Deep learning based CETSA feature prediction cross multiple cell lines with latent space representation.

Mass spectrometry-coupled cellular thermal shift assay (MS-CETSA), a biophysical principle-based technique that measures the thermal stability of proteins at the proteome level inside the cell, has contributed significantly to the understanding of drug mechanisms of action and the dissection of protein interaction dynamics in different cellular states. One of the barriers to the wide applications of MS-CETSA is that MS-CETSA experiments must be performed on the specific cell lines of interest, which is typically time-consuming and costly in terms of labeling reagents and mass spectrometry time. In this study, we aim to predict CETSA features in various cell lines by introducing a computational framework called CycleDNN based on deep neural network technology. For a given set of n cell lines, CycleDNN comprises n auto-encoders. Each auto-encoder includes an encoder to convert CETSA features from one cell line into latent features in a latent space [Formula: see text]. It also features a decoder that transforms the latent features back into CETSA features for another cell line. In such a way, the proposed CycleDNN creates a cyclic prediction of CETSA features across different cell lines. The prediction loss, cycle-consistency loss, and latent space regularization loss are used to guide the model training. Experimental results on a public CETSA dataset demonstrate the effectiveness of our proposed approach. Furthermore, we confirm the validity of the predicted MS-CETSA data from our proposed CycleDNN through validation in protein-protein interaction prediction.

Establishment and Validation of Novel Prognostic Subtypes in Hepatocellular Carcinoma Based on Bile Acid Metabolism Gene Signatures Using Bulk and Single-Cell RNA-Seq Data.

Hepatocellular carcinoma (HCC) is a highly detrimental cancer type and has limited therapeutic options, posing significant threats to human health. The development of HCC has been associated with a disorder in bile acid (BA) metabolism. In this study, we employed an integrative approach, combining various datasets and omics analyses, to comprehensively characterize the tumor microenvironment in HCC based on genes related to BA metabolism. Our analysis resulted in the classification of HCC samples into four subtypes (C1, C2a, C2b, and C3). Notably, subtype C2a, characterized by the highest bile acid metabolism score (BAMS), exhibited the highest survival probability. This subtype also demonstrated increased immune cell infiltration, lower cell cycle scores, reduced AFP levels, and a lower risk of metastasis compared to subtypes C1 and C3. Subtype C1 displayed poorer survival probability and elevated cell cycle scores. Importantly, the identified subtypes based on BAMS showed potential relevance to the gene expression of drug targets in currently approved drugs and those under clinical research. Genes encoding VEGFR (FLT4 and KDR) and MET were elevated in C2, while genes such as TGFBR1, TGFB1, ADORA3, SRC, BRAF, RET, FLT3, KIT, PDGFRA, and PDGFRB were elevated in C1. Additionally, FGFR2 and FGFR3, along with immune target genes including PDCD1 and CTLA4, were higher in C3. This suggests that subtypes C1, C2, and C3 might represent distinct potential candidates for TGFB1 inhibitors, VEGFR inhibitors, and immune checkpoint blockade treatments, respectively. Significantly, both bulk and single-cell transcriptome analyses unveiled a negative correlation between BA metabolism and cell cycle-related pathways. In vitro experiments further confirmed that the treatment of HCC cell lines with BA receptor agonist ursodeoxycholic acid led to the downregulation of the expression of cell cycle-related genes. Our findings suggest a plausible involvement of BA metabolism in liver carcinogenesis, potentially mediated through the regulation of tumor cell cycles and the immune microenvironment. This preliminary understanding lays the groundwork for future investigations to validate and elucidate the specific mechanisms underlying this potential association. Furthermore, this study provides a novel foundation for future precise molecular typing and the design of systemic clinical trials for HCC therapy.

Quality Control for Single Cell Analysis of High-plex Tissue Profiles using CyLinter.

Tumors are complex assemblies of cellular and acellular structures patterned on spatial scales from microns to centimeters. Study of these assemblies has advanced dramatically with the introduction of high-plex spatial profiling. Image-based profiling methods reveal the intensities and spatial distributions of 20-100 proteins at subcellular resolution in 103-107 cells per specimen. Despite extensive work on methods for extracting single-cell data from these images, all tissue images contain artefacts such as folds, debris, antibody aggregates, optical aberrations and image processing errors that arise from imperfections in specimen preparation, data acquisition, image assembly, and feature extraction. We show that these artefacts dramatically impact single-cell data analysis, obscuring meaningful biological interpretation. We describe an interactive quality control software tool, CyLinter, that identifies and removes data associated with imaging artefacts. CyLinter greatly improves single-cell analysis, especially for archival specimens sectioned many years prior to data collection, such as those from clinical trials.

Ecological factors associated with child sexual abuse among 15- to 17-year-old adolescents in mainland China: implications for intervention.

Background: Child sexual abuse is a major public health problem with adverse consequences for victims' physical, mental, and reproductive health. This cross-sectional study aimed to determine the prevalence of child sexual abuse and its associated factors among 15- to 17-year-old adolescents in mainland China. Methods: From September 8, 2019 to January 17, 2020, a total of 48,660 participants were recruited by 58 colleges and universities across the whole country to complete the self-administered, structured, online questionnaire. This analysis was restricted to 3,215 adolescents aged between 15 and 17 years in mainland China. Chi-square tests and multivariate Logistic regression analyses were performed to identify individual, relationship, and community factors associated with child sexual abuse. Results: The overall prevalence of child sexual abuse was 12.0%. More specifically, 13.0% of girls and 10.6% of boys reported that they were sexually abused prior to 18 years of age. At the individual level, being female, sexual minority identity, younger age, and higher levels of knowledge, skills and self-efficacy regarding condom use were significantly related to increased odds of reporting sexual abuse. At the relationship and community level, adolescents from disrupted families and those entering into a marriage, having casual sexual partners, and having first intercourse at a younger age were more likely to report sexual abuse. On the contrary, those who had never discussed sex-related topics with their family members at home and were offered school-based sexuality education later (vs. earlier) were less likely to report sexual abuse. Conclusion: Multilevel prevention programs and strategies, including targeting adolescents with high-risk characteristics, educating young children and their parents about child sexual abuse prevention and optimizing the involvement of parents, school, community, society and government in comprehensive sexuality education, should be taken to reduce child sexual abuse among 15- to 17-year-old adolescents.

Freezing of water and melting of ice: theoretical modeling at the nanoscale.

Freezing of water and melting of ice at the nanoscale play critical roles in science and technology fields, including aviation systems, infrastructures, and other broad spectrum of technologies. To cope with the icing challenge, nanoscale anti-icing surface technology has been developed. The freezing and melting temperatures can be tailored by manipulating the size (the radius of water or ice); however, it lacks systemic research. In this work, the size effect on the melting temperature of ice nanocrystals was first established, which considered the variation of bond energy and equivalent heat energy from the perspective of the force-heat equivalence energy density principle. Based on the heterogeneous nucleation mode and by further considering the size and temperature effects on the interface energy involved solid-liquid energy and liquid-vapor energy as well as the above developed melting temperature model, another model is established to accurately predict the freezing temperature of water nanodroplets. The parameters required by the two models established in this paper have a clear physical meaning and establish the quantitative relationships among freezing temperature, melting temperature, surface stress, interface energy, and other thermodynamic parameters. The agreement between model prediction and experimental simulation data confirms the validity and universality of the established models. The higher prediction accuracy of this work compared to the other theoretical models, due to the more detailed consideration and the reference point, captures the errors introduced by the experiment or simulation. This study contributes to a deeper understanding of the underlying mechanism of freezing of water and melting of ice nanocrystals and provides theoretical guidance for the design of cryopreservation systems and anti-icing systems for aviation.

Robust Detection, Segmentation, and Metrology of High Bandwidth Memory 3D Scans Using an Improved Semi-Supervised Deep Learning Approach.

Recent advancements in 3D deep learning have led to significant progress in improving accuracy and reducing processing time, with applications spanning various domains such as medical imaging, robotics, and autonomous vehicle navigation for identifying and segmenting different structures. In this study, we employ the latest developments in 3D semi-supervised learning to create cutting-edge models for the 3D object detection and segmentation of buried structures in high-resolution X-ray semiconductors scans. We illustrate our approach to locating the region of interest of the structures, their individual components, and their void defects. We showcase how semi-supervised learning is utilized to capitalize on the vast amounts of available unlabeled data to enhance both detection and segmentation performance. Additionally, we explore the benefit of contrastive learning in the data pre-selection step for our detection model and multi-scale Mean Teacher training paradigm in 3D semantic segmentation to achieve better performance compared with the state of the art. Our extensive experiments have shown that our method achieves competitive performance and is able to outperform by up to 16% on object detection and 7.8% on semantic segmentation. Additionally, our automated metrology package shows a mean error of less than 2 µm for key features such as Bond Line Thickness and pad misalignment.

A multiplex method for detection of SARS-CoV-2 variants based on MALDI-TOF mass spectrometry.

The recent outbreak of the coronavirus disease 2019 (COVID-19) pandemic and the continuous evolution of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have highlighted the significance of new detection methods for global monitoring and prevention. Although quantitative reverse transcription PCR (RT-qPCR), the current gold standard for diagnosis, performs excellently in genetic testing, its multiplexing capability is limited because of the signal crosstalk of various fluorophores. Herein, we present a highly efficient platform which combines 17-plex assays with matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS), enabling the targeting of 14 different mutation sites of the spike gene. Diagnosis using a set of 324 nasopharyngeal swabs or sputum clinical samples with SARS-CoV-2 MS method was identical to that with the RT-qPCR. The detection consistency of mutation sites was 97.9% (47/48) compared to Sanger sequencing without cross-reaction with other respiratory-related pathogens. Therefore, the MS method is highly potent to track and assess SARS-CoV-2 changes in a timely manner, thereby aiding the continuous response to viral variation and prevention of further transmission.

Rapid Detection of Predominant SARS-CoV-2 Variants Using Multiplex High-Resolution Melting Analysis.

Coronavirus disease 2019, caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), poses a considerable threat to global public health. This study developed and evaluated a rapid, low-cost, expandable, and sequencing-free high-resolution melting (HRM) assay for the direct detection of SARS-CoV-2 variants. A panel of 64 common bacterial and viral pathogens that can cause respiratory tract infections was employed to evaluate our method's specificity. Serial dilutions of viral isolates determined the sensitivity of the method. Finally, the assay's clinical performance was assessed using 324 clinical samples with potential SARS-CoV-2 infection. Multiplex HRM analysis accurately identified SARS-CoV-2 (as confirmed with parallel reverse transcription-quantitative PCR [qRT-PCR] tests), differentiating between mutations at each marker site within approximately 2 h. For each target, the limit of detection (LOD) was lower than 10 copies/reaction (the LOD of N, G142D, R158G, Y505H, V213G, G446S, S413R, F486V, and S704L was 7.38, 9.72, 9.96, 9.96, 9.50, 7.80, 9.33, 8.25, and 8.25 copies/reaction, respectively). No cross-reactivity occurred with organisms of the specificity testing panel. In terms of variant detection, our results had a 97.9% (47/48) rate of agreement with standard Sanger sequencing. The multiplex HRM assay therefore offers a rapid and simple procedure for detecting SARS-CoV-2 variants. IMPORTANCE In the face of the current severe situation of increasing SARS-CoV-2 variants, we developed an upgraded multiplex HRM method for the predominant SARS-CoV-2 variants based on our original research. This method not only could identify the variants but also could be utilized in subsequent detection of novel variants since the assay has great performance in terms of flexibility. In summary, the upgraded multiplex HRM assay is a rapid, reliable, and economical detection method, which could better screen prevalent virus strains, monitor the epidemic situation, and help to develop measures for the prevention and control of SARS-CoV-2.

Stereogenic-at-Cobalt(III) Complex Catalyzed Halocyclization of Alkynes: Enantioselective Access to Axially Chiral ortho-Halo-C2-indoles.

Here, we report an anionic stereogenic-at-cobalt(III) complex catalysis strategy for the enantioselective halocyclization of ortho-alkynylanilines using N-halosuccinimide (NXS) as the halogen source. This protocol provides a distinct atroposelective approach to access the axially chiral ortho-halo-C2-indole skeletons in excellent yields with good to high enantioselectivities (up to 99% yield, 99:1 er).

Insights into membrane association of the SMP domain of extended synaptotagmin.

The Synaptotagmin-like Mitochondrial-lipid-binding Protein (SMP) domain is a newly identified lipid transfer module present in proteins that regulate lipid homeostasis at membrane contact sites (MCSs). However, how the SMP domain associates with the membrane to extract and unload lipids is unclear. Here, we performed in vitro DNA brick-assisted lipid transfer assays and in silico molecular dynamics simulations to investigate the molecular basis of the membrane association by the SMP domain of extended synaptotagmin (E-Syt), which tethers the tubular endoplasmic reticulum (ER) to the plasma membrane (PM). We demonstrate that the SMP domain uses its tip region to recognize the extremely curved subdomain of tubular ER and the acidic-lipid-enriched PM for highly efficient lipid transfer. Supporting these findings, disruption of these mechanisms results in a defect in autophagosome biogenesis contributed by E-Syt. Our results suggest a model that provides a coherent picture of the action of the SMP domain at MCSs.

Electrodeposition of chitosan/graphene oxide conduit to enhance peripheral nerve regeneration.

Currently available commercial nerve guidance conduits have been applied in the repair of peripheral nerve defects. However, a conduit exhibiting good biocompatibility remains to be developed. In this work, a series of chitosan/graphene oxide (GO) films with concentrations of GO varying from 0-1 wt% (collectively referred to as CHGF-n) were prepared by an electrodeposition technique. The effects of CHGF-n on proliferation and adhesion abilities of Schwann cells were evaluated. The results showed that Schwann cells exhibited elongated spindle shapes and upregulated expression of nerve regeneration-related factors such as Krox20 (a key myelination factor), Zeb2 (essential for Schwann cell differentiation, myelination, and nerve repair), and transforming growth factor ß (a cytokine with regenerative functions). In addition, a nerve guidance conduit with a GO content of 0.25% (CHGFC-0.25) was implanted to repair a 10-mm sciatic nerve defect in rats. The results indicated improvements in sciatic functional index, electrophysiology, and sciatic nerve and gastrocnemius muscle histology compared with the CHGFC-0 group, and similar outcomes to the autograft group. In conclusion, we provide a candidate method for the repair of peripheral nerve defects using free-standing chitosan/GO nerve conduits produced by electrodeposition.

CoIn: Correlation Induced Clustering for Cognition of High Dimensional Bioinformatics Data.

Analysis of high dimensional biomedical data such as microarray gene expression data and mass spectrometry images, is crucial to provide better medical services including cancer subtyping, protein homology detection, etc. Clustering is a fundamental cognitive task which aims to group unlabeled data into multiple clusters based on their intrinsic similarities. However, for most clustering methods, including the most widely used K-means algorithm, all features of the high dimensional data are considered equally in relevance, which distorts the performance when clustering high-dimensional data where there exist many redundant variables and correlated variables. In this paper, we aim at addressing the problem of the high dimensional bioinformatics data clustering and propose a new correlation induced clustering, CoIn, to capture complex correlations among high dimensional data and guarantee the correlation consistency within each cluster. We evaluate the proposed method on a high dimensional mass spectrometry dataset of liver cancer tumor to explore the metabolic differences on tissues and discover the intra-tumor heterogeneity (ITH). By comparing the results of baselines and ours, it has been found that our method produces more explainable and understandable results for clinical analysis, which demonstrates the proposed clustering paradigm has the potential with application to knowledge discovery in high dimensional bioinformatics data.

Neutrophil extracellular traps: A novel target for the treatment of stroke.

Stroke is a threatening cerebrovascular disease caused by thrombus with high morbidity and mortality rates. Neutrophils are the first to be recruited in the brain after stroke, which aggravate brain injury through multiple mechanisms. Neutrophil extracellular traps (NETs), as a novel regulatory mechanism of neutrophils, can trap bacteria and secret antimicrobial molecules, thereby degrading pathogenic factors and killing bacteria. However, NETs also exacerbate certain non-infectious diseases by activating autoimmune or inflammatory responses. NETs have been found to play important roles in the pathological process of stroke in recent years. In this review, the mechanisms of NETs formation, the physiological roles of NETs, and the dynamic changes of NETs after stroke are summarized. NETs participate in stroke through various mechanisms. NETs promote the coagulation cascade and interact with platelets to induce thrombosis. tPA induces the degranulation of neutrophils to form NETs, leading to hemorrhagic transformation and thrombolytic resistance. NETs aggravate stroke by mediating inflammation, atherosclerosis and vascular injury. In addition, the regulation of NETs in stroke, the potential of NETs as biomarker and the treatment of stroke targeting NETs are discussed. The increasing evidences suggest that NETs may be a potential target for stroke treatment. Inhibition of NETs formation or promotion of NETs degradation plays protective effects in stroke. However, how to avoid the adverse effects of NETs-targeted therapy deserves further study. In summary, this review provides a reference for the pathogenesis, drug targets, biomarkers and drug development of NETs in stroke.

Efficient Perturbation Inference and Expandable Network for continual learning.

Although humans are capable of learning new tasks without forgetting previous ones, most neural networks fail to do so because learning new tasks could override the knowledge acquired from previous data. In this work, we alleviate this issue by proposing a novel Efficient Perturbation Inference and Expandable Network (EPIE-Net), which dynamically expands lightweight task-specific decoders for new classes and utilizes a mixed-label uncertainty strategy to improve the robustness. Moreover, we calculate the average probability of perturbed samples at inference, which can generally improve the performance of the model. Experimental results show that our method consistently outperforms other methods with fewer parameters in class incremental learning benchmarks. For example, on the CIFAR-100 10 steps setup, our method achieves an average accuracy of 76.33% and the last accuracy of 65.93% within only 3.46M average parameters.

LE-UDA: Label-Efficient Unsupervised Domain Adaptation for Medical Image Segmentation.

While deep learning methods hitherto have achieved considerable success in medical image segmentation, they are still hampered by two limitations: (i) reliance on large-scale well-labeled datasets, which are difficult to curate due to the expert-driven and time-consuming nature of pixel-level annotations in clinical practices, and (ii) failure to generalize from one domain to another, especially when the target domain is a different modality with severe domain shifts. Recent unsupervised domain adaptation (UDA) techniques leverage abundant labeled source data together with unlabeled target data to reduce the domain gap, but these methods degrade significantly with limited source annotations. In this study, we address this underexplored UDA problem, investigating a challenging but valuable realistic scenario, where the source domain not only exhibits domain shift w.r.t. the target domain but also suffers from label scarcity. In this regard, we propose a novel and generic framework called "Label-Efficient Unsupervised Domain Adaptation" (LE-UDA). In LE-UDA, we construct self-ensembling consistency for knowledge transfer between both domains, as well as a self-ensembling adversarial learning module to achieve better feature alignment for UDA. To assess the effectiveness of our method, we conduct extensive experiments on two different tasks for cross-modality segmentation between MRI and CT images. Experimental results demonstrate that the proposed LE-UDA can efficiently leverage limited source labels to improve cross-domain segmentation performance, outperforming state-of-the-art UDA approaches in the literature.

Self-supervised Assisted Active Learning for Skin Lesion Segmentation.

Label scarcity has been a long-standing issue for biomedical image segmentation, due to high annotation costs and professional requirements. Recently, active learning (AL) strategies strive to reduce annotation costs by querying a small portion of data for annotation, receiving much traction in the field of medical imaging. However, most of the existing AL methods have to initialize models with some randomly selected samples followed by active selection based on various criteria, such as uncertainty and diversity. Such random-start initialization methods inevitably introduce under-value redundant samples and unnecessary annotation costs. For the purpose of addressing the issue, we propose a novel self-supervised assisted active learning framework in the cold-start setting, in which the segmentation model is first warmed up with self-supervised learning (SSL), and then SSL features are used for sample selection via latent feature clustering without accessing labels. We assess our proposed methodology on skin lesions segmentation task. Extensive experiments demonstrate that our approach is capable of achieving promising performance with substantial improvements over existing baselines. Clinical Relevance- The proposed method can smartly select samples to annotate without requiring labels for model initialization, which can save annotation costs in clinical practice.

CETSA Feature Based Clustering for Protein Outlier Discovery by Protein-to-Protein Interaction Prediction.

The Cellular Thermal Shift Assay (CETSA) is a biophysical assay based on the principle of ligand-induced thermal stabilization of target proteins. This technology has revolutionized cell-based target engagement studies and has been used as guidance for drug design. Although many ap-plications of CETSA data have been explored, the correlations between CETSA data and protein-protein interactions (PPI) have barely been touched. In this study, we conduct the first exploration study applying CETSA data for PPI prediction. We use a machine learning method, Decision Tree, to predict PPI scores using proteins' CETSA features. It shows promising results that the predicted PPI scores closely match the ground-truth PPI scores. Furthermore, for a small number of protein pairs, whose PPI score predictions mismatch the ground truth, we use iterative clustering strategy to gradually reduce the number of these pairs. At the end of iterative clustering, the remaining protein pairs may have some unusual properties and are of scientific value for further biological investigation. Our study has demonstrated that PPI is a brand-new application of CETSA data. At the same time, it also manifests that CETSA data can be used as a new data source for PPI exploration study.

CycleDNN - A Novel Deep Neural Network Model for CETSA Feature Prediction cross Cell Lines.

Cellular Thermal Shift Assay (CETSA) has been widely used in drug discovery, cancer cell biology, immunology, etc. One of the barriers for CETSA applications is that CETSA experiments have to be conducted on various cell lines, which is extremely time-consuming and costly. In this study, we make an effort to explore the translation of CETSA features cross cell lines, i.e., known CETSA feature of a given protein in one cell line, can we automatically predict the CETSA feature of this protein in another cell line, and vice versa? Inspired by pix2pix and CycleGAN, which perform well on image-to-image translation cross various domains in computer vision, we propose a novel deep neural network model called CycleDNN for CETSA feature translation cross cell lines. Given cell lines A and B, the proposed CycleDNN consists of two auto-encoders, the first one encodes the CETSA feature from cell line A into Z in the latent space [Formula: see text], then decodes Z into the CETSA feature in cell line B., Similarly, the second one translates the CETSA feature from cell line B to cell line A through the latent space [Formula: see text]. In such a way, the two auto-encoders form a cyclic feature translation between cell lines. The reconstructed loss, cycle-consistency loss, and latent vector regularization loss are used to guide the training of the model. The experimental results on a public CETSA dataset demonstrate the effectiveness of the proposed approach.

ADAN: An Adversarial Domain Adaptation Neural Network for Early Gastric Cancer Prediction.

Gastric cancer is a highly prevalent cancer world-wide. Accurate diagnosis of Early Gastric Cancer (EGC) is of great significance to improve the treatment and survival rate of patients. However, EGC and gastric ulcers have similar en-doscopic image characteristics, resulting in a high misdiagnosis rate. Most existing deep learning and machine learning models for EGC recognition have the disadvantages of cumbersome pre-processing steps and high leakage ratios. To address the above challenges, we propose an end-to-end Adversarial Do-main Adaptation Neural network (ADAN) for EGC prediction on endoscopic images. ADAN network consists of a source domain feature extractor, a source domain classifier, two target domain feature extractors, a target domain classifier, and a domain discriminator. A source domain feature extractor is designed to train the model on public gastrointestinal datasets, which effectively solves the problem of insufficient training data. In addition, an adaptive source-target domain mapping classifier is added to each target domain feature extractor for automatically adjusting the number of classification categories in the target domain. Experimental results show that the proposed ADAN network is superior to the most advanced methods and can accurately predict EGC in clinical practice. Clinical relevance-In this study, the EGC diagnosis model based on the adversarial domain adaptive construction will be more applicable to the real clinical scenario, with higher accuracy and sensitivity and assist the endoscopist to make more accurate diagnosis for EGC and reduce the workload.

Residual Channel Attention Network for Brain Glioma Segmentation.

A glioma is a malignant brain tumor that seriously affects cognitive functions and lowers patients' life quality. Segmentation of brain glioma is challenging because of inter-class ambiguities in tumor regions. Recently, deep learning approaches have achieved outstanding performance in the automatic segmentation of brain glioma. However, existing al-gorithms fail to exploit channel-wise feature interdependence to select semantic attributes for glioma segmentation. In this study, we implement a novel deep neural network that integrates residual channel attention modules to calibrate intermediate features for glioma segmentation. The proposed channel at-tention mechanism adaptively weights feature channel-wise to optimize the latent representation of gliomas. We evaluate our method on the established dataset BraTS2017. Experimental results indicate the superiority of our method. Clinical relevance - While existing glioma segmentation approaches do not leverage channel-wise feature dependence for feature selection our method can generate segmentation masks with higher accuracies and provide more insights on graphic patterns in brain MRI images for further clinical reference.