Advancing single-cell RNA-seq data analysis through the fusion of multi-layer perceptron and graph neural network.

The advancement of single-cell sequencing technology has smoothed the ability to do biological studies at the cellular level. Nevertheless, single-cell RNA sequencing (scRNA-seq) data presents several obstacles due to the considerable heterogeneity, sparsity and complexity. Although many machine-learning models have been devised to tackle these difficulties, there is still a need to enhance their efficiency and accuracy. Current deep learning methods often fail to fully exploit the intrinsic interconnections within cells, resulting in unsatisfactory results. Given these obstacles, we propose a unique approach for analyzing scRNA-seq data called scMPN. This methodology integrates multi-layer perceptron and graph neural network, including attention network, to execute gene imputation and cell clustering tasks. In order to evaluate the gene imputation performance of scMPN, several metrics like cosine similarity, median L1 distance and root mean square error are used. These metrics are utilized to compare the efficacy of scMPN with other existing approaches. This research utilizes criteria such as adjusted mutual information, normalized mutual information and integrity score to assess the efficacy of cell clustering across different approaches. The superiority of scMPN over current single-cell data processing techniques in cell clustering and gene imputation investigations is shown by the experimental findings obtained from four datasets with gold-standard cell labels. This observation demonstrates the efficacy of our suggested methodology in using deep learning methodologies to enhance the interpretation of scRNA-seq data.

Single-cell RNA-seq data analysis based on directed graph neural network.

Single-cell RNA sequencing (scRNA-seq) data scale surges with high-throughput sequencing technology development. However, although single-cell data analysis is a powerful tool, various issues have been reported, such as sequencing sparsity and complex differential patterns in gene expression. Statistical or traditional machine learning methods are inefficient, and the accuracy needs to be improved. The methods based on deep learning can not directly process non-Euclidean spatial data, such as cell diagrams. In this study, we have developed graph autoencoders and graph attention network for scRNA-seq analysis based on a directed graph neural network named scDGAE. Directed graph neural networks cannot only retain the connection properties of the directed graph but also expand the receptive field of the convolution operation. Cosine similarity, median L1 distance, and root-mean-squared error are used to measure the gene imputation performance of different methods with scDGAE. Furthermore, adjusted mutual information, normalized mutual information, completeness score, and Silhouette coefficient score are used to measure the cell clustering performance of different methods with scDGAE. Experiment results show that the scDGAE model achieves promising performance in gene imputation and cell clustering prediction on four scRNA-seq data sets with gold-standard cell labels. Furthermore, it is a robust framework that can be applied to general scRNA-Seq analyses.

Improved Intrusion Detection Based on Hybrid Deep Learning Models and Federated Learning.

The security of the Industrial Internet of Things (IIoT) is of vital importance, and the Network Intrusion Detection System (NIDS) plays an indispensable role in this. Although there is an increasing number of studies on the use of deep learning technology to achieve network intrusion detection, the limited local data of the device may lead to poor model performance because deep learning requires large-scale datasets for training. Some solutions propose to centralize the local datasets of devices for deep learning training, but this may involve user privacy issues. To address these challenges, this study proposes a novel federated learning (FL)-based approach aimed at improving the accuracy of network intrusion detection while ensuring data privacy protection. This research combines convolutional neural networks with attention mechanisms to develop a new deep learning intrusion detection model specifically designed for the IIoT. Additionally, variational autoencoders are incorporated to enhance data privacy protection. Furthermore, an FL framework enables multiple IIoT clients to jointly train a shared intrusion detection model without sharing their raw data. This strategy significantly improves the model's detection capability while effectively addressing data privacy and security issues. To validate the effectiveness of the proposed method, a series of experiments were conducted on a real-world Internet of Things (IoT) network intrusion dataset. The experimental results demonstrate that our model and FL approach significantly improve key performance metrics such as detection accuracy, precision, and false-positive rate (FPR) compared to traditional local training methods and existing models.

Ethereum Phishing Scam Detection Based on Data Augmentation Method and Hybrid Graph Neural Network Model.

The rapid advancement of blockchain technology has fueled the prosperity of the cryptocurrency market. Unfortunately, it has also facilitated certain criminal activities, particularly the increasing issue of phishing scams on blockchain platforms such as Ethereum. Consequently, developing an efficient phishing detection system is critical for ensuring the security and reliability of cryptocurrency transactions. However, existing methods have shortcomings in dealing with sample imbalance and effective feature extraction. To address these issues, this study proposes an Ethereum phishing scam detection method based on DA-HGNN (Data Augmentation Method and Hybrid Graph Neural Network Model), validated by real Ethereum datasets to prove its effectiveness. Initially, basic node features consisting of 11 attributes were designed. This study applied a sliding window sampling method based on node transactions for data augmentation. Since phishing nodes often initiate numerous transactions, the augmented samples tended to balance. Subsequently, the Temporal Features Extraction Module employed Conv1D (One-Dimensional Convolutional neural network) and GRU-MHA (GRU-Multi-Head Attention) models to uncover intrinsic relationships between features from the time sequences and to mine adequate local features, culminating in the extraction of temporal features. The GAE (Graph Autoencoder) concept was then leveraged, with SAGEConv (Graph SAGE Convolution) as the encoder. In the SAGEConv reconstruction module, by reconstructing the relationships between transaction graph nodes, the structural features of the nodes were learned, obtaining reconstructed node embedding representations. Ultimately, phishing fraud nodes were further identified by integrating temporal features, basic features, and embedding representations. A real Ethereum dataset was collected for evaluation, and the DA-HGNN model achieved an AUC-ROC (Area Under the Receiver Operating Characteristic Curve) of 0.994, a Recall of 0.995, and an F1-score of 0.994, outperforming existing methods and baseline models.

Synergistic immunotherapy targeting cancer-associated anemia: prospects of a combination strategy.

Cancer-associated anemia promotes tumor progression, leads to poor quality of life in patients with cancer, and even obstructs the efficacy of immune checkpoint inhibitors therapy. However, the precise mechanism for cancer-associated anemia remains unknown and the feasible strategy to target cancer-associated anemia synergizing immunotherapy needs to be clarified. Here, we review the possible mechanisms of cancer-induced anemia regarding decreased erythropoiesis and increased erythrocyte destruction, and cancer treatment-induced anemia. Moreover, we summarize the current paradigm for cancer-associated anemia treatment. Finally, we propose some prospective paradigms to slow down cancer-associated anemia and synergistic the efficacy of immunotherapy. Video Abstract.

Structural and functional biomarkers of the insula subregions predict sex differences in aggression subscales.

Aggression is a common and complex social behavior that is associated with violence and mental diseases. Although sex differences were observed in aggression, the neural mechanism for the effect of sex on aggression behaviors remains unclear, especially in specific subscales of aggression. In this study, we investigated the effects of sex on aggression subscales, gray matter volume (GMV), and functional connectivity (FC) of each insula subregion as well as the correlation of aggression subscales with GMV and FC. This study found that sex significantly influenced (a) physical aggression, anger, and hostility; (b) the GMV of all insula subregions; and (c) the FC of the dorsal agranular insula (dIa), dorsal dysgranular insula (dId), and ventral dysgranular and granular insula (vId_vIg). Additionally, mediation analysis revealed that the GMV of bilateral dIa mediates the association between sex and physical aggression, and left dId-left medial orbital superior frontal gyrus FC mediates the relationship between sex and anger. These findings revealed the neural mechanism underlying the sex differences in aggression subscales and the important role of the insula in aggression differences between males and females. This finding could potentially explain sexual dimorphism in neuropsychiatric disorders and improve dysregulated aggressive behavior.

IGWO-IVNet3: DL-Based Automatic Diagnosis of Lung Nodules Using an Improved Gray Wolf Optimization and InceptionNet-V3.

Artificial intelligence plays an essential role in diagnosing lung cancer. Lung cancer is notoriously difficult to diagnose until it has progressed to a late stage, making it a leading cause of cancer-related mortality. Lung cancer is fatal if not treated early, making this a significant issue. Initial diagnosis of malignant nodules is often made using chest radiography (X-ray) and computed tomography (CT) scans; nevertheless, the possibility of benign nodules leads to wrong choices. In their first phases, benign and malignant nodules seem very similar. Additionally, radiologists have a hard time viewing and categorizing lung abnormalities. Lung cancer screenings performed by radiologists are often performed with the use of computer-aided diagnostic technologies. Computer scientists have presented many methods for identifying lung cancer in recent years. Low-quality images compromise the segmentation process, rendering traditional lung cancer prediction algorithms inaccurate. This article suggests a highly effective strategy for identifying and categorizing lung cancer. Noise in the pictures was reduced using a weighted filter, and the improved Gray Wolf Optimization method was performed before segmentation with watershed modification and dilation operations. We used InceptionNet-V3 to classify lung cancer into three groups, and it performed well compared to prior studies: 98.96% accuracy, 94.74% specificity, as well as 100% sensitivity.

The mechanisms of pathological extramedullary hematopoiesis in diseases.

Extramedullary hematopoiesis (EMH) is the expansion and differentiation of hematopoietic stem and progenitor cells outside of the bone marrow. In postnatal life, as a compensatory mechanism for ineffective hematopoiesis of the bone marrow, pathological EMH is triggered by hematopoietic disorders, insufficient hematopoietic compensation, and other pathological stress conditions, such as infection, advanced tumors, anemia, and metabolic stress. Pathological EMH has been reported in many organs, and the sites of pathological EMH may be related to reactivation of the embryonic hematopoietic structure in these organs. As a double-edged sword (blood and immune cell supplementation as well as clinical complications), pathological EMH has been widely studied in recent years. In particular, pathological EMH induced by late-stage tumors contributes to tumor immunosuppression. Thus, a deeper understanding of the mechanism of pathological EMH may be conducive to the development of therapies against the pathological processes that induce EMH. This article reviews the recent progress of research on the cellular and molecular mechanisms of pathological EMH in specific diseases.

A pooled analysis of primary hepatic angiosarcoma.

BACKGROUND: Angiosarcoma is an aggressive and malignant neoplasm. Primary hepatic angiosarcoma is extremely rare and accounts for only approximately 5% of all angiosarcomas. Therefore, many doctors do not know enough about this disease; this lack of knowledge motivated us to perform this study. METHODS: We carried out a systematic review of the literature published worldwide from 1990 to 2019 to study the main characteristics, demographics, treatment and prognosis of primary hepatic angiosarcoma. RESULT: A total of 219 patients were included in this study. Patients were mainly middle-aged and elderly at diagnosis, with an average age at onset of 56.7 years. The vast majority of patients (61.5%) presented with abdominal pain or distension. Of 143 patients with clear records of metastasis, 31.5% (45 patients) had distant metastasis. The median overall survival time was only 6 months, and the 1- and 2-year survival rates were 30.4 and 17.3%, respectively. Sex, age, tumor size and metastasis at diagnosis showed no correlation with survival rate. Hepatic rupture was a significant predictor of survival. Surgery is a major treatment choice, and adjuvant chemotherapy can improve the prognosis of patients. Hepatic artery embolization is mainly used in cases of tumor rupture. However, liver transplantation is not advised. CONCLUSION: We presented an overview of the demographics, tumor characteristics and treatment outcomes of the largest number of primary hepatic angiosarcoma patients investigated to date. We highlight the use of routine physical examinations and surgery combined with adjuvant chemotherapy to improve the outcomes in these cases.

Effect of Comorbidity on Outcomes of Patients with Advanced Non-Small Cell Lung Cancer Undergoing Anti-PD1 Immunotherapy.

BACKGROUND Comorbidities are reportedly related to the survival of patients with non-small cell lung cancer (NSCLC). The purpose of this study was to explore the impact of comorbidity, assessed by the Charlson comorbidity index (CCI) and the simplified comorbidity scores (SCS) on clinical outcomes of patients with NSCLC treated with immune checkpoint inhibitors. MATERIAL AND METHODS Sixty-six patients with NSCLC who received programmed cell death protein 1 (PD1) inhibitors in our institution in the past 2 years were enrolled in this retrospective study. Data on comorbidity (CCI and SCS) and clinical outcomes, including progression-free survival (PFS), immunotherapy responses, and immunotherapy-related adverse events, were analyzed. RESULTS The disease control rate was obviously higher among patients in the CCI <1 group than the CCI ≥1 group (P<0.001), but were similar between the SCS <8 group and SCS ≥8 group (P=0.585). The median PFS in the CCI <1 group was 271.0 days (95% CI: 214.3-327.7 days) compared with 232.0 days (95% CI: 66.2-397.8 days) for the CCI ≥1 group (P=0.0084). However, the median PFS showed no difference between the groups with SCS <8 at 271.0 days (95% CI: 138.7-403.3 days) versus SCS ≥8 at 222.0 days (95% CI: 196.2-247.8 days), P=0.2106). The incidence of adverse events was similar among patients with high versus low comorbidity indexes (CCI: 35.8% versus 23.6%, P=0.286, respectively; and SCS: 28.0% versus 29.3%, respectively, P=0.912). CONCLUSIONS The comorbidity burden might be a predictor for survival in patients with NSCLC undergoing PD1 inhibitor immunotherapy.

Influence of Hypertension on the Survival of Non-Small Cell Lung Cancer Patients with Type 2 Diabetes Mellitus.

BACKGROUND Hypertension and diabetes mellitus (DM) are both the risk factors for cancer. This study aimed to explore the prognostic value of fasting blood glucose (FBG) and hypertension in type 2 DM (T2DM) patients with advanced non-small cell lung cancer (NSCLC) who had received chemotherapy treatment. MATERIAL AND METHODS There were 181 advanced NSCLC patients with T2DM between 2010 and 2019 included in this study. Their laboratory and clinical data were retrospectively analyzed. The predictive value of FBG and hypertension was evaluated. The Kaplan-Meier method was used to evaluate progression-free survival (PFS). RESULTS The median PFS was 168.0 days (95% CI: 137.9-198.7 days) in patients with FBG ≥7 mmol/L compared to 154.0 days (95% CI: 126.7-181.3 days) for patients with FBG <7 mmol/L (hazard ratio [HR]=1.054; 95% CI: 0.7669-1.452; P=0.7447). Median PFS was longer in non-hypertensive patients than in hypertensive patients [179.0 days (95% CI: 137.3-220.7 days) versus 128.0 days (95% CI: 96.3-159.7 days); P=0.0189]. The existence of hypertension (HR=1.478; 95% CI: 1.063-2.055; P=0.020) was an independent predictor for shorter PFS in the multivariate analysis. Decreased hemoglobin was the major adverse event (over 95% patients). The incidence of all grades of adverse reactions was similar between hypertensive and non-hypertensive patients (all P>0.05) except diarrhea (P=0.020). CONCLUSIONS Complication of hypertension might confer a poor survival for advanced NSCLC patients with T2DM. Further prospective research is needed to confirm these findings.

EZH2 regulates PD-L1 expression via HIF-1α in non-small cell lung cancer cells.

Lung cancer is the most commonly diagnosed cancer and accounts for most cancer-related mortalities worldwide. The high expression of programmed death ligand 1 (PD-L1) is an important factor that promotes immune escape of lung cancer, thus aggravates chemotherapy resistance and poor prognosis. Therefore, understanding the regulatory mechanism of PD-L1 in lung cancer is critical for tumor immunotherapy. Enhancer of Zeste homolog2 (EZH2), an epigenetic regulatory molecule with histone methyltransferase activity, promotes the formation of an immunosuppressive microenvironment. This study aimed to investigate the role of EZH2 in PD-L1 expression and in the progression of lung tumors. We found that EZH2 was upregulated in lung cancer tissues and positively correlated with PD-L1 levels and poor prognosis. Further, shRNA-expressing lentivirus mediated EZH2 knockdown suppressed both the mRNA and protein expression level of PD-L1, thus delaying lung cancer progression in vivo by enhancing anti-tumor immune responses. Moreover, the regulatory effect of EZH2 on PD-L1 depended on HIF-1α. The present results indicate that EZH2 regulates the immunosuppressive molecule PD-L1 expression via HIF-1α in non-small cell lung cancer cells.

Molecular Network-Based Drug Prediction in Thyroid Cancer.

As a common malignant tumor disease, thyroid cancer lacks effective preventive and therapeutic drugs. Thus, it is crucial to provide an effective drug selection method for thyroid cancer patients. The connectivity map (CMAP) project provides an experimental validated strategy to repurpose and optimize cancer drugs, the rationale behind which is to select drugs to reverse the gene expression variations induced by cancer. However, it has a few limitations. Firstly, CMAP was performed on cell lines, which are usually different from human tissues. Secondly, only gene expression information was considered, while the information about gene regulations and modules/pathways was more or less ignored. In this study, we first measured comprehensively the perturbations of thyroid cancer on a patient including variations at gene expression level, gene co-expression level and gene module level. After that, we provided a drug selection pipeline to reverse the perturbations based on drug signatures derived from tissue studies. We applied the analyses pipeline to the cancer genome atlas (TCGA) thyroid cancer data consisting of 56 normal and 500 cancer samples. As a result, we obtained 812 up-regulated and 213 down-regulated genes, whose functions are significantly enriched in extracellular matrix and receptor localization to synapses. In addition, a total of 33,778 significant differentiated co-expressed gene pairs were found, which form a larger module associated with impaired immune function and low immunity. Finally, we predicted drugs and gene perturbations that could reverse the gene expression and co-expression changes incurred by the development of thyroid cancer through the Fisher's exact test. Top predicted drugs included validated drugs like baclofen, nevirapine, glucocorticoid, formaldehyde and so on. Combining our analyses with literature mining, we inferred that the regulation of thyroid hormone secretion might be closely related to the inhibition of the proliferation of thyroid cancer cells.

S100B Mediates Stemness of Ovarian Cancer Stem-Like Cells Through Inhibiting p53.

S100B is one of the members of the S100 protein family and is involved in the progression of a variety of cancers. Ovarian cancer is driven by cancer stem-like cells (CSLCs) that are involved in tumorigenesis, metastasis, chemo-resistance and relapse. We then hypothesized that S100B might exert pro-tumor effects by regulating ovarian CSLCs stemness, a key characteristic of CSLCs. First, we observed the high expression of S100B in ovarian cancer specimens when compared to that in normal ovary. The S100B upregulation associated with more advanced tumor stages, poorer differentiation and poorer survival. In addition, elevated S100B expression correlated with increased expression of stem cell markers including CD133, Nanog and Oct4. Then, we found that S100B was preferentially expressed in CD133+ ovarian CSLCs derived from both ovarian cancer cell lines and primary tumors of patients. More importantly, we revealed that S100B knockdown suppressed the in vitro self-renewal and in vivo tumorigenicity of ovarian CSLCs and decreased their expression of stem cell markers. S100B ectopic expression endowed non-CSLCs with stemness, which has been demonstrated with both in vitro and in vivo experiments. Mechanically, we demonstrated that the underlying mechanism of S100B-mediated effects on CSLCs stemness was not dependent on its binding with a receptor for advanced glycation end products (RAGE), but might be through intracellular regulation, through the inhibition of p53 expression and phosphorylation. In conclusion, our results elucidate the importance of S100B in maintenance of ovarian CSLCs stemness, which might provide a promising therapeutic target for ovarian cancer. Stem Cells 2017;35:325-336.

A Hybrid Deep Learning Model for Predicting Protein Hydroxylation Sites.

Protein hydroxylation is one type of post-translational modifications (PTMs) playing critical roles in human diseases. It is known that protein sequence contains many uncharacterized residues of proline and lysine. The question that needs to be answered is: which residue can be hydroxylated, and which one cannot. The answer will not only help understand the mechanism of hydroxylation but can also benefit the development of new drugs. In this paper, we proposed a novel approach for predicting hydroxylation using a hybrid deep learning model integrating the convolutional neural network (CNN) and long short-term memory network (LSTM). We employed a pseudo amino acid composition (PseAAC) method to construct valid benchmark datasets based on a sliding window strategy and used the position-specific scoring matrix (PSSM) to represent samples as inputs to the deep learning model. In addition, we compared our method with popular predictors including CNN, iHyd-PseAAC, and iHyd-PseCp. The results for 5-fold cross-validations all demonstrated that our method significantly outperforms the other methods in prediction accuracy.

Targeting the Wnt-Regulatory Protein CTNNBIP1 by microRNA-214 Enhances the Stemness and Self-Renewal of Cancer Stem-Like Cells in Lung Adenocarcinomas.

A novel hypothesis in cancer biology proposes that cancer growth is driven by cancer stem-like cells (CSLCs), also called tumor-initiating cells, which can self-renew and differentiate into multilineage progeny in a fashion similar to stem cells. However, the impact and underlying mechanisms of this process in lung adenocarcinoma (LAC) remain to be elucidated. Here, we report that microRNA-214 (miR-214) contributes to cell self-renewal by directly targeting catenin beta interacting protein 1 (CTNNBIP1), a member of the Wnt signaling pathway. We demonstrate that miR-214 overexpression enhances stem-like properties in LAC cells and that miR-214 shows increased expression in CSLCs derived from primary tumor tissue and from two LAC cell lines (A549 and NCI-H1650). Strikingly, downregulation of miR-214 expression in CSLCs resulted in a significant decrease in spheroid formation and the expression of the stem-cell markers Nanog, Oct-4, and Sox-2. Finally, CTNNBIP1 was identified as a target of miR-214. miR-214 expression in LAC was negatively correlated with CTNNBIP1 expression and positively correlated with differentiated cellular states. Moreover, CTNNBIP1 expression correlated with longer overall survival in LAC patients. This study reveals that miR-214 plays a critical role in CSLC self-renewal and stemness by targeting CTNNBIP1. The identification of this functional miR-214-CTNNBIP1 interaction that regulates self-renewal in CSLCs has the potential to direct the development of novel therapeutic strategies for LAC.

Dosage effects of BDNF Val66Met polymorphism on cortical surface area and functional connectivity.

The single nucleotide polymorphism (SNP) that leads to a valine-to-methionine substitution at codon 66 (Val66Met) in BDNF is correlated with differences in cognitive and memory functions, as well as with several neurological and psychiatric disorders. MRI studies have already shown that this genetic variant contributes to changes in cortical thickness and volume, but whether the Val66Met polymorphism affects the cortical surface area of healthy subjects remains unclear. Here, we used multimodal MRI to study whether this polymorphism would affect the cortical morphology and resting-state functional connectivity of a large sample of healthy Han Chinese human subjects. An SNP-wise general linear model analysis revealed a "dosage effect" of the Met allele, specifically a stepwise increase in cortical surface area of the right anterior insular cortex with increasing numbers of the Met allele. Moreover, we found enhanced functional connectivity between the anterior insular and the dorsolateral prefrontal cortices that was linked with the dosage of the Met allele. In conclusion, these data demonstrated a "dosage effect" of BDNF Val66Met on normal cortical structure and function, suggesting a new path for exploring the mechanisms underlying the effects of genotype on cognition.

Residual graph transformer for autism spectrum disorder prediction.

Brain functional connectivity (FC) based on resting-state functional magnetic resonance imaging (rs-fMRI) has been in vogue to predict Autism Spectrum Disorder (ASD), which is a neuropsychiatric disease up the plight of locating latent biomarkers for clinical diagnosis. Albeit massive endeavors have been made, most studies are fed up with several chronic issues, such as the intractability of harnessing the interaction flourishing within brain regions, the astriction of representation due to vanishing gradient within deeper network architecture, and the poor interpretability leading to unpersuasive diagnosis. To ameliorate these issues, a FC-learned Residual Graph Transformer Network, namely RGTNet, is proposed. Specifically, we design a Graph Encoder to extract temporal-related features with long-range dependencies, from which interpretable FC matrices would be modeled. Besides, the residual trick is introduced to deepen the GCN architecture, thereby learning the higher-level information. Moreover, a novel Graph Sparse Fitting followed by weighted aggregation is proposed to ease dimensionality explosion. Empirically, the results on two types of ABIDE data sets demonstrate the meliority of RGTNet. Notably, the achieved ACC metric reaches 73.4%, overwhelming most competitors with merely 70.9% on the AAL atlas using a five-fold cross-validation policy. Moreover, the investigated biomarkers concord closely with the authoritative medical knowledge, paving a viable way for ASD-clinical diagnosis. Our code is available at https://github.com/CodeGoat24/RGTNet.

NIMEQ-SACNet: A novel self-attention precision medicine model for vision-threatening diabetic retinopathy using image data.

In the realm of precision medicine, the potential of deep learning is progressively harnessed to facilitate intricate clinical decision-making, especially when navigating multifaceted datasets encompassing Omics, Clinical, image, device, social, and environmental dimensions. This study accentuates the criticality of image data, given its instrumental role in detecting and classifying vision-threatening diabetic retinopathy (VTDR) - a predominant global contributor to vision impairment. The timely identification of VTDR is a linchpin for efficacious interventions and the mitigation of vision loss. Addressing this, This study introduces "NIMEQ-SACNet," a novel hybrid model by the prowess of the Enhanced Quantum-Inspired Binary Grey Wolf Optimizer (EQI-BGWO) with a self-attention capsule network. The proposed approach is characterized by two pivotal advancements: firstly, the augmentation of the Binary Grey Wolf Optimization through Quantum Computing methodologies, and secondly, the deployment of the enhanced EQI-BGWO to adeptly calibrate the SACNet's parameters, culminating in a notable uplift in VTDR classification accuracy. The proposed model's ability to handle binary, 5-stage, and 7-stage VTDR classifications adroitly is noteworthy. Rigorous assessments on the fundus image dataset, underscored by metrics such as Accuracy, Sensitivity, Specificity, Precision, F1-Score, and MCC, bear testament to NIMEQ-SACNet's pre-eminence over prevailing algorithms and classification frameworks.

Improved Support Vector Machine based on CNN-SVD for vision-threatening diabetic retinopathy detection and classification.

The integration of artificial intelligence (AI) in diagnosing diabetic retinopathy, a major contributor to global vision impairment, is becoming increasingly pronounced. Notably, the detection of vision-threatening diabetic retinopathy (VTDR) has been significantly fortified through automated techniques. Traditionally, the reliance on manual analysis of retinal images, albeit slow and error-prone, constituted the conventional approach. Addressing this, our study introduces a novel methodology that amplifies the robustness and precision of the detection process. This is complemented by the groundbreaking Hierarchical Block Attention (HBA) and HBA-U-Net architecture, which notably propel attention mechanisms in image segmentation. This innovative model refines image processing without imposing excessive computational demands by honing in on individual pixel intricacies, spatial relationships, and channel-specific attention. Building upon this innovation, our proposed method employs a multi-stage strategy encompassing data pre-processing, feature extraction via a hybrid CNN-SVD model, and classification employing an amalgamation of Improved Support Vector Machine-Radial Basis Function (ISVM-RBF), DT, and KNN techniques. Rigorously tested on the IDRiD dataset classified into five severity tiers, the hybrid model yields remarkable performance, achieving a 99.18% accuracy, 98.15% sensitivity, and 100% specificity in VTDR detection, thus surpassing existing methods. These results underscore a more potent avenue for diagnosing and addressing this crucial ocular condition while underscoring AI's transformative potential in medical care, particularly in ophthalmology.