get worse. The majority of people experience symptoms such as exhaustion, shortness of breath, ankle swelling, fluid retention, and other symptoms when starting CVD. Coronary artery disease (CAD), arrhythmia, cardiomyopathy, congenital heart defect (CHD), mitral regurgitation, and angina are the most common CVDs. Clinical methods such as blood tests, electrocardiography (ECG) signals, and medical imaging are the most effective methods used for the detection of CVDs. Among the diagnostic methods, cardiac magnetic resonance imaging (CMRI) is increasingly used to diagnose, monitor the disease, plan treatment and predict CVDs. Coupled with all the advantages of CMR data, CVDs diagnosis is challenging for physicians as each scan has many slices of data, and the contrast of it might be low. To address these issues, deep learning (DL) techniques have been employed in the diagnosis of CVDs using CMR data, and much research is currently being conducted in this field. This review provides an overview of the studies performed in CVDs detection using CMR images and DL techniques. The introduction section examined CVDs types, diagnostic methods, and the most important medical imaging techniques. The following presents research to detect CVDs using CMR images and the most significant DL methods. Another section discussed the challenges in diagnosing CVDs from CMRI data. Next, the discussion section discusses the results of this review, and future work in CVDs diagnosis from CMR images and DL techniques are outlined. Finally, the most important findings of this study are presented in the conclusion section.

Diagnosis of cerebral microbleed via VGG and extreme learning machine trained by Gaussian map bat algorithm

Cerebral microbleed (CMB) is a serious public health concern. It is associated with dementia, which can be detected with brain magnetic resonance image (MRI). CMBs often appear as tiny round dots on MRIs, and they can be spotted anywhere over brain. Therefore, manual inspection is tedious and lengthy, and the results are often short in reproducible. In this paper, a novel automatic CMB diagnosis method was proposed based on deep learning and optimization algorithms, which used the brain MRI as the input and output the diagnosis results as CMB and non-CMB. Firstly, sliding window processing was employed to generate the dataset from brain MRIs. Then, a pre-trained VGG was employed to obtain the image features from the dataset. Finally, an ELM was trained by Gaussian-map bat algorithm (GBA) for identification. Results showed that the proposed method VGG-ELM-GBA provided better generalization performance than several state-of-the-art approaches.

CTMLP: Can MLPs replace CNNs or transformers for COVID-19 diagnosis?

BACKGROUND

Convolutional Neural Networks (CNNs) and the hybrid models of CNNs and Vision Transformers (VITs) are the recent mainstream methods for COVID-19 medical image diagnosis. However, pure CNNs lack global modeling ability, and the hybrid models of CNNs and VITs have problems such as large parameters and computational complexity. These models are difficult to be used effectively for medical diagnosis in just-in-time applications.

METHODS

Therefore, a lightweight medical diagnosis network CTMLP based on convolutions and multi-layer perceptrons (MLPs) is proposed for the diagnosis of COVID-19. The previous self-supervised algorithms are based on CNNs and VITs, and the effectiveness of such algorithms for MLPs is not yet known. At the same time, due to the lack of ImageNet-scale datasets in the medical image domain for model pre-training. So, a pre-training scheme TL-DeCo based on transfer learning and self-supervised learning was constructed. In addition, TL-DeCo is too tedious and resource-consuming to build a new model each time. Therefore, a guided self-supervised pre-training scheme was constructed for the new lightweight model pre-training.

RESULTS

The proposed CTMLP achieves an accuracy of 97.51%, an f1-score of 97.43%, and a recall of 98.91% without pre-training, even with only 48% of the number of ResNet50 parameters. Furthermore, the proposed guided self-supervised learning scheme can improve the baseline of simple self-supervised learning by 1%-1.27%.

CONCLUSION

The final results show that the proposed CTMLP can replace CNNs or Transformers for a more efficient diagnosis of COVID-19. In addition, the additional pre-training framework was developed to make it more promising in clinical practice.

[The role of Keap1/Nrf2/HO-1 signal pathway in liver injury induced by rare earth neodymium oxide in mice]

Objective: To investigate the role of Keap1/Nrf2/HO-1 signaling pathway in liver injury induced by neodymium oxide (Nd(2)O(3)) in mice. Methods: In March 2021, forty-eight SPF grade healthy male C57BL/6J mice were randomly divided into control group (0.9% NaCl), low dose group (62.5 mg/ml Nd(2)O(3)), medium dose group (125.0 mg/ml Nd(2)O(3)), and high dose group (250.0 mg/ml Nd(2)O(3)), each group consisted of 12 animals. The infected groups were treated with Nd(2)O(3) suspension by non-exposed tracheal drip and were killed 35 days after dust exposure. The liver weight of each group was weighed and the organ coefficient was calculated. The content of Nd(3+) in liver tissue was detected by inductively coupled plasma mass spectrometry (ICP-MS). HE staining and immunofluorescence was used to observe the changes of inflammation and nuclear entry. The mRNA expression levels of Keap1, Nrf2 and HO-1 in mice liver tissue were detected by qRT-PCR. Western blotting was used to detect the protein expression levels of Keap1 and HO-1. The contents of catalase (CAT), glutathione peroxidase (GSH-Px) and total superoxide dismutase (T-SOD) were detected by colorimetric method. The contents of interleukin 1β (IL-1β), interleukin 6 (IL-6) and tumor necrosis factor α (TNF-α) were determined by ELISA. The data was expressed in Mean±SD. Two-independent sample t-test was used for inter-group comparison, and one-way analysis of variance was used for multi-group comparison. Results: Compared with the control group, the liver organ coefficient of mice in medium and high dose groups were increased, and the Nd(3+) accumulation in liver of mice in all dose groups were significantly increased (P<0.05). Pathology showed that the structure of liver lobules in the high dose group was slightly disordered, the liver cells showed balloon-like lesions, the arrangement of liver cell cords was disordered, and the inflammatory exudation was obvious. Compared with the control group, the levels of IL-1β and IL-6 in liver tissue of mice in all dose groups were increased, and the levels of TNF-α in liver tissue of mice in high dose group were increased (P<0.05). Compared with the control group, the mRNA and protein expression levels of Keap1 in high dose group were significantly decreased, while the mRNA expression level of Nrf2, the mRNA and protein expression levels of HO-1 were significantly increased (P<0.05), and Nrf2 was successfully activated into the nucleus. Compared with the control group, the activities of CAT, GSH-Px and T-SOD in high dose group were significantly decreased (P<0.05) . Conclusion: A large amount of Nd(2)O(3) accumulates in the liver of male mice, which may lead to oxidative stress and inflammatory response through activation of Keap1/Nrf2/HO-1 signal pathway. It is suggested that Keap1/Nrf2/HO-1 signal pathway may be one of the mechanisms of Nd(2)O(3) expose-induced liver injury in mice.

A Survey of Convolutional Neural Network in Breast Cancer

Problems

For people all over the world, cancer is one of the most feared diseases. Cancer is one of the major obstacles to improving life expectancy in countries around the world and one of the biggest causes of death before the age of 70 in 112 countries. Among all kinds of cancers, breast cancer is the most common cancer for women. The data showed that female breast cancer had become one of the most common cancers.

Aims

A large number of clinical trials have proved that if breast cancer is diagnosed at an early stage, it could give patients more treatment options and improve the treatment effect and survival ability. Based on this situation, there are many diagnostic methods for breast cancer, such as computer-aided diagnosis (CAD).

Methods

We complete a comprehensive review of the diagnosis of breast cancer based on the convolutional neural network (CNN) after reviewing a sea of recent papers. Firstly, we introduce several different imaging modalities. The structure of CNN is given in the second part. After that, we introduce some public breast cancer data sets. Then, we divide the diagnosis of breast cancer into three different tasks: 1. classification; 2. detection; 3. segmentation.

Conclusion

Although this diagnosis with CNN has achieved great success, there are still some limitations. (i) There are too few good data sets. A good public breast cancer dataset needs to involve many aspects, such as professional medical knowledge, privacy issues, financial issues, dataset size, and so on. (ii) When the data set is too large, the CNN-based model needs a sea of computation and time to complete the diagnosis. (iii) It is easy to cause overfitting when using small data sets.

An Evolutionary Attention-Based Network for Medical Image Classification

Deep learning has become a primary choice in medical image analysis due to its powerful representation capability. However, most existing deep learning models designed for medical image classification can only perform well on a specific disease. The performance drops dramatically when it comes to other diseases. Generalizability remains a challenging problem. In this paper, we propose an evolutionary attention-based network (EDCA-Net), which is an effective and robust network for medical image classification tasks. To extract task-related features from a given medical dataset, we first propose the densely connected attentional network (DCA-Net) where feature maps are automatically channel-wise weighted, and the dense connectivity pattern is introduced to improve the efficiency of information flow. To improve the model capability and generalizability, we introduce two types of evolution: intra- and inter-evolution. The intra-evolution optimizes the weights of DCA-Net, while the inter-evolution allows two instances of DCA-Net to exchange training experience during training. The evolutionary DCA-Net is referred to as EDCA-Net. The EDCA-Net is evaluated on four publicly accessible medical datasets of different diseases. Experiments showed that the EDCA-Net outperforms the state-of-the-art methods on three datasets and achieves comparable performance on the last dataset, demonstrating good generalizability for medical image classification.

[Clinical and chest CT features of immune checkpoint inhibitor-related pneumonitis]

Objective: To explore the clinical and chest computed tomography (CT) features and the outcome of immune checkpoint inhibitor-related pneumonitis (CIP). Methods: Clinical and chest CT data of 38 CIP patients with malignant tumors from the Cancer Hospital, Chinese Academy of Medical Sciences between August 2017 and April 2021 were retrospectively reviewed, and the outcomes of pneumonitis were followed up. Results: The median time from the administration of immune checkpoint inhibitors (ICIs) to the onset of CIP was 72.5 days in 38 patients with CIP, and 22 patients developed CIP within 3 months after the administration of ICIs. The median occurrence time of CIP in 24 lung cancer patients was 54.5 days, earlier than 119.0 days of non-lung cancer patients (P=0.138), with no significant statistical difference. 34 patients (89.5%) were accompanied by symptoms when CIP occurred. The common clinical symptoms were cough (29 cases) and dyspnea (27 cases). The distribution of CIP on chest CT was asymmetric in 31 cases and symmetrical in 7 cases. Among the 24 lung cancer patients, inflammation was mainly distributed ipsilateral to the primary lung cancer site in 16 cases and diffusely distributed throughout the lung in 8 cases. Ground glass opacities (37 cases) and consolidation (30 cases) were the common imaging manifestations, and organizing pneumonia (OP) pattern (15 cases) was the most common pattern. In 30 CIP patients who were followed up for longer than one month, 17 cases had complete absorption (complete absorption group), and 13 cases had partial absorption or kept stable (incomplete absorption group). The median occurrence time of CIP in the complete absorption group was 55 days, shorter than 128 days of the incomplete absorption group (P=0.022). Compared with the incomplete absorption group, there were less consolidation(P=0.010) and CIP were all classified as hypersensitivity pneumonitis (HP) pattern (P=0.004) in the complete absorption group. Conclusions: CIP often occurs within 3 months after ICIs treatment, and the clinical and CT findings are lack of specificity. Radiologic features may have a profound value in predicting the outcome of CIP.

[Yin Chan Quan Shu, the Obstetrics and Gynecology Monograph by Wang Kentang]

Yin Chan Quan Shu (Obstetrics and gynecology monograph) is a monograph on obstetrics and gynecology compiled by Wang Kentang in the Ming Dynasty. It had four volumes and was published in the thirtieth year of Wanli (1602) in the Ming Dynasty after it was edited by Zhang Shoukong and others. It was found that Yin Chan Quan Shu has four versions remaining. They were the version printed by Shu Lin Qiao Shan Tang in the Ming Dynasty, held in the National Library of China and the Cabinet Library of Japanese Official Documents Library; the version revised according to the version of Shu Lin Qiao Shan Tang, held in the Library of Capital Medical University, Tianjin Medical College, Shanghai Branch of the Chinese Medical Association, the Library of Guangzhou University of Chinese Medicine and the Cabinet Library of the National Archives of Japan; the version based on the version of Shu Lin Qiao Shan Tang in the Ming Dynasty, transcribed in the fourth year of Wen Hua (1807), collected in the Cabinet Library of the National Archives of Japan; the version transcribed according to the revised version in the Ming Dynasty, collected in the Shanghai Branch of the Chinese Medical Association. It was found that there was no evidence to support the existence of the so-called "version of Kangxi in the Qing Dynasty". This means almost all versions remaining came from the versions published in the Ming Dynasty. The references of Yin Chan Quan Shu came from Pulse Classic (Mai Jing), Chan Bao, Fu Ren Da Quan Liang Fang and other works with the supplement and development by Wang Kentang.Yin Chan Quan Shu was the main sources and foundation of the Criteria of Syndrome Identification and Treatment in Gynecology (Nv Ke Zheng Zhi Zhun Sheng) by Wang Kentang.

ELUCNN for explainable COVID-19 diagnosis

COVID-19 is a positive-sense single-stranded RNA virus caused by a strain of coronavirus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Several noteworthy variants of SARS-CoV-2 were declared by WHO as Alpha, Beta, Gamma, Delta, and Omicron. Till 13/Dec/2022, it has caused 6.65 million death tolls, and over 649 million confirmed positive cases. Based on the convolutional neural network (CNN), this study first proposes a ten-layer CNN as the backbone model. Then, the exponential linear unit (ELU) is introduced to replace ReLU, and the traditional convolutional block is now transformed into conv-ELU. Finally, an ELU-based CNN (ELUCNN) model is proposed for COVID-19 diagnosis. Besides, the MDA strategy is used to enhance the size of the training set. We develop a mobile app integrating ELUCNN, and this web app is run on a client-server modeled structure. Ten runs of the tenfold cross-validation experiment show our model yields a sensitivity of 94.41 ± 0.98 , a specificity of 94.84 ± 1.21 , an accuracy of 94.62 ± 0.96 , and an F1 score of 94.61 ± 0.95 . The ELUCNN model and mobile app are effective in COVID-19 diagnosis and give better results than 14 state-of-the-art COVID-19 diagnosis models concerning accuracy.

ReRNet: A Deep Learning Network for Classifying Blood Cells

AIMS

Blood cell classification helps detect various diseases. However, the current classification model of blood cells cannot always get great results. A network that automatically classifies blood cells can provide doctors with data as one of the criteria for diagnosing patients' disease types and severity. If doctors diagnose blood cells, doctors could spend lots of time on the diagnosis. The diagnosis progress is very tedious. Doctors can make some mistakes when they feel tired. On the other hand, different doctors may have different points on the same patient.

METHODS

We propose a ResNet50-based ensemble of randomized neural networks (ReRNet) for blood cell classification. ResNet50 is used as the backbone model for feature extraction. The extracted features are fed to 3 randomized neural networks (RNNs): Schmidt neural network, extreme learning machine, and dRVFL. The outputs of the ReRNet are the ensemble of these 3 RNNs based on the majority voting mechanism. The 5 × 5-fold cross-validation is applied to validate the proposed network.

RESULTS

The average-accuracy, average-sensitivity, average-precision, and average-F1-score are 99.97%, 99.96%, 99.98%, and 99.97%, respectively.

CONCLUSIONS

The ReRNet is compared with 4 state-of-the-art methods and achieves the best classification performance. The ReRNet is an effective method for blood cell classification based on these results.

PSTCNN: Explainable COVID-19 diagnosis using PSO-guided self-tuning CNN

Since 2019, the coronavirus disease-19 (COVID-19) has been spreading rapidly worldwide, posing an unignorable threat to the global economy and human health. It is a disease caused by severe acute respiratory syndrome coronavirus 2, a single-stranded RNA virus of the genus Betacoronavirus. This virus is highly infectious and relies on its angiotensin-converting enzyme 2-receptor to enter cells. With the increase in the number of confirmed COVID-19 diagnoses, the difficulty of diagnosis due to the lack of global healthcare resources becomes increasingly apparent. Deep learning-based computer-aided diagnosis models with high generalisability can effectively alleviate this pressure. Hyperparameter tuning is essential in training such models and significantly impacts their final performance and training speed. However, traditional hyperparameter tuning methods are usually time-consuming and unstable. To solve this issue, we introduce Particle Swarm Optimisation to build a PSO-guided Self-Tuning Convolution Neural Network (PSTCNN), allowing the model to tune hyperparameters automatically. Therefore, the proposed approach can reduce human involvement. Also, the optimisation algorithm can select the combination of hyperparameters in a targeted manner, thus stably achieving a solution closer to the global optimum. Experimentally, the PSTCNN can obtain quite excellent results, with a sensitivity of 93.65%±1.86%, a specificity of 94.32%±2.07%, a precision of 94.30%±2.04%, an accuracy of 93.99%±1.78%, an F1-score of 93.97%±1.78%, Matthews Correlation Coefficient of 87.99%±3.56%, and Fowlkes-Mallows Index of 93.97%±1.78%. Our experiments demonstrate that compared to traditional methods, hyperparameter tuning of the model using an optimisation algorithm is faster and more effective.

WACPN: A Neural Network for Pneumonia Diagnosis

Community-acquired pneumonia (CAP) is considered a sort of pneumonia developed outside hospitals and clinics. To diagnose community-acquired pneumonia (CAP) more efficiently, we proposed a novel neural network model. We introduce the 2-dimensional wavelet entropy (2d-WE) layer and an adaptive chaotic particle swarm optimization (ACP) algorithm to train the feed-forward neural network. The ACP uses adaptive inertia weight factor (AIWF) and Rossler attractor (RA) to improve the performance of standard particle swarm optimization. The final combined model is named WE-layer ACP-based network (WACPN), which attains a sensitivity of 91.87±1.37%, a specificity of 90.70±1.19%, a precision of 91.01±1.12%, an accuracy of 91.29±1.09%, F1 score of 91.43±1.09%, an MCC of 82.59±2.19%, and an FMI of 91.44±1.09%. The AUC of this WACPN model is 0.9577. We find that the maximum deposition level chosen as four can obtain the best result. Experiments demonstrate the effectiveness of both AIWF and RA. Finally, this proposed WACPN is efficient in diagnosing CAP and superior to six state-of-the-art models. Our model will be distributed to the cloud computing environment.

Covid-19 Diagnosis by WE-SAJ

With a global COVID-19 pandemic, the number of confirmed patients increases rapidly, leaving the world with very few medical resources. Therefore, the fast diagnosis and monitoring of COVID-19 are one of the world's most critical challenges today. Artificial intelligence-based CT image classification models can quickly and accurately distinguish infected patients from healthy populations. Our research proposes a deep learning model (WE-SAJ) using wavelet entropy for feature extraction, two-layer FNNs for classification and the adaptive Jaya algorithm as a training algorithm. It achieves superior performance compared to the Jaya-based model. The model has a sensitivity of 85.47±1.84, specificity of 87.23±1.67 precision of 87.03±1.34, an accuracy of 86.35±0.70, and F1 score of 86.23±0.77, Matthews correlation coefficient of 72.75±1.38, and Fowlkes-Mallows Index of 86.24±0.76. Our experiments demonstrate the potential of artificial intelligence techniques for COVID-19 diagnosis and the effectiveness of the Self-adaptive Jaya algorithm compared to the Jaya algorithm for medical image classification tasks.

[Effects of Nd(2)O(3) exposure of rare earth particles on C57 BL/6J male mice sex hormone secretion and CYP11A1/PLZF/STRA8 protein expression]

Objective: To explore the effects of Nd(2)O(3) exposure to rare earth particles on the secretion of sex hormones, cytochrome P450 family member 11A1 (CYP11A1) , spermatogenesis markers promyelocytic leukemia zinc finger protein (PLZF) and retinoic acid stimulating gene 8 (STRA8) protein in C57 BL/6J male mice. Methods: In March 2021, Forty-eight male C57 BL/6J mice aged 6-8 weeks divided into control group and Nd(2)O(3) exposure low, medium and high dose groups (exposing doses of 62.5, 125.0, 250.0 mg/ml Nd(2)O(3)) , 12 per group. The mice in the Nd(2)O(3) groups were perfused with different doses of Nd(2)O(3) suspension by a one-time non-exposing tracheal instillation method, and the control group was perfused with an equal volume of normal saline, with a volume of 0.1 ml, to establish a mouse reproductive function injury model. After 28 days of exposure, the mice's body weight, testes and epididymis were weighed, and the organ coefficients were calculated; the two epididymis were taken to make a sperm suspension to determine the sperm count, survival rate, and deformity rate; inductively coupled plasma mass spectrometry (ICP-MS) method was used to detect the content of Nd in mouse testis tissue; HE staining was used to detect testicular tissue pathological changes and quantitative analysis; enzyme-linked immunosorbent assay (ELISA) method was used to detect serum luteinizing hormone (LH) and follicle stimulating hormone (FSH) and testosterone (T) content; western blot was used to detect the protein levels of CYP11A1, PLZF and STRA8 in testicular tissues. Results: Compared with the control group, with the increase of the exposure dose, the Nd content in the testis of the mice showed an increasing trend, the sperm survival rate and LH showed a decreasing trend, and the sperm deformity rate showed an increasing trend (P<0.05) ; Pathological showed that the number of sperm in the seminiferous tubules of the testicular tissue in the Nd(2)O(3) medium and high dose groups was significantly reduced, and the germinal epithelial disintegration, intraepithelial vacuolization, and exfoliation of spermatogenic cells and supporting cells occurred; The height of germinal epithelium was significantly reduced, and the percentage of damaged seminiferous tubules showed an increasing trend (P<0.05) ; FSH and T levels in serum in the middle and high dose groups of Nd(2)O(3), and CYP11A1, PLZF and STRA8 proteins in testicular tissues showed a downward trend with increasing dose (P<0.05) . Conclusion: The rare earth particulate Nd(2)O(3) may interfere with the expression of CYP11A1, PLZF and STRA8 protein, thereby causing the disorder of sex hormone secretion in the body, the maintenance of spermatogonia and the obstruction of the process of meiosis, causing reproductive function damage.

[Experience in emergency response to 2019-nCoV positive cases in an international test competition]

Objective: To analyze the performance of emergency response to 2019 novel coronavirus (2019-nCoV) positive cases in an international test competition in an Winter Olympic Game venue and provide evidences for the COVID-19 prevention and control in similar competitions. Methods: A retrospective analysis on the epidemiological investigation and nucleic acid test results of the cases, the implementation of prevention and control measures, including the communication with sport teams and others, was conducted. Results: The positive cases of 2019-nCoV among entering people were detected before entry, at airport, hotel and venue. Two positive cases were reported before entry, 2 positive cases infected previously and 3 asymptomatic cases were reported after the entry. The venue public health team and local CDC conducted epidemiological investigation and contact assessment jointly in a timely and efficient manner. No local secondary transmission occurred, but the nucleic acid test results of positive persons fluctuated, posing serious challenges to the implementation of prevention and control measures. Conclusion: In large scale international competition, there is high risk of imported COVID-19. It is necessary to fully consider the fluctuation of nucleic acid test results, the criteria for determination and cancellation of positive results and give warm care to positive cases in the emergency response.

A review on extreme learning machine

Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising performance. In this paper, we hope to present a comprehensive review on ELM. Firstly, we will focus on the theoretical analysis including universal approximation theory and generalization. Then, the various improvements are listed, which help ELM works better in terms of stability, efficiency, and accuracy. Because of its outstanding performance, ELM has been successfully applied in many real-time learning tasks for classification, clustering, and regression. Besides, we report the applications of ELM in medical imaging: MRI, CT, and mammogram. The controversies of ELM were also discussed in this paper. We aim to report these advances and find some future perspectives.

[The versions of Shiguzhai Hui Ju Jian Bian Dan Fang by Wu Mianxue]

Shiguzhai Hui Ju Jian Bian Dan Fang, was the only medical book for prescription and formula collected and compiled by Wu Mianxue in the period of the Wanli in the Ming Dynasty (1573-1620). It had seven volumes in total with six of them popular at that time. The volumes contained 1,460 folk formula and clinical prescriptions which were divided into 111 categories based on their corresponding symptoms of diseases. The set was issued in the beginning of the 17^th century, with only three subsets of the volumes left in China today. The three remained versions were the subset of volumes 4-5 left in the Ming Dynasty in the Medical College of Tianjin, the subset of volumes 1-2 and 6-7, with preface, left in the seventeenth of the Shun Zhi Period in the Qing Dynasty (1660) in the Shanghai University of Chinese Medicine and the subset of volumes 4 and 6-7 from time unknown. Additionally, three unabridged versions were found in the Cabinet Library of the National Archives of Japan. They were the Ming version with preface of the seventeenth of the Shun Zhi Period in the Qing Dynasty and a hand-copied version left in the Edo period. It was found that the preface in the seventeenth of the Shun Zhi Period in the Qing Dynasty in both of these versions in China as well as the version in Japan, were counterfeit. The main texts in these versions were edited according to the Ming version. The hand-copied version in Japan was transcribed by Kasahara Eisan and edited by Tanba Motoken according to the Ming version in the late Edo Period.

COVID-19 classification using chest X-ray images based on fusion-assisted deep Bayesian optimization and Grad-CAM visualization

The COVID-19 virus's rapid global spread has caused millions of illnesses and deaths. As a result, it has disastrous consequences for people's lives, public health, and the global economy. Clinical studies have revealed a link between the severity of COVID-19 cases and the amount of virus present in infected people's lungs. Imaging techniques such as computed tomography (CT) and chest x-rays can detect COVID-19 (CXR). Manual inspection of these images is a difficult process, so computerized techniques are widely used. Deep convolutional neural networks (DCNNs) are a type of machine learning that is frequently used in computer vision applications, particularly in medical imaging, to detect and classify infected regions. These techniques can assist medical personnel in the detection of patients with COVID-19. In this article, a Bayesian optimized DCNN and explainable AI-based framework is proposed for the classification of COVID-19 from the chest X-ray images. The proposed method starts with a multi-filter contrast enhancement technique that increases the visibility of the infected part. Two pre-trained deep models, namely, EfficientNet-B0 and MobileNet-V2, are fine-tuned according to the target classes and then trained by employing Bayesian optimization (BO). Through BO, hyperparameters have been selected instead of static initialization. Features are extracted from the trained model and fused using a slicing-based serial fusion approach. The fused features are classified using machine learning classifiers for the final classification. Moreover, visualization is performed using a Grad-CAM that highlights the infected part in the image. Three publically available COVID-19 datasets are used for the experimental process to obtain improved accuracies of 98.8, 97.9, and 99.4%, respectively.

NSCGCN: A novel deep GCN model to diagnosis COVID-19

AIM

Corona Virus Disease 2019 (COVID-19) was a lung disease with high mortality and was highly contagious. Early diagnosis of COVID-19 and distinguishing it from pneumonia was beneficial for subsequent treatment.

OBJECTIVES

Recently, Graph Convolutional Network (GCN) has driven a significant contribution to disease diagnosis. However, limited by the nature of the graph convolution algorithm, deep GCN has an over-smoothing problem. Most of the current GCN models are shallow neural networks, which do not exceed five layers. Furthermore, the objective of this study is to develop a novel deep GCN model based on the DenseGCN and the pre-trained model of deep Convolutional Neural Network (CNN) to complete the diagnosis of chest X-ray (CXR) images.

METHODS

We apply the pre-trained model of deep CNN to perform feature extraction on the data to complete the extraction of pixel-level features in the image. And then, to extract the potential relationship between the obtained features, we propose Neighbourhood Feature Reconstruction Algorithm to reconstruct them into graph-structured data. Finally, we design a deep GCN model that exploits the graph-structured data to diagnose COVID-19 effectively. In the deep GCN model, we propose a Node-Self Convolution Algorithm (NSC) based on feature fusion to construct a deep GCN model called NSCGCN (Node-Self Convolution Graph Convolutional Network).

RESULTS

Experiments were carried out on the Computed Tomography (CT) and CXR datasets. The results on the CT dataset confirmed that: compared with the six state-of-the-art (SOTA) shallow GCN models, the accuracy and sensitivity of the proposed NSCGCN had improve 8% as sensitivity (Sen.) = 87.50%, F1 score = 97.37%, precision (Pre.) = 89.10%, accuracy (Acc.) = 97.50%, area under the ROC curve (AUC) = 97.09%. Moreover, the results on the CXR dataset confirmed that: compared with the fourteen SOTA GCN models, sixteen SOTA CNN transfer learning models and eight SOTA COVID-19 diagnosis methods on the COVID-19 dataset. Our proposed method had best performances as Sen. = 96.45%, F1 score = 96.45%, Pre. = 96.61%, Acc. = 96.45%, AUC = 99.22%.

CONCLUSION

Our proposed NSCGCN model is effective and performed better than the thirty-eight SOTA methods. Thus, the proposed NSC could help build deep GCN models. Our proposed COVID-19 diagnosis method based on the NSCGCN model could help radiologists detect pneumonia from CXR images and distinguish COVID-19 from Ordinary Pneumonia (OPN). The source code of this work will be publicly available at https://github.com/TangChaosheng/NSCGCN.

AVNC: Attention-Based VGG-Style Network for COVID-19 Diagnosis by CBAM

(Aim) To detect COVID-19 patients more accurately and more precisely, we proposed a novel artificial intelligence model. (Methods) We used previously proposed chest CT dataset containing four categories: COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy subjects. First, we proposed a novel VGG-style base network (VSBN) as backbone network. Second, convolutional block attention module (CBAM) was introduced as attention module into our VSBN. Third, an improved multiple-way data augmentation method was used to resist overfitting of our AI model. In all, our model was dubbed as a 12-layer attention-based VGG-style network for COVID-19 (AVNC) (Results) This proposed AVNC achieved the sensitivity/precision/F1 per class all above 95%. Particularly, AVNC yielded a micro-averaged F1 score of 96.87%, which is higher than 11 state-of-the-art approaches. (Conclusion) This proposed AVNC is effective in recognizing COVID-19 diseases.

COVID-19 classification using chest X-ray images: A framework of CNN-LSTM and improved max value moth flame optimization

Coronavirus disease 2019 (COVID-19) is a highly contagious disease that has claimed the lives of millions of people worldwide in the last 2 years. Because of the disease's rapid spread, it is critical to diagnose it at an early stage in order to reduce the rate of spread. The images of the lungs are used to diagnose this infection. In the last 2 years, many studies have been introduced to help with the diagnosis of COVID-19 from chest X-Ray images. Because all researchers are looking for a quick method to diagnose this virus, deep learning-based computer controlled techniques are more suitable as a second opinion for radiologists. In this article, we look at the issue of multisource fusion and redundant features. We proposed a CNN-LSTM and improved max value features optimization framework for COVID-19 classification to address these issues. The original images are acquired and the contrast is increased using a combination of filtering algorithms in the proposed architecture. The dataset is then augmented to increase its size, which is then used to train two deep learning networks called Modified EfficientNet B0 and CNN-LSTM. Both networks are built from scratch and extract information from the deep layers. Following the extraction of features, the serial based maximum value fusion technique is proposed to combine the best information of both deep models. However, a few redundant information is also noted; therefore, an improved max value based moth flame optimization algorithm is proposed. Through this algorithm, the best features are selected and finally classified through machine learning classifiers. The experimental process was conducted on three publically available datasets and achieved improved accuracy than the existing techniques. Moreover, the classifiers based comparison is also conducted and the cubic support vector machine gives better accuracy.

A weighted least squares optimisation strategy for medical image super resolution via multiscale convolutional neural networks for healthcare applications

Medical imaging is an essential medical diagnosis system subsequently integrated with artificial intelligence for assistance in clinical diagnosis. The actual medical images acquired during the image capturing procedures generate poor quality images as a result of numerous physical restrictions of the imaging equipment and time constraints. Recently, medical image super-resolution (SR) has emerged as an indispensable research subject in the community of image processing to address such limitations. SR is a classical computer vision operation that attempts to restore a visually sharp high-resolution images from the degraded low-resolution images. In this study, an effective medical super-resolution approach based on weighted least squares optimisation via multiscale convolutional neural networks (CNNs) has been proposed for lesion localisation. The weighted least squares optimisation strategy that particularly is well-suited for progressively coarsening the original images and simultaneously extract multiscale information has been executed. Subsequently, a SR model by training CNNs based on wavelet analysis has been designed by carrying out wavelet decomposition of optimized images for multiscale representations. Then multiple CNNs have been trained separately to approximate the wavelet multiscale representations. The trained multiple convolutional neural networks characterize medical images in many directions and multiscale frequency bands, and thus facilitate image restoration subject to increased number of variations depicted in different dimensions and orientations. Finally, the trained CNNs regress wavelet multiscale representations from a LR medical images, followed by wavelet synthesis that forms a reconstructed HR medical image. The experimental performance indicates that the proposed model SR restoration approach achieve superior SR efficiency over existing comparative methods

SAFNet: A deep spatial attention network with classifier fusion for breast cancer detection

Breast cancer is a top dangerous killer for women. An accurate early diagnosis of breast cancer is the primary step for treatment. A novel breast cancer detection model called SAFNet is proposed based on ultrasound images and deep learning. We employ a pre-trained ResNet-18 embedded with the spatial attention mechanism as the backbone model. Three randomized network models are trained for prediction in the SAFNet, which are fused by majority voting to produce more accurate results. A public ultrasound image dataset is utilized to evaluate the generalization ability of our SAFNet using 5-fold cross-validation. The simulation experiments reveal that the SAFNet can produce higher classification results compared with four existing breast cancer classification methods. Therefore, our SAFNet is an accurate tool to detect breast cancer that can be applied in clinical diagnosis.

CNNG: A Convolutional Neural Networks With Gated Recurrent Units for Autism Spectrum Disorder Classification

As a neurodevelopmental disorder, autism spectrum disorder (ASD) severely affects the living conditions of patients and their families. Early diagnosis of ASD can enable the disease to be effectively intervened in the early stage of development. In this paper, we present an ASD classification network defined as CNNG by combining of convolutional neural network (CNN) and gate recurrent unit (GRU). First, CNNG extracts the 3D spatial features of functional magnetic resonance imaging (fMRI) data by using the convolutional layer of the 3D CNN. Second, CNNG extracts the temporal features by using the GRU and finally classifies them by using the Sigmoid function. The performance of CNNG was validated on the international public data—autism brain imaging data exchange (ABIDE) dataset. According to the experiments, CNNG can be highly effective in extracting the spatio-temporal features of fMRI and achieving a classification accuracy of 72.46%.

TSRNet: Diagnosis of COVID-19 based on self-supervised learning and hybrid ensemble model

BACKGROUND

As of Feb 27, 2022, coronavirus (COVID-19) has caused 434,888,591 infections and 5,958,849 deaths worldwide, dealing a severe blow to the economies and cultures of most countries around the world. As the virus has mutated, its infectious capacity has further increased. Effective diagnosis of suspected cases is an important tool to stop the spread of the pandemic. Therefore, we intended to develop a computer-aided diagnosis system for the diagnosis of suspected cases.

METHODS

To address the shortcomings of commonly used pre-training methods and exploit the information in unlabeled images, we proposed a new pre-training method based on transfer learning with self-supervised learning (TS). After that, a new convolutional neural network based on attention mechanism and deep residual network (RANet) was proposed to extract features. Based on this, a hybrid ensemble model (TSRNet) was proposed for classifying lung CT images of suspected patients as COVID-19 and normal.

RESULTS

Compared with the existing five models in terms of accuracy (DarkCOVIDNet: 98.08%; Deep-COVID: 97.58%; NAGNN: 97.86%; COVID-ResNet: 97.78%; Patch-based CNN: 88.90%), TSRNet has the highest accuracy of 99.80%. In addition, the recall, f1-score, and AUC of the model reached 99.59%, 99.78%, and 1, respectively.

CONCLUSION

TSRNet can effectively diagnose suspected COVID-19 cases with the help of the information in unlabeled and labeled images, thus helping physicians to adopt early treatment plans for confirmed cases.

ROENet: A ResNet-Based Output Ensemble for Malaria Parasite Classification

Background

(1)People may be infected with an insect-borne disease (malaria) through the blood input of malaria-infected people or the bite of Anopheles mosquitoes. Doctors need a lot of time and energy to diagnose malaria, and sometimes the results are not ideal. Many researchers use CNN to classify malaria images. However, we believe that the classification performance of malaria parasites can be improved.

Methods

(2)In this paper, we propose a novel method (ROENet) to automatically classify malaria parasite on the blood smear. The backbone of ROENet is the pretrained ResNet-18. We use randomized neural networks (RNNs) as the classifier in our proposed model. Three RNNs are used in ROENet, which are random vector functional link (RVFL), Schmidt neural network (SNN), and extreme learning machine (ELM). To improve the performance of ROENet, the results of ROENet are the ensemble outputs from three RNNs.

Results

(3)We evaluate the proposed ROENet by five-fold cross-validation. The specificity, F1 score, sensitivity, and accuracy are 96.68 ± 3.81%, 95.69 ± 2.65%, 94.79 ± 3.71%, and 95.73 ± 2.63%, respectively.

Conclusions

(4)The proposed ROENet is compared with other state-of-the-art methods and provides the best results of these methods.

VISPNN: VGG-inspired Stochastic Pooling Neural Network

Aim

Alcoholism is a disease that a patient becomes dependent or addicted to alcohol. This paper aims to design a novel artificial intelligence model that can recognize alcoholism more accurately.

Methods

We propose the VGG-Inspired stochastic pooling neural network (VISPNN) model based on three components: (i) a VGG-inspired mainstay network, (ii) the stochastic pooling technique, which aims to outperform traditional max pooling and average pooling, and (iii) an improved 20-way data augmentation (Gaussian noise, salt-and-pepper noise, speckle noise, Poisson noise, horizontal shear, vertical shear, rotation, Gamma correction, random translation, and scaling on both raw image and its horizontally mirrored image). In addition, two networks (Net-I and Net-II) are proposed in ablation studies. Net-I is based on VISPNN by replacing stochastic pooling with ordinary max pooling. Net-II removes the 20-way data augmentation.

Results

The results by ten runs of 10-fold cross-validation show that our VISPNN model gains a sensitivity of 97.98±1.32, a specificity of 97.80±1.35, a precision of 97.78±1.35, an accuracy of 97.89±1.11, an F1 score of 97.87±1.12, an MCC of 95.79±2.22, an FMI of 97.88±1.12, and an AUC of 0.9849, respectively.

Conclusion

The performance of our VISPNN model is better than two internal networks (Net-I and Net-II) and ten state-of-the-art alcoholism recognition methods.

DSNN: A DenseNet-Based SNN for Explainable Brain Disease Classification

Aims: Brain diseases refer to intracranial tissue and organ inflammation, vascular diseases, tumors, degeneration, malformations, genetic diseases, immune diseases, nutritional and metabolic diseases, poisoning, trauma, parasitic diseases, etc. Taking Alzheimer’s disease (AD) as an example, the number of patients dramatically increases in developed countries. By 2025, the number of elderly patients with AD aged 65 and over will reach 7.1 million, an increase of nearly 29% over the 5.5 million patients of the same age in 2018. Unless medical breakthroughs are made, AD patients may increase from 5.5 million to 13.8 million by 2050, almost three times the original. Researchers have focused on developing complex machine learning (ML) algorithms, i.e., convolutional neural networks (CNNs), containing millions of parameters. However, CNN models need many training samples. A small number of training samples in CNN models may lead to overfitting problems. With the continuous research of CNN, other networks have been proposed, such as randomized neural networks (RNNs). Schmidt neural network (SNN), random vector functional link (RVFL), and extreme learning machine (ELM) are three types of RNNs.

Methods: We propose three novel models to classify brain diseases to cope with these problems. The proposed models are DenseNet-based SNN (DSNN), DenseNet-based RVFL (DRVFL), and DenseNet-based ELM (DELM). The backbone of the three proposed models is the pre-trained “customize” DenseNet. The modified DenseNet is fine-tuned on the empirical dataset. Finally, the last five layers of the fine-tuned DenseNet are substituted by SNN, ELM, and RVFL, respectively.

Results: Overall, the DSNN gets the best performance among the three proposed models in classification performance. We evaluate the proposed DSNN by five-fold cross-validation. The accuracy, sensitivity, specificity, precision, and F1-score of the proposed DSNN on the test set are 98.46% ± 2.05%, 100.00% ± 0.00%, 85.00% ± 20.00%, 98.36% ± 2.17%, and 99.16% ± 1.11%, respectively. The proposed DSNN is compared with restricted DenseNet, spiking neural network, and other state-of-the-art methods. Finally, our model obtains the best results among all models.

Conclusions: DSNN is an effective model for classifying brain diseases.

[Research progress on the regulatory mechanism of non-coding RNA in arsenic toxicity]

Arsenic is a non-metallic element, and the International Agency for Research on Cancer has identified arsenic and its compounds as carcinogens. Arsenic and its compounds can be absorbed through the respiratory tract, skin and digestive tract, distributed in the liver, kidney, lung and skin, and cause damage. Non-coding RNAs are closely related to arsenic-induced nervous system disorders, cell necrosis, reproductive toxicity, and carcinogenesis. In recent years, the network regulation of microRNAs (miRNAs) , long non-coding RNAs (lncRNAs) , and circular RNAs (circRNAs) among non-coding RNAs in various diseases induced by arsenic has become a new research field. This paper summarizes the existing scientific research results, and expounds the mechanism of miRNAs, lncRNAs and circRNAs in arsenic toxicity, and provides basic data and theoretical basis for the prevention and treatment of arsenic poisoning.

A survey on gait recognition in IoT applications

In IoT applications, identity recognition is a basic and critical requirement. In recent years, IoT technology has developed rapidly, and IoT devices such as wearable devices, environmental sensors, and WiFi devices have been popularized and developed. The unobtrusive, low-cost, continuous advanced identity recognition methods are needed in IoT applications. Gait recognition not only has high performance but also is not easy to be forged or hidden. It has excellent potential in IoT intelligent identity recognition. This review discusses the implementation of gait analysis, representative datasets, and algorithms. Finally, we also discussed the challenges of gait analysis in IoT applications.

DSSAE: Deep Stacked Sparse Autoencoder Analytical Model for COVID-19 Diagnosis by Fractional Fourier Entropy

( Aim ) COVID-19 has caused more than 2.28 million deaths till 4/Feb/2021 while it is still spreading across the world. This study proposed a novel artificial intelligence model to diagnose COVID-19 based on chest CT images. ( Methods ) First, the two-dimensional fractional Fourier entropy was used to extract features. Second, a custom deep stacked sparse autoencoder (DSSAE) model was created to serve as the classifier. Third, an improved multiple-way data augmentation was proposed to resist overfitting. ( Results ) Our DSSAE model obtains a micro-averaged F1 score of 92.32% in handling a four-class problem (COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy control). ( Conclusion ) Our method outperforms 10 state-of-the-art approaches.

[Safety and efficacy of left atrial appendage closure combined with patent foramen ovale closure for atrial fibrillation patients with patent foramen ovale]

Objective: To analyze the safety and efficacy of combined left atrial appendage (LAA) and patent foramen ovale (PFO) closure in adult atrial fibrillation (AF) patients complicating with PFO. Methods: This study is a retrospective and cross-sectional study. Seven patients with AF complicated with PFO diagnosed by transesophageal echocardiography (TEE) in Zhoupu Hospital Affiliated to Shanghai University of Medicine & Health Sciences from June 2017 to October 2020 were selected. Basic data such as age, gender and medical history were collected. The atrial septal defect or PFO occluder and LAA occluder were selected according to the size of PFO, the ostia width and depth of LAA. Four patients underwent left atrial appendage closure(LAAC) and PFO closure at the same time. PFO closure was performed during a one-stop procedure of cryoablation combined with LAAC in 2 patients. One patient underwent PFO closure at 10 weeks after one-stop procedure because of recurrent transient ischemic attack (TIA). All patients continued to take oral anticoagulants. TEE was repeated 8-12 weeks after intervention. In case of device related thrombus(DRT), TEE shall be rechecked 6 months after adjusting anticoagulant and antiplatelet drug treatment. Patients were follow-up at 1, 3, 6, 12, 24 months by telephone call, and the occurrence of cardio-cerebrovascular events was recorded. Results: Among the 7 patients with AF, 2 were male, aged (68.0±9.4) years, and 3 had a history of recurrent cerebral infarction and TIA. Average PFO diameter was (3.5±0.8)mm. Three patients were implanted with Watchman LAA occluder (30, 30, 33 mm) and atrial septal defect occluder (8, 9, 16 mm). 2 patients were implanted with LAmbre LAA occluder (34/38, 18/32 mm) and PFO occluder (PF1825, PF2525). 2 patients were implanted with LACbes LAA occluder (24, 28 mm) and PFO occluder (PF2525, PF1825) respectively. The patients were followed up for 12 (11, 24) months after operation. TEE reexamination showed that the position of LAA occluder and atrial septal defect occluder or PFO occluder was normal in all patients. DRT was detected in 1 patient, and anticoagulant therapy was adjusted in this patient. 6 months later, TEE showed that DRT disappeared. No cardiovascular and cerebrovascular events occurred in all patients with AF during follow-up. Conclusions: In AF patients complicated with PFO, LAAC combined with PFO closure may have good safety and effectiveness.

Sire pedigree error estimation and sire verification of the Taiwan dairy cattle population by using SNP markers

Information regarding the correct pedigree of and relationship between animals is useful for managing dairy breeding, reducing inbreeding, estimating breeding value, and establishing correct breeding programs. Additionally, the successful implementation of progeny testing is crucial for improving the genetics of dairy cattle, which depends on the availability of correct pedigree information. Incorrect pedigree information leads to bias in bull evaluation. In this study, Neogen GeneSeek Genomic Profiler (GGP) 50K SNP chips were used to identify and verify the sire of Taiwanese Holstein dairy cattle and analyze the reasons that lead to incorrect sire records. Samples were collected from 2,059 cows of 36 dairy farms, and the pedigree information was provided by breeders. The results of sire verification can be divided into three categories: submitted unconfirmed sire, submitted confirmed sire, and incorrectly submitted verified sire. Data on the sires of 1,323 (64.25%) and 572 (27.78%) dairy cows were verified and discovered, respectively. Sires of 1,895 (92.03%) dairy cattle were identified, which showed that the paternal pedigree of dairy cattle could be discovered and verified through genetic testing. An error-like analysis revealed that the data of 37 sires were incorrectly recorded because the bull's NAAB code number was incorrectly entered into the insemination records: for 19 sires, the wrong bull was recorded because the frozen semen of a bull placed in the wrong storage tank was used, 6 had no sire records, and for 12 sires, the NAAB code of the correct bull was recorded but with a wrong stud code, marketing code, or unique number for the stud or breed. To reduce recorded sire error rates by at least 27.78%, automated identification of the mated bull must be adopted to reduce human error and improve dairy breeding management on dairy farms.

TBNet: a context-aware graph network for tuberculosis diagnosis

Tuberculosis (TB) is an infectious bacterial disease. It can affect the human lungs, brain, bones, and kidneys. Pulmonary tuberculosis is the most common. This airborne bacterium can be transmitted with the droplets by coughing and sneezing. So far, the most convenient and effective method for diagnosing TB is through medical imaging. Computed tomography (CT) is the first choice for lung imaging in clinics because the conditions of the lungs can be interpreted from CT images. However, manual screening poses an enormous burden for radiologists, resulting in high inter-observer variances. Hence, developing computer-aided diagnosis systems to implement automatic TB diagnosis is an emergent and significant task for researchers and practitioners. This paper proposed a novel context-aware graph neural network called TBNet to detect TB from chest CT images METHODS: Traditional convolutional neural networks can extract high-level image features to achieve good classification performance on the ImageNet dataset. However, we observed that the spatial relationships between the feature vectors are beneficial for the classification because the feature vector may share some common characteristics with its neighboring feature vectors. To utilize this context information for the classification of chest CT images, we proposed to use a feature graph to generate context-aware features. Finally, a context-aware random vector functional-link net served as the classifier of the TBNet to identify these context-aware features as TB or normal RESULTS: The proposed TBNet produced state-of-the-art classification performance for detecting TB from healthy samples in the experiments CONCLUSIONS: Our TBNet can be an accurate and effective verification tool for manual screening in clinical diagnosis.

Breast microscopic cancer segmentation and classification using unique 4-qubit-quantum model

The visual inspection of histopathological samples is the benchmark for detecting breast cancer, but a strenuous and complicated process takes a long time of the pathologist practice. Deep learning models have shown excellent outcomes in clinical diagnosis and image processing and advances in various fields, including drug development, frequency simulation, and optimization techniques. However, the resemblance of histopathologic images of breast cancer and the inclusion of stable and infected tissues in different areas make detecting and classifying tumors on entire slide images more difficult. In breast cancer, a correct diagnosis is needed for complete care in a limited amount of time. An effective detection can relieve the pathologist's workload and mitigate diagnostic subjectivity. Therefore, this research work investigates improved the pre-trained xception and deeplabv3+ design semantic model. The model has been trained on input images with ground masks on the tuned parameters that significantly improve the segmentation of ultrasound breast images into respective classes, that is, benign/malignant. The segmentation model delivered an accuracy of greater than 99% to prove the model's effectiveness. The segmented images and histopathological breast images are transferred to the 4-qubit-quantum circuit with six-layered architecture to detect breast malignancy. The proposed framework achieved remarkable performance as contrasted to currently published methodologies. HIGHLIGHTS: This research proposed hybrid semantic model using pre-trained xception and deeplabv3 for breast microscopic cancer classification in to benign and malignant classes at accuracy of 95% accuracy, 99% accuracy for detection of breast malignancy.

PeMNet for Pectoral Muscle Segmentation

Simple Summary

Deep learning has become a popular technique in modern computer-aided (CAD) systems. In breast cancer CAD systems, breast pectoral segmentation is an important procedure to remove unwanted pectoral muscle in the images. In recent decades, there are numerous studies aiming at developing efficient and accurate methods for pectoral muscle segmentation. However, some methods heavily rely on manually crafted features that can easily lead to segmentation failure. Moreover, deep learning-based methods are still suffering from poor performance at high computational costs. Therefore, we propose a novel deep learning segmentation framework to provide fast and accurate pectoral muscle segmentation result. In the proposed framework, the novel network architecture enables more useful information to be used and therefore improve the segmentation results. The experimental results using two public datasets validated the effectiveness of the proposed network.

Abstract

As an important imaging modality, mammography is considered to be the global gold standard for early detection of breast cancer. Computer-Aided (CAD) systems have played a crucial role in facilitating quicker diagnostic procedures, which otherwise could take weeks if only radiologists were involved. In some of these CAD systems, breast pectoral segmentation is required for breast region partition from breast pectoral muscle for specific analysis tasks. Therefore, accurate and efficient breast pectoral muscle segmentation frameworks are in high demand. Here, we proposed a novel deep learning framework, which we code-named PeMNet, for breast pectoral muscle segmentation in mammography images. In the proposed PeMNet, we integrated a novel attention module called the Global Channel Attention Module (GCAM), which can effectively improve the segmentation performance of Deeplabv3+ using minimal parameter overheads. In GCAM, channel attention maps (CAMs) are first extracted by concatenating feature maps after paralleled global average pooling and global maximum pooling operation. CAMs are then refined and scaled up by multi-layer perceptron (MLP) for elementwise multiplication with CAMs in next feature level. By iteratively repeating this procedure, the global CAMs (GCAMs) are then formed and multiplied elementwise with final feature maps to lead to final segmentation. By doing so, CAMs in early stages of a deep convolution network can be effectively passed on to later stages of the network and therefore leads to better information usage. The experiments on a merged dataset derived from two datasets, INbreast and OPTIMAM, showed that PeMNet greatly outperformed state-of-the-art methods by achieving an IoU of 97.46%, global pixel accuracy of 99.48%, Dice similarity coefficient of 96.30%, and Jaccard of 93.33%, respectively.