Hengyang Liu, Chuncheng Huang^*

CMC-Computers, Materials & Continua, Vol.76, No.2, pp. 1745-1761, 2023, DOI:10.32604/cmc.2023.040710

Abstract In the field of medical images, pixel-level labels are time-consuming and expensive to acquire, while image-level labels are relatively easier to obtain. Therefore, it makes sense to learn more information (knowledge) from a small number of hard-to-get pixel-level annotated images to apply to different tasks to maximize their usefulness and save time and training costs. In this paper, using Pixel-Level Labeled Images for Multi-Task Learning (PLDMLT), we focus on grading the severity of fundus images for Diabetic Retinopathy (DR). This is because, for the segmentation task, there is a finely labeled mask, while the severity grading task is without classification… More >

Lihong Guo^*, Jie Yang, Haitao Wu

CMC-Computers, Materials & Continua, Vol.76, No.2, pp. 1929-1946, 2023, DOI:10.32604/cmc.2023.039170

Abstract Attribute-based encryption (ABE) is a technique used to encrypt data, it has the flexibility of access control, high security, and resistance to collusion attacks, and especially it is used in cloud security protection. However, a large number of bilinear mappings are used in ABE, and the calculation of bilinear pairing is time-consuming. So there is the problem of low efficiency. On the other hand, the decryption key is not uniquely associated with personal identification information, if the decryption key is maliciously sold, ABE is unable to achieve accountability for the user. In practical applications, shared message requires hierarchical sharing in… More >

HANY M. ABD EL-LATEEF^1,2,*, SAFA H. QAHL³, EMAN FAYAD⁴, SARAH A. ALTALHI⁴, IBRAHIM JAFRI⁴, EL SHAIMAA SHABANA⁵, MARWA K. DARWISH^6,7, REHAB MAHER⁸, SAAD SHAABAN^1,9, SHADY G. EL-SAWAH^10,*

BIOCELL, Vol.47, No.8, pp. 1885-1895, 2023, DOI:10.32604/biocell.2023.030680

Abstract Background: The increasing occurrence of diabetes mellitus (DM) noted worldwide has considerably elicited concern in the recent past. DM is associated with elevated vascular complications, morbidity, mortality, and poor quality of life. In this context, mesenchymal stem cells (MSCs) have shown significant therapeutic potentialities in managing and curing type 1 DM owing to their self-renewable, immunosuppressive, and differentiation capacities. We investigated the potential action of N, N′-diphenyl-1,4-phenylenediamine (DPPD), a well-known synthetic antioxidant to enhance the therapeutic ability of the adipose-derived stem cells (AD-MSCs) in alleviating kidney and liver complications in diabetic rats. Methods: Over the four weeks of experiments, albino… More > Graphic Abstract

FENGMEI QIAN^1,2, PEIYAO REN², LI ZHAO², DANNA ZHENG², WENFANG HE³, JUAN JIN^3,*

BIOCELL, Vol.47, No.8, pp. 1853-1867, 2023, DOI:10.32604/biocell.2023.029353

Abstract Background: Diabetic nephropathy (DN) is a serious complication of diabetes with rising prevalence worldwide. We aimed to explore the anti-DN mechanisms of the compound celastrol derived from the medicinal plant Tripterygium wilfordii. Methods: Celastrol-related targets were obtained from Herbal Ingredients’ Targets (HIT) and GeneCards databases. DN-related targets were retrieved from GeneCards, DisGeNET, and Therapeutic Targets Database (TTD). A Protein-protein interaction (PPI) network was established using the Search Tool for the Retrieval of Interacting Genes (STRING) database. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed using ClusterProfiler. The cytoHubba plugin was used to select… More > Graphic Abstract

B. Ramesh, Kuruva Lakshmanna^*

CMES-Computer Modeling in Engineering & Sciences, Vol.137, No.3, pp. 2513-2528, 2023, DOI:10.32604/cmes.2023.028944

Abstract Major chronic diseases such as Cardiovascular Disease (CVD), diabetes, and cancer impose a significant burden on people and healthcare systems around the globe. Recently, Deep Learning (DL) has shown great potential for the development of intelligent mobile Health (mHealth) interventions for chronic diseases that could revolutionize the delivery of health care anytime, anywhere. The aim of this study is to present a systematic review of studies that have used DL based on mHealth data for the diagnosis, prognosis, management, and treatment of major chronic diseases and advance our understanding of the progress made in this rapidly developing field. Type 2… More > Graphic Abstract

Qiankun Zuo^1,4, Junhua Hu², Yudong Zhang^3,*, Junren Pan⁴, Changhong Jing⁴, Xuhang Chen⁵, Xiaobo Meng⁶, Jin Hong^7,8,*

CMES-Computer Modeling in Engineering & Sciences, Vol.137, No.3, pp. 2129-2147, 2023, DOI:10.32604/cmes.2023.028732

Abstract The topological connectivity information derived from the brain functional network can bring new insights for diagnosing and analyzing dementia disorders. The brain functional network is suitable to bridge the correlation between abnormal connectivities and dementia disorders. However, it is challenging to access considerable amounts of brain functional network data, which hinders the widespread application of data-driven models in dementia diagnosis. In this study, a novel distribution-regularized adversarial graph auto-Encoder (DAGAE) with transformer is proposed to generate new fake brain functional networks to augment the brain functional network dataset, improving the dementia diagnosis accuracy of data-driven models. Specifically, the label distribution… More > Graphic Abstract

JING JIN^1,2,#, XIE LI^1,#, TING QIU^1,#, LEI SONG¹, YUANYUE CUI¹, GUANGYA ZHANG^3,4, SHU LI², WENCHENG ZHAO^5,*

BIOCELL, Vol.47, No.7, pp. 1645-1650, 2023, DOI:10.32604/biocell.2023.029493

Abstract Background: This work aimed to reveal the expression profiles of tRNA-derived small RNAs (tsRNAs) in diabetes. Methods: Thirty-five diabetes patients and thirty-three controls were enrolled. The serum samples of 4 diabetes patients and 4 controls were subjected to tRF and tiRNA polymerase chain reaction (PCR) Array analysis. Then quantitative PCR (qPCR) validation was performed on all the samples. Bioinformatics analyses were conducted to explore their functions. Results: We found 115 tsRNAs that significantly differed between the two groups. 3′tiR-080-ProTGG(mt) was selected for further qPCR validation in all participants, and it was significantly decreased in diabetes patients compared with controls. Bioinformatics… More >

JAMES L. ROSENBERG¹, WILLIAM WOOLLEY¹, IHSAN ELNUNU¹, JULIA KAMML², DAVID S. KAMMER², CLAIRE ACEVEDO^1,3,*

BIOCELL, Vol.47, No.7, pp. 1651-1659, 2023, DOI:10.32604/biocell.2023.028014

Abstract Age and diabetes have long been known to induce an oxidative reaction between glucose and collagen, leading to the accumulation of advanced glycation end-products (AGEs) cross-links in collagenous tissues. More recently, AGEs content has been related to loss of bone quality, independent of bone mass, and increased fracture risk with aging and diabetes. Loss of bone quality is mostly attributed to changes in material properties, structural organization, or cellular remodeling. Though all these factors play a role in bone fragility disease, some common recurring patterns can be found between diabetic and age-related bone fragility. The main pattern we will discuss… More >

UMAPATHY PRAKASH¹, SUBRAMANIAM RAJESH BHARATHIDEVI^1,*, RAMYA R. NADIG², RAJIV RAMAN², GIRISH SHIV RAO², MUNA BHENDE²

BIOCELL, Vol.47, No.7, pp. 1473-1482, 2023, DOI:10.32604/biocell.2023.027804

Abstract Zinc alpha 2 glycoprotein (ZAG) is a 41 KDa secretory soluble glycoprotein found in different body fluids like the serum, saliva, sweat, breast milk, and urine. It is also found in tissues like the testis, epididymis, kidney, spleen, liver, lungs, heart, and brain. ZAG is an adipokine with multiple roles, including lipid mobilization, modulating glucose metabolisms, improving insulin sensitivity, inhibiting tumor proliferation through RNAse activity, and suppressing inflammation. Low levels of zinc and ZAG are linked to metabolic syndrome and are also reported as potential biomarkers for diabetic nephropathy. Interestingly zinc has been found to regulate the binding of ZAG… More >

Zhicong Qiu^1,2, Xianmin Wang^1,*, Huawei Ma¹, Songcao Hou¹, Jing Li^1,2,*, Zuoyong Li²

Intelligent Automation & Soft Computing, Vol.37, No.2, pp. 1243-1256, 2023, DOI:10.32604/iasc.2023.038241

Abstract Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks, which lies in the fact that examples closer to the decision boundaries are much more vulnerable to being attacked and should be given larger weights. The probability margin (PM) method is a promising approach to continuously and path-independently measuring such closeness between the example and decision boundary. However, the performance of PM is limited due to the fact that PM fails to effectively distinguish the examples having only one misclassified category and the ones with multiple misclassified categories, where the latter is closer to… More >