Multi-level feature extraction and reconstruction for 3D MRI image super-resolution.

Magnetic resonance imaging (MRI) is an essential radiology technique in clinical diagnosis, but its spatial resolution may not suffice to meet the growing need for precise diagnosis due to hardware limitations and thicker slice thickness. Therefore, it is crucial to explore suitable methods to increase the resolution of MRI images. Recently, deep learning has yielded many impressive results in MRI image super-resolution (SR) reconstruction. However, current SR networks mainly use convolutions to extract relatively single image features, which may not be optimal for further enhancing the quality of image reconstruction. In this work, we propose a multi-level feature extraction and reconstruction (MFER) method to restore the degraded high-resolution details of MRI images. Specifically, to comprehensively extract different types of features, we design the triple-mixed convolution by leveraging the strengths and uniqueness of different filter operations. For the features of each level, we then apply deconvolutions to upsample them separately at the tail of the network, followed by the feature calibration of spatial and channel attention. Besides, we also use a soft cross-scale residual operation to improve the effectiveness of parameter optimization. Experiments on lesion-free and glioma datasets indicate that our method obtains superior quantitative performance and visual effects when compared with state-of-the-art MRI image SR methods.

MS-DCANet: A Novel Segmentation Network For Multi-Modality COVID-19 Medical Images.

Aim: The Coronavirus Disease 2019 (COVID-19) pandemic has increased the public health burden and brought profound disaster to humans. For the particularity of the COVID-19 medical images with blurred boundaries, low contrast and different infection sites, some researchers have improved the accuracy by adding more complexity. Also, they overlook the complexity of lesions, which hinder their ability to capture the relationship between segmentation sites and the background, as well as the edge contours and global context. However, increasing the computational complexity, parameters and inference speed is unfavorable for model transfer from laboratory to clinic. A perfect segmentation network needs to balance the above three factors completely. To solve the above issues, this paper propose a symmetric automatic segmentation framework named MS-DCANet. We introduce Tokenized MLP block, a novel attention scheme that uses a shift-window mechanism to conditionally fuse local and global features to get more continuous boundaries and spatial positioning capabilities. It has greater understanding of irregular lesion contours. MS-DCANet also uses several Dual Channel blocks and a Res-ASPP block to improve the ability to recognize small targets. On multi-modality COVID-19 tasks, MS-DCANet achieved state-of-the-art performance compared with other baselines. It can well trade off the accuracy and complexity. To prove the strong generalization ability of our proposed model, we apply it to other tasks (ISIC 2018 and BAA) and achieve satisfactory results. Patients: The X-ray dataset from Qatar University which contains 3379 cases for light, normal and heavy COVID-19 lung infection. The CT dataset contains the scans of 10 patient cases with COVID-19, a total of 1562 CT axial slices. The BAA dataset is obtained from the hospital and includes 387 original images. The ISIC 2018 dataset is from the International Skin Imaging Collaborative (ISIC) containing 2594 original images. Results: The proposed MS-DCANet achieved evaluation metrics (MIOU) of 73.86, 97.26, 89.54, and 79.54 on the four datasets, respectively, far exceeding other current state-of-the art baselines. Conclusion: The proposed MS-DCANet can help clinicians to automate the diagnosis of COVID-19 patients with different symptoms.

Application of Zero-Watermarking Scheme Based on Swin Transformer for Securing the Metaverse Healthcare Data.

The existing medical image privacy solutions cannot completely solve the security problems created by applying the metaverse healthcare system. A robust zero-watermarking scheme based on the Swin Transformer is proposed in this paper to improve the security of medical images in the metaverse healthcare system. This scheme uses a pretrained Swin Transformer to extract deep features from the original medical images with a good generalization performance and multiscale, and binary feature vectors are generated by using the mean hashing algorithm. Then, the logistic chaotic encryption algorithm boosts the security of the watermarking image by encrypting it. Finally, an encrypted watermarking image is XORed with the binary feature vector to create a zero-watermarking, and the validity of the proposed scheme is verified through experimentation. According to the results of the experiments, the proposed scheme has excellent robustness to common attacks and geometric attacks, and implements privacy protections for medical image security transmissions in the metaverse. The research results provide a reference for the data security and privacy protection of the metaverse healthcare system.

A meta-analysis of the relationship between circulating microRNA-155 and coronary artery disease.

OBJECTIVE: Coronary artery disease (CAD) is a leading cause of death worldwide. Many studies in China and abroad have reported an association between the expression level of microRNA-155 and CAD; however, the results remain controversial. We aimed to comprehensively investigate this association based on a meta-analysis. METHODS: We first systematically searched eight Chinese and English databases, including China National Knowledge Infrastructure, Wanfang, China Science and Technology Journal Database, PubMed, Web of Science, Embase, Google Scholar, and Cochrane Library, to identify studies concerning the relationship between microRNA-155 levels and CAD published before February 7, 2021. The quality of the literature was assessed by the Newcastle-Ottawa Scale (NOS). Meta-analysis was performed using a random-effects model to calculate the standard mean difference with a 95% confidence interval (CI). RESULTS: Sixteen articles with a total of 2069 patients with CAD and 1338 controls were included. All the articles were of high quality according to the NOS. The meta-analysis showed that the mean level of microRNA-155 was significantly lower in patients with CAD than in controls. Based on subgroup analyses, the level of microRNA-155 in the plasma of CAD patients and in acute myocardial infarction (AMI) patients was significantly lower than that in controls, whereas this level in CAD patients with mild stenosis was significantly higher than that in controls. CONCLUSION: Our study indicates that the expression level of circulating microRNA-155 in patients with CAD is lower than that in a non-CAD group, suggesting a new possible reference index for the diagnosis and monitoring of patients with CAD.

Research and application of intelligent image processing technology in the auxiliary diagnosis of aortic coarctation.

Objective: To explore the application of the proposed intelligent image processing method in the diagnosis of aortic coarctation computed tomography angiography (CTA) and to clarify its value in the diagnosis of aortic coarctation based on the diagnosis results. Methods: Fifty-three children with coarctation of the aorta (CoA) and forty children without CoA were selected to constitute the study population. CTA was performed on all subjects. The minimum diameters of the ascending aorta, proximal arch, distal arch, isthmus, and descending aorta were measured using manual and intelligent methods, respectively. The Wilcoxon signed-rank test was used to analyze the differences between the two measurements. The surgical diagnosis results were used as the gold standard, and the diagnostic results obtained by the two measurement methods were compared with the gold standard to quantitatively evaluate the diagnostic results of CoA by the two measurement methods. The Kappa test was used to analyze the consistency of intelligence diagnosis results with the gold standard. Results: Whether people have CoA or not, there was a significant difference (p < 0.05) in the measurements of the minimum diameter at most sites using the two methods. However, close final diagnoses were made using the intelligent method and the manual. Meanwhile, the intelligent measurement method obtained higher accuracy, specificity, and AUC (area under the curve) compared to manual measurement in diagnosing CoA based on Karl's classification (accuracy = 0.95, specificity = 0.9, and AUC = 0.94). Furthermore, the diagnostic results of the intelligence method applied to the three criteria agreed well with the gold standard (all kappa ≥ 0.8). The results of the comparative analysis showed that Karl's classification had the best diagnostic effect on CoA. Conclusion: The proposed intelligent method based on image processing can be successfully applied to assist in the diagnosis of CoA.

Application of Robust Zero-Watermarking Scheme Based on Federated Learning for Securing the Healthcare Data.

The privacy protection and data security problems existing in the healthcare framework based on the Internet of Medical Things (IoMT) have always attracted much attention and need to be solved urgently. In the teledermatology healthcare framework, the smartphone can acquire dermatology medical images for remote diagnosis. The dermatology medical image is vulnerable to attacks during transmission, resulting in malicious tampering or privacy data disclosure. Therefore, there is an urgent need for a watermarking scheme that doesn't tamper with the dermatology medical image and doesn't disclose the dermatology healthcare data. Federated learning is a distributed machine learning framework with privacy protection and secure encryption technology. Therefore, this paper presents a robust zero-watermarking scheme based on federated learning to solve the privacy and security issues of the teledermatology healthcare framework. This scheme trains the sparse autoencoder network by federated learning. The trained sparse autoencoder network is applied to extract image features from the dermatology medical image. Image features are undergone to two-dimensional Discrete Cosine Transform (2D-DCT) in order to select low-frequency transform coefficients for creating zero-watermarking. Experimental results show that the proposed scheme has more robustness to the conventional attack and geometric attack and achieves superior performance when compared with other zero-watermarking schemes. The proposed scheme is suitable for the specific requirements of medical images, which neither changes the important information contained in medical images nor divulges privacy data.

Coupled Gold Nanoparticles with Aptamers Colorimetry for Detection of Amoxicillin in Human Breast Milk Based on Image Preprocessing and BP-ANN.

Antibiotic residues in breast milk can have an impact on the intestinal flora and health of babies. Amoxicillin, as one of the most used antibiotics, affects the abundance of some intestinal bacteria. In this study, we developed a convenient and rapid process that used a combination of colorimetric methods and artificial intelligence image preprocessing, and back propagation-artificial neural network (BP-ANN) analysis to detect amoxicillin in breast milk. The colorimetric method derived from the reaction of gold nanoparticles (AuNPs) was coupled to aptamers (ssDNA) with different concentrations of amoxicillin to produce different color results. The color image was captured by a portable image acquisition device, and image preprocessing was implemented in three steps: segmentation, filtering, and cropping. We decided on a range of detection from 0 µM to 3.9 µM based on the physiological concentration of amoxicillin in breast milk and the detection effect. The segmentation and filtering steps were conducted by Hough circle detection and Gaussian filtering, respectively. The segmented results were analyzed by linear regression and BP-ANN, and good linear correlations between the colorimetric image value and concentration of target amoxicillin were obtained. The R2 and MSE of the training set were 0.9551 and 0.0696, respectively, and those of the test set were 0.9276 and 0.1142, respectively. In prepared breast milk sample detection, the recoveries were 111.00%, 98.00%, and 100.20%, and RSDs were 6.42%, 4.27%, and 1.11%. The result suggests that the colorimetric process combined with artificial intelligence image preprocessing and BP-ANN provides an accurate, rapid, and convenient way to achieve the detection of amoxicillin in breast milk.

Efficacy and safety of a bridging strategy that uses intravenous platelet glycoprotein receptor inhibitors for patients undergoing surgery after coronary stent implantation: a meta-analysis.

BACKGROUND: Current guidelines indicate we can consider a bridging strategy that uses intravenous, reversible glycoprotein inhibitors for patients that required surgery following recent stent implantation. However, no strong clinical evidence exists that demonstrates the efficacy and safety of this treatment. Therefore, in this study, the efficacy and safety of a bridging strategy that uses intravenous platelet glycoprotein receptor inhibitors will be evaluated. METHODS: A meta-analysis was performed on preoperative bridging studies in patients undergoing coronary stent surgery. The primary outcome was the success rate of no major adverse cardiovascular events (MACE). The secondary outcomes were the success rate of no reoperations to stop bleeding. RESULTS: A total of 10 studies that included 382 patients were used in this meta-analysis. For the primary endpoint, the success rate was 97.7% (95% CI 94.4-98.0%) for glycoprotein IIb/IIIa inhibitors, 98.8% (95% CI 96.0-100%) for tirofiban (6 studies) and 95.8% (95% CI 90.4-99.4%) for eptifibatide (4 studies). For secondary endpoints, the success rate was 98.0% (95% CI 94.8-99.9%) for glycoprotein IIb/IIIa inhibitors, 99.7% (95% CI 97.1-100%) for tirofiban (5 studies), and 95.3% (95% CI 88.5-99.4%) for eptifibatide (4 studies). CONCLUSION: The results of this study showed that the use of intravenous platelet glycoprotein IIb/IIIa inhibitors as a bridging strategy might be safe and effective for patients undergoing coronary stent implantation that require surgery soon after.

Diagnostic performance of computed tomography-based fraction flow reserve in identifying myocardial ischemia caused by coronary artery stenosis: A meta-analysis.

BACKGROUND: As a new noninvasive diagnostic technique, computed tomography (CT)-based fraction flow reserve (FFR) has been used to identify hemodynamically significant coronary artery stenosis. This meta-analysis used invasive FFR as the standard to evaluate the diagnostic performance of FFRCT. METHODS: We searched the PubMed, Cochrane library, and EMBASE for articles published between January 2009 and January 2021. The synthesized sensitivity and specificity of invasive FFR and FFRCT were analyzed at both the patient and vessel levels. We generated a summary receiver operating characteristic curve (SROC) and then calculated the area under the curve (AUC). RESULTS: We included a total of 23 studies, including 2,178 patients and 3,029 vessels or lesions. Analysis at each patient level demonstrated a synthesized sensitivity of 88%, specificity of 79%, LR+ of 4.16, LR-of 0.15, and AUC of 0.89 for FFRCT. Analysis at the level of each vessel or lesion showed a synthesized sensitivity of 85%, specificity of 81%, LR+ of 4.44, LR-of 0.19, and AUC of 0.87 for FFRCT. CONCLUSION: Our research reveals that FFRCT has high diagnostic performance in patients with coronary artery stenosis, regardless of whether it is at the patient level or the vessel level.

Zero-Watermarking Algorithm for Medical Image Based on VGG19 Deep Convolution Neural Network.

Aiming at the security issues in the storage and transmission of medical images in the medical information system, combined with the special requirements of medical images for the protection of lesion areas, this paper proposes a robust zero-watermarking algorithm for medical images' security based on VGG19. First, the pretrained VGG19 is used to extract deep feature maps of medical images, which are fused into the feature image. Second, the feature image is transformed by Fourier transform, and low-frequency coefficients of the Fourier transform are selected to construct the feature matrix of the medical image. Then, based on the low-frequency part of the feature matrix of the medical image, the mean-perceptual hashing algorithm is used to achieve a set of 64-bit binary perceptual hashing values, which can effectively resist local nonlinear geometric attacks. Finally, the algorithm adopts a watermarking image after scrambling and the 64-bit binary perceptual hashing value to obtain robust zero-watermarking. At the same time, the proposed algorithm utilizes Hermite chaotic neural network to scramble the watermarking image for secondary protection, which enhances the security of the algorithm. Compared with the existing related works, the proposed algorithm is simple to implement and can effectively resist local nonlinear geometric attacks, with good robustness, security, and invisibility.

Integrated bioinformatic analysis and experiment confirmation of the antagonistic effect and molecular mechanism of ginsenoside Rh2 in metastatic osteosarcoma.

This study aimed to compare the gene expression variation of clinical primary osteosarcoma (OS) and metastatic OS, identify expression profiles and signal pathways related to disease classification, and systematically evaluate the potential anticancer effect and molecular mechanism of ginsenoside Rh2 on OS. A raw dataset (GSE14359), which excluded GSM359137 and GSM359138, was downloaded from the Gene Expression Omnibus. Differentially expressed genes (DEGs) and principal component analysis (PCA) were obtained with limma. Pathways enrichment analysis was understood by GSEA app. Rh2-associated targets were harvested and mapped through PharmMapper and Cytoscape 3.4.0. The toxicity of Rh2 was determined using crystal staining and MTT assay on 143B and MG63 cell lines. The relative protein expression was confirmed through Western blot analysis. The mitochondrial membrane potential (△Ψm) was evaluated by JC-1 fluorescence staining. The cell mobility was measured via wound healing and transwell assays. A total of 752 genes were upregulated, while 161 genes were downregulated. GSEA and PCA displayed significant function enrichment and classification. Through PharmMapper and Cytoscape 3.4.0, Rh2 was found to target the mitogen activated protein kinase (MAPK) and PI3K signaling pathways, which are the key pathways in the metastasis of OS. Furthermore, Rh2 induced a concentration-dependent decrease in cell viability and early apoptosis associated with ΔΨm decline, while a non-lethal dose of Rh2 weakened the metastatic capability. Moreover, systematic evaluation showed that promoting the MAPK signaling pathway and inhibiting PI3K/Akt/mTOR were correlated with the anticancer effects of Rh2 on metastatic OS. In conclusion, transcriptome-derived approaches may be beneficial in diagnosing early metastases, and Rh2, a multi-targeting agent, shows promising application potential in suppressing metastatic OS in an MAPK- and PI3K/Akt/mTOR-dependent manner.

Immunological pathways of macrophage response to Brucella ovis infection.

As the molecular mechanisms of Brucella ovis pathogenicity are not completely clear, we have applied a transcriptome approach to identify the differentially expressed genes (DEGs) in RAW264.7 macrophage infected with B. ovis. The DEGs related to immune pathway were identified by Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) functional enrichment analysis. Quantitative real-time PCR (qRT-PCR) was performed to validate the transcriptome sequencing data. In total, we identified 337 up-regulated and 264 down-regulated DEGs in B. ovis-infected group versus mock group. Top 20 pathways were enriched by KEGG analysis and 20 GO by functional enrichment analysis in DEGs involved in the molecular function, cellular component, and biological process and so on, which revealed multiple immunological pathways in RAW264.7 macrophage cells in response to B. ovis infection, including inflammatory response, immune system process, immune response, cytokine activity, chemotaxis, chemokine-mediated signaling pathway, chemokine activity, and CCR chemokine receptor binding. qRT-PCR results showed Ccl2 (ENSMUST00000000193), Ccl2 (ENSMUST00000124479), Ccl3 (ENSMUST00000001008), Hmox1 (ENSMUST00000005548), Hmox1 (ENSMUST00000159631), Cxcl2 (ENSMUST00000075433), Cxcl2 (ENSMUST00000200681), Cxcl2 (ENSMUST00000200919), and Cxcl2 (ENSMUST00000202317). Our findings firstly elucidate the pathways involved in B. ovis-induced host immune response, which may lay the foundation for revealing the bacteria-host interaction and demonstrating the pathogenic mechanism of B. ovis.