RECONSTRUCTING RETINAL VISUAL IMAGES FROM 3T FMRI DATA ENHANCED BY UNSUPERVISED LEARNING.

The reconstruction of human visual inputs from brain activity, particularly through functional Magnetic Resonance Imaging (fMRI), holds promising avenues for unraveling the mechanisms of the human visual system. Despite the significant strides made by deep learning methods in improving the quality and interpretability of visual reconstruction, there remains a substantial demand for high-quality, long-duration, subject-specific 7-Tesla fMRI experiments. The challenge arises in integrating diverse smaller 3-Tesla datasets or accommodating new subjects with brief and low-quality fMRI scans. In response to these constraints, we propose a novel framework that generates enhanced 3T fMRI data through an unsupervised Generative Adversarial Network (GAN), leveraging unpaired training across two distinct fMRI datasets in 7T and 3T, respectively. This approach aims to overcome the limitations of the scarcity of high-quality 7-Tesla data and the challenges associated with brief and low-quality scans in 3-Tesla experiments. In this paper, we demonstrate the reconstruction capabilities of the enhanced 3T fMRI data, highlighting its proficiency in generating superior input visual images compared to data-intensive methods trained and tested on a single subject.

ENHANCING 3T RETINOTOPIC MAPS USING DIFFEOMORPHIC REGISTRATION.

Retinotopic mapping aims to uncover the relationship between visual stimuli on the retina and neural responses on the visual cortical surface. This study advances retinotopic mapping by applying diffeomorphic registration to the 3T NYU retinotopy dataset, encompassing analyze-PRF and mrVista data. Diffeomorphic Registration for Retinotopic Maps (DRRM) quantifies the diffeomorphic condition, ensuring accurate alignment of retinotopic maps without topological violations. Leveraging the Beltrami coefficient and topological condition, DRRM significantly enhances retinotopic map accuracy. Evaluation against existing methods demonstrates DRRM's superiority on various datasets, including 3T and 7T retinotopy data. The application of diffeomorphic registration improves the interpretability of low-quality retinotopic maps, holding promise for clinical applications.

Transcriptome Responses in Medicago sativa (Alfalfa) Associated with Regrowth Process in Different Grazing Intensities.

Medicago sativa L. (alfalfa), a perennial legume, is generally regarded as a valuable source of protein for livestock and is subjected to long and repeated grazing in natural pastures. Studying the molecular response mechanism of alfalfa under different grazing treatments is crucial for understanding its adaptive traits and is of great significance for cultivating grazing-tolerant grass. Here, we performed a transcriptomic analysis to investigate changes in the gene expression of M. sativa under three grazing intensities. In total, 4184 differentially expressed genes (DEGs) were identified among the tested grazing intensities. The analysis of gene ontology (GO) revealed that genes were primarily enriched in cells, cellular processes, metabolic processes, and binding. In addition, two pathways, the plant-pathogen interaction pathway and the plant hormone signal pathway, showed significant enrichment in the Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis. Protein kinases and transcription factors associated with hormones and plant immunity were identified. The plant immunity-related genes were more activated under high grazing treatment, while more genes related to regeneration were expressed under light grazing treatment. These results suggest that M. sativa exhibits different strategies to increase resilience and stress resistance under various grazing intensities. Our findings provide important clues and further research directions for understanding the molecular mechanisms of plant responses to grazing.

Insight into the differences in meat quality among three breeds of sheep on the Qinghai-Tibetan plateau from the perspective of metabolomics and rumen microbiota.

Mutton is one of the most popular meats among the general public due to its high nutritional value. This study evaluated the differences in meat quality among Chaka (CK), Black Tibetan (BT) and Oula (OL) sheep and investigated the metabolic mechanisms affecting meat quality using targeted and untargeted metabolomics and 16S rRNA. The results showed that the meat quality of CK sheep was superior to that of BT and OL sheep in terms of meat color, muscle fiber characteristics and nutritional quality. Pseudobutyrivibrio, Alloprevotella, Methanobrevibacter, unidentified_Christensenellaceae, and unidentified_Bacteroidales were key microbes involved in regulating meat color, muscle fiber characteristics, amino acid and fatty acid content. Protein digestion/absorption, pentose phosphate metabolism, carbon metabolism, and glyoxylate and dicarboxylate metabolism were important metabolic pathways involved in meat quality regulation. Our study is important for the development of sheep breeding strategy and sheep meat industry in Qinghai-Tibetan Plateau.

Short-term multi-energy consumption forecasting for integrated energy system based on interactive multi-scale convolutional module.

Accurate consumption forecasting is of great importance to grasp the energy consumption habits of consumers and promote the stable and efficient operation of integrated energy system (IES). To this end, this paper proposes an interactive multi-scale convolutional module-based short-term multi-energy consumption forecasting method for IES. Firstly, based on multi-scale feature fusion and multi-energy interactive learning, a novel interactive multi-scale convolutional module is proposed to extract and share the coupling information between energy consumption from different scales without increasing network parameters. Then, a short-term multi-energy consumption forecasting method is proposed, where different forecasting network structures are selected in different seasons to make full use of seasonal and coupling characteristics of the energy consumption, thus enhancing prediction performance. Furthermore, a Laplace distribution-based loss function weight optimization method is proposed to dynamically balance the loss magnitude and training speed of joint forecast tasks more robustly. Finally, the effectiveness and superiority of the proposed method are verified by comparative simulation experiments.

A Competition for the Diagnosis of Myopic Maculopathy by Artificial Intelligence Algorithms.

Importance: Myopic maculopathy (MM) is a major cause of vision impairment globally. Artificial intelligence (AI) and deep learning (DL) algorithms for detecting MM from fundus images could potentially improve diagnosis and assist screening in a variety of health care settings. Objectives: To evaluate DL algorithms for MM classification and segmentation and compare their performance with that of ophthalmologists. Design, Setting, and Participants: The Myopic Maculopathy Analysis Challenge (MMAC) was an international competition to develop automated solutions for 3 tasks: (1) MM classification, (2) segmentation of MM plus lesions, and (3) spherical equivalent (SE) prediction. Participants were provided 3 subdatasets containing 2306, 294, and 2003 fundus images, respectively, with which to build algorithms. A group of 5 ophthalmologists evaluated the same test sets for tasks 1 and 2 to ascertain performance. Results from model ensembles, which combined outcomes from multiple algorithms submitted by MMAC participants, were compared with each individual submitted algorithm. This study was conducted from March 1, 2023, to March 30, 2024, and data were analyzed from January 15, 2024, to March 30, 2024. Exposure: DL algorithms submitted as part of the MMAC competition or ophthalmologist interpretation. Main Outcomes and Measures: MM classification was evaluated by quadratic-weighted κ (QWK), F1 score, sensitivity, and specificity. MM plus lesions segmentation was evaluated by dice similarity coefficient (DSC), and SE prediction was evaluated by R2 and mean absolute error (MAE). Results: The 3 tasks were completed by 7, 4, and 4 teams, respectively. MM classification algorithms achieved a QWK range of 0.866 to 0.901, an F1 score range of 0.675 to 0.781, a sensitivity range of 0.667 to 0.778, and a specificity range of 0.931 to 0.945. MM plus lesions segmentation algorithms achieved a DSC range of 0.664 to 0.687 for lacquer cracks (LC), 0.579 to 0.673 for choroidal neovascularization, and 0.768 to 0.841 for Fuchs spot (FS). SE prediction algorithms achieved an R2 range of 0.791 to 0.874 and an MAE range of 0.708 to 0.943. Model ensemble results achieved the best performance compared to each submitted algorithms, and the model ensemble outperformed ophthalmologists at MM classification in sensitivity (0.801; 95% CI, 0.764-0.840 vs 0.727; 95% CI, 0.684-0.768; P = .006) and specificity (0.946; 95% CI, 0.939-0.954 vs 0.933; 95% CI, 0.925-0.941; P = .009), LC segmentation (DSC, 0.698; 95% CI, 0.649-0.745 vs DSC, 0.570; 95% CI, 0.515-0.625; P < .001), and FS segmentation (DSC, 0.863; 95% CI, 0.831-0.888 vs DSC, 0.790; 95% CI, 0.742-0.830; P < .001). Conclusions and Relevance: In this diagnostic study, 15 AI models for MM classification and segmentation on a public dataset made available for the MMAC competition were validated and evaluated, with some models achieving better diagnostic performance than ophthalmologists.

The geography of healthcare: Mapping patient flow and medical resource allocation in China.

The misallocation of medical resources leads to interregional patient flow in search of better healthcare. Using out-of-pocket medical expenditure data and a delineating method, this paper identifies spatial clusters of medical services in China based on patient flow across cities. Our findings indicate that healthcare resources are more concentrated in northern China, while southern China is divided into several large healthcare clusters at the same threshold. The provincial capital and economically significant cities are more likely to serve as medical cluster centers. We further apply the gravity model to examine the effects of healthcare disparity on cross-city medical expenditure. The results reveal that geographic disparities in high-quality medical resources encourage remote healthcare-seeking behavior, and the shorter the distance between locations, the higher the level of medical consumption. Patients are inclined to seek medical services within their own province and within specific medical clusters identified through delineation methods. This effect is more pronounced among patients from non-central cities. This study highlights healthcare inequality by examining cross-regional medical expenditure, providing valuable insights for future healthcare policy.

RTP4 Enhances Corneal HSV-1 Infection in Mice With Type 2 Diabetes Mellitus.

Purpose: The purpose of this study was to investigate whether corneal lesions in mice with type 2 diabetes mellitus (T2D) infected with herpes simplex virus (HSV)-1 are more severe, and to elucidate the specific underlying mechanism. Methods: The corneas of control mice and T2D mice induced by a high-fat diet combined with streptozotocin were infected with the HSV-1 Mckrae strain to assess corneal infection, opacity, and HSV-1 replication. RNA sequencing of the corneal epithelium from wild-type and db/db mice (a genetic T2D mouse model) was conducted to identify the key gene affecting T2D infection. Immunofluorescence staining was performed on corneal sections from T2D mice and patients with T2D. The effect of small interfering RNA (siRNA) knockdown on corneal HSV-1 infection was evaluated in both in vitro and in vivo models. Results: T2D mice exhibited a more severe infection phenotype following HSV-1 infection, characterized by augmented corneal opacity scores, elevated viral titers, and transcripts compared to control mice. Transcriptome analysis of corneal epithelium revealed a hyperactive viral response in T2D mice, highlighting the differentially expressed gene Rtp4 (encoding receptor transporter protein 4). Receptor transporter protein 4 (RTP4) expression was enhanced in the corneal epithelium of T2D mice and patients with T2D. Virus binding assays demonstrated that RTP4 facilitated HSV-1 binding to human corneal epithelial cells. Silencing RTP4 alleviated HSV-1 infection in both in vitro and in vivo T2D models. Conclusions: The findings indicate that elevated RTP4 exacerbates HSV-1 infection by enhancing its binding to corneal epithelial cells, whereas Rtp4 knockdown mitigated corneal lesions in T2D mice. This implies RTP4 as a potential target for intervention in diabetic HSV-1 infection.

HBsAg and TLR7/8 dual-targeting antibody-drug conjugates induce sustained anti-HBV activity in AAV/HBV mice: a preliminary study.

Hepatitis B virus (HBV) infection is a significant global health concern due to elevated immunosuppressive viral antigen levels, the host immune system's inability to manage HBV, and the liver's immunosuppressive conditions. While immunotherapies utilizing broadly reactive HBV neutralizing antibodies present potential due to their antiviral capabilities and Fc-dependent vaccinal effects, they necessitate prolonged and frequent dosing to achieve optimal therapeutic outcomes. Toll-like receptor 7/8 (TLR7/8) agonists have been demonstrated promise for the cure of chronic hepatitis B, but their systemic use often leads to intense side effects. In this study, we introduced immune-stimulating antibody conjugates which consist of TLR7/8 agonists 1-[[4-(aminomethyl)phenyl]methyl]-2-butyl-imidazo[4,5-c]quinolin-4-amine (IMDQ) linked to an anti-hepatitis B surface antigen (HBsAg) antibody 129G1, and designated as 129G1-IMDQ. Our preliminary study highlights that 129G1-IMDQ can prompt robust and sustained anti-HBsAg specific reactions with short-term administration. This underscores the conjugate's potential as an effective strategy for HBsAg clearance and seroconversion, offering a fresh perspective for a practical therapeutic approach in the functional cure of CHB. Highlights: HBV-neutralizing antibody 129G1 was linked with a TLR7/8 agonist small molecule compound IMDQ.Treatment with 129G1-IMDQ has shown significant promise in lowering HBsAg levels in AAV/HBV mice.129G1-IMDQ were eliciting a strong and lasting anti-HBsAg immune response after short-term treatment in AAV/HBV mice.

Development of T follicular helper cell-independent nanoparticle vaccines for SARS-CoV-2 or HIV-1 by targeting ICOSL.

T helper cells, particularly T follicular helper (TFH) cells, are essential for the neutralizing antibody production elicited by pathogens or vaccines. However, in immunocompromised individuals, the inefficient support from TFH cells could lead to limited protection after vaccine inoculation. Here we showed that the conjugation of inducible T cell costimulatory (ICOS) onto the nanoparticle, together with immunogen, significantly enhanced the immune response of the vaccines specific for SARS-CoV-2 or human immunodeficiency virus type-1 (HIV-1) in TFH-deficient mice. Further studies indicated that ICOSL on B cells was triggered by ICOS binding, subsequently activated the PKCß signaling pathway, and enhanced the survival and proliferation of B cells. Our findings revealed that the stimulation of ICOS-ICOSL interaction by adding ICOS on the nanoparticle vaccine significantly substitutes the function of TFH cells to support B cell response, which is significant for the immunocompromised people, such as the elderly or HIV-1-infected individuals.

qPRF: A system to accelerate population receptive field decoding.

Patterns of BOLD response can be decoded using the population receptive field (PRF) model to reveal how visual input is represented on the cortex (Dumoulin and Wandell, 2008). The time cost of evaluating the PRF model is high, often requiring days to decode BOLD signals for a small cohort of subjects. We introduce the qPRF, an efficient method for decoding that reduced the computation time by a factor of 1436 when compared to another widely available PRF decoder (Kay, Winawer, Mezer and Wandell, 2013) on a benchmark of data from the Human Connectome Project (HCP; Van Essen, Smith, Barch, Behrens, Yacoub and Ugurbil, 2013). With a specially designed data structure and an efficient search algorithm, the qPRF optimizes the five PRF model parameters according to a least-squares criterion. To verify the accuracy of the qPRF solutions, we compared them to those provided by Benson, Jamison, Arcaro, Vu, Glasser, Coalson, Van Essen, Yacoub, Ugurbil, Winawer and Kay (2018). Both hemispheres of the 181 subjects in the HCP data set (a total of 10,753,572 vertices, each with a unique BOLD time series of 1800 frames) were decoded by qPRF in 15.2 hours on an ordinary CPU. The absolute difference in R 2 reported by Benson et al. and achieved by the qPRF was negligible, with a median of 0.39% ( R 2 units being between 0% and 100%). In general, the qPRF yielded a slightly better fitting solution, achieving a greater R 2 on 99.7% of vertices. The qPRF may facilitate the development and computation of more elaborate models based on the PRF framework, as well as the exploration of novel clinical applications.

Analysis of the Therapeutic Efficacy of Hysteroscopic Electric Resection in the Treatment of Atypical Endometrial Hyperplasia and Factors Influencing Prognosis.

Objective: The objective of this study was to evaluate the efficacy of hysteroscopic electroresection in the treatment of atypical endometrial hyperplasia and to determine the prognostic factors. Methods: 226 patients with endometrial dysplasia treated in hospital from January 2021 to August 2022 were selected and divided into control group (113 cases) and study group (113 cases) according to different treatment methods selected by the patients themselves. The control group received curettage plus conventional progesterone treatment, while the study group received hysteroscopic electroresection plus conventional progesterone treatment. After 6 months of treatment, the clinical efficacy (complete response, partial response and progress) of the two groups were evaluated, complications and adverse drug reactions of the two groups were analyzed, and estrogen levels before and after treatment were compared between the two groups. After 1 year follow-up, patients were divided into relapse group and non-recurrence group according to whether they had relapse or not. Clinical data of the two groups were compared to analyze the related factors affecting the prognosis of patients. Results: (1) Chi-square test results showed that the total effective rate of the study group was higher (96.46% VS 77.88%) than that of the control group (P < .05). The complication rate and recurrence rate of the study group were lower than those of the control group (1.77% VS 7.96%, 4.42% VS 21.24%) (P < .05). (2) t test results of independent samples showed that after 6 months of treatment, the levels of luteinizing hormone (LH) and follicle-stimulating hormone (FSH) in the study group were lower than those in the control group (P < .05); (3) The t test results of independent samples indicated that the age and body mass index of the relapsed group were higher than those of the non-relapsed group (P < .05); Chi-square test results showed that the proportion of diabetes was higher than that of the group without recurrence, and the proportion of hysteroscopic electroresection was lower than that of the group without recurrence (P < .05). (4) Logistic regression model was established, and the results showed that age (OR=1.159), body mass index (OR=1.529) and diabetes (OR=3.861) were the risk factors for prognosis of patients with endometrial dysplasia (P < .05), and hysteroscopic electroresection was the protective factor (OR < 1, P < .05). Conclusion: Hysteroscopic electroresection shows significant potential in the treatment of atypical hyperplasia of endometrial, and can improve clinical efficacy and reduce complications by effectively regulating estrogen secretion. In addition, studies have shown that the prognosis of endometrial dysplasia may be related to the age of patients, body mass index and diabetes mellitus. Therefore, for patients with the above risk factors, early consideration of hysteroscopic electrotomy therapy is recommended to reduce recurrence rates and provide important informational support for treatment protocols and clinical guidelines.

Effects of HOX family regulator-mediated modification patterns and immunity characteristics on tumor-associated cell type in endometrial cancer.

Endometrial cancer (UCEC) is one of three major malignant tumors in women. The HOX gene regulates tumor development. However, the potential roles of HOX in the expression mechanism of multiple cell types and in the development and progression of tumor microenvironment (TME) cell infiltration in UCEC remain unknown. In this study, we utilized both the The Cancer Genome Atlas (TCGA) database and International Cancer Genome Consortium (ICGC) database to analyze transcriptome data of 529 patients with UCEC based on 39 HOX genes, combing clinical information, we discovered HOX gene were a pivotal factor in the development and progression of UCEC and in the formation of TME diversity and complexity. Here, a new scoring system was developed to quantify individual HOX patterns in UCEC. Our study found that patients in the low HOX score group had abundant anti-tumor immune cell infiltration, good tumor differentiation, and better prognoses. In contrast, a high HOX score was associated with blockade of immune checkpoints, which enhances the response to immunotherapy. The Real-Time quantitative PCR (RT-qPCR) and Immunohistochemistry (IHC) exhibited a higher expression of the HOX gene in the tumor patients. We revealed that the significant upregulation of the HOX gene in the epithelial cells can activate signaling pathway associated with tumour invasion and metastasis through single-cell RNA sequencing (scRNA-seq), such as nucleotide metabolic proce and so on. Finally, a risk prognostic model established by the positive relationship between HOX scores and cancer-associated fibroblasts (CAFs) can predict the prognosis of individual patients by scRNA-seq and transcriptome data sets. In sum, HOX gene may serve as a potential biomarker for the diagnosis and prediction of UCEC and to develop more effective therapeutic strategies.

Integrated Piezoelectric/Pyroelectric Sensing from Organic-Inorganic Perovskite Nanocomposites.

Flexible ferroelectric materials are in high demand in emerging energy harvesting and self-powered sensing electronics. However, current flexible ferroelectric polymers, such as poly(vinylidene fluoride) (PVDF) and P(VDF-co-trifluoroethylene) [P(VDF-TrFE)], cannot fulfill the requirement of emerging applications because of their low piezoelectric/pyroelectric performance. In this work, using organic-inorganic hybrid perovskite [(4-aminotetrahydropyran)2PbBr2Cl2] ferroelectric nanorods as reinforcement and P(VDF-TrFE) as the matrix, we prepared flexible core-sheath piezoelectric nanofibers and pyroelectric nanocomposite films. The core-sheath nanofibers possess a record-high piezoelectric coefficient of 78.1 pC·N-1, and the output voltage reaches to 192 V, with the maximum power density of 1.04 W·m-2. On the other hand, the nanocomposite film exhibits a high pyroelectric coefficient of 58.2 µC·m-2·K-1 at 333 K, which yields a voltage of 6.1 V under 6.6 K temperature fluctuation. An integrated flexible sensing device was prepared by combining piezoelectric nanofibers and pyroelectric films, which can wirelessly detect vibration and temperature fluctuation simultaneously. The integrated device is suitable for pipelines, power equipment, and other scenarios, where vibration and temperature need to be monitored at the same time.

Bacteria-Like Gaiella Accelerate Soil Carbon Loss by Decomposing Organic Matter of Grazing Soils in Alpine Meadows on the Qinghai-Tibet Plateau.

The alpine meadows of the Qinghai-Tibet Plateau have significant potential for storing soil carbon, which is important to global carbon sequestration. Grazing is a major threat to its potential for carbon sequestration. However, grazing poses a major threat to this potential by speeding up the breakdown of organic matter in the soil and releasing carbon, which may further lead to positive carbon-climate change feedback and threaten ecological security. Therefore, in order to accurately explore the driving mechanism and regulatory factors of soil organic matter decomposition in grazing alpine meadows on the Qinghai-Tibet Plateau, we took the grazing sample plots of typical alpine meadows as the research object and set up grazing intensities of different life cycles, aiming to explore the relationship and main regulatory factors of grazing on soil organic matter decomposition and soil microorganisms. The results show the following: (1) soil microorganisms, especially Acidobacteria and Acidobacteria, drove the decomposition of organic matter in the soil, thereby accelerating the release of soil carbon, which was not conducive to soil carbon sequestration in grassland; (2) the grazing triggering effect formed a positive feedback with soil microbial carbon release, accelerating the decomposition of organic matter and soil carbon loss; and (3) the grazing ban and light grazing were more conducive to slowing down soil organic matter decomposition and increasing soil carbon sequestration.

Alternating electric fields transform the intricate network of tumour vasculature into orderly parallel capillaries and enhance the anti-angiogenesis effect of bevacizumab.

The search for effective strategies to target tumour angiogenesis remains a critical goal of cancer research. We present a pioneering approach using alternating electric fields to inhibit tumour angiogenesis and enhance the therapeutic efficacy of bevacizumab. Chicken chorioallantoic membrane, cell viability and in vitro endothelial tube formation assays revealed that electric fields with a frequency of 1000 kHz and an electric intensity of 0.6 V/cm inhibited the growth of vascular endothelial cells and suppressed tumour-induced angiogenesis. In an animal U87MG glioma model, 1000 kHz electric fields inhibited tumour angiogenesis and suppressed tumour growth. As demonstrated by 3D vessel analysis, tumour vasculature in the control group was a stout, interwoven network. However, electric fields transformed it into slim, parallel capillaries that were strictly perpendicular to the electric field direction. This architectural transformation was accompanied by apoptosis of vascular endothelial cells and a notable reduction in tumour vessel number. Additionally, we found that the anti-angiogenesis and tumour-suppression effects of electric fields synergised with bevacizumab. The anti-angiogenic mechanisms of electric fields include disrupting spindle formation during endothelial cell division and downregulating environmental angiogenesis-related cytokines, such as interleukin-6, CXCL-1, 2, 3, 5 and 8, and matrix metalloproteinases. In summary, our findings demonstrate the potential of alternating electric fields (AEFs) as a therapeutic modality to impede angiogenesis and restrain cancer growth.

Robust PCA with Lw,∗ and L2,1 Norms: A Novel Method for Low-Quality Retinal Image Enhancement.

Nonmydriatic retinal fundus images often suffer from quality issues and artifacts due to ocular or systemic comorbidities, leading to potential inaccuracies in clinical diagnoses. In recent times, deep learning methods have been widely employed to improve retinal image quality. However, these methods often require large datasets and lack robustness in clinical settings. Conversely, the inherent stability and adaptability of traditional unsupervised learning methods, coupled with their reduced reliance on extensive data, render them more suitable for real-world clinical applications, particularly in the limited data context of high noise levels or a significant presence of artifacts. However, existing unsupervised learning methods encounter challenges such as sensitivity to noise and outliers, reliance on assumptions like cluster shapes, and difficulties with scalability and interpretability, particularly when utilized for retinal image enhancement. To tackle these challenges, we propose a novel robust PCA (RPCA) method with low-rank sparse decomposition that also integrates affine transformations τi, weighted nuclear norm, and the L2,1 norms, aiming to overcome existing method limitations and to achieve image quality improvement unseen by these methods. We employ the weighted nuclear norm (Lw,∗) to assign weights to singular values to each retinal images and utilize the L2,1 norm to eliminate correlated samples and outliers in the retinal images. Moreover, τi is employed to enhance retinal image alignment, making the new method more robust to variations, outliers, noise, and image blurring. The Alternating Direction Method of Multipliers (ADMM) method is used to optimally determine parameters, including τi, by solving an optimization problem. Each parameter is addressed separately, harnessing the benefits of ADMM. Our method introduces a novel parameter update approach and significantly improves retinal image quality, detecting cataracts, and diabetic retinopathy. Simulation results confirm our method's superiority over existing state-of-the-art methods across various datasets.

Causal Brain Network in Clinically-Annotated Epileptogenic Zone Predicts Surgical Outcomes of Drug-Resistant Epilepsy.

OBJECTIVE: Patients with drug-resistant epilepsy (DRE) are commonly treated using neurosurgery, while its success rate is limited with approximately 50%. Predicting surgical outcomes is currently a prominent topic. The DRE is recognized as a network disorder involving a seizure triggering mechanism within epileptogenic zone (EZ); however, a systematic exploration of the EZ causal network remains lacking. METHODS: This paper will advance DRE study by: (1) developing a novel causal coupling algorithm, "full convergent cross mapping (FCCM)" to improve the quantization performance; (2) characterizing the DRE's multi-frequency epileptogenic network by FCCM calculation of ictal iEEG; (3) predicting surgical outcomes using network features and machine learning. Numerical validations demonstrate the FCCM's superior quantization in terms of nonlinearity, accuracy, and stability. A multicenter cohort containing 22 DRE patients with 81 seizures is included. RESULT: Based on the Mann-Whitney-U-test, coupling strength of the epileptogenic network in successful surgeries is significantly higher than that of the failed group, with the most significant difference observed in α -iEEG network (p = 1.52e - 07 ) Other clinical covariates are also considered and all th α -iEEG networks demonstrate consistent differences comparing successful and failed groups, with p = 0.014 and 9.23e - 06 for lesional and non-lesional DRE, p = 2.32e - 05, 0.0074 and 0.0030 for three clinical centers CHFU, JHU and NIH. Using FCCM features and 10-fold cross validation, the SVM achieves the highest accuracy of 87.65% in predicting surgical outcomes. CONCLUSION: The epileptogenic causal network is a reliable biomarker for estimating DRE's surgical outcomes. SIGNIFICANCE: The proposed approach is promising to facilitate DRE precision medicine.

Causal Brain Network Predicts Surgical Outcomes in Patients With Drug-Resistant Epilepsy: A Retrospective Comparative Study.

Network neuroscience, especially causal brain network, has facilitated drug-resistant epilepsy (DRE) studies, while surgical success rate in patients with DRE is still limited, varying from 30%  âˆ¼  70 %. Predicting surgical outcomes can provide additional guidance to adjust treatment plans in time for poorly predicted curative effects. In this retrospective study, we aim to systematically explore biomarkers for surgical outcomes by causal brain network methods and multicenter datasets. Electrocorticogram (ECoG) recordings from 17 DRE patients with 58 seizures were included. Ictal ECoG within clinically annotated epileptogenic zone (EZ) and non-epileptogenic zone (NEZ) were separately computed using six different algorithms to construct causal brain networks. All the brain network results were divided into two groups, successful and failed surgeries. Statistical results based on the Mann-Whitney-U-test show that: causal connectivity of α -frequency band ( 8  âˆ¼  13 Hz) in EZ calculated by convergent cross mapping (CCM) gains the most significant differences between the surgical success and failure groups, with a P value of 7.85e-08 and Cohen's d effect size of 0.77. CCM-defined EZ brain network can also distinguish the successful and failed surgeries considering clinical covariates (clinical centers, DRE types) with [Formula: see text]. Based on the brain network features, machine learning models were developed to predict the surgical outcomes. Among them, the SVM classifier with Gaussian kernel function and Bayesian optimization demonstrates the highest average accuracy of 84.48% by 5-fold cross-validation, further indicating that the CCM-defined EZ brain network is a reliable biomarker for predicting DRE surgical outcomes.