HCA-DAN: hierarchical class-aware domain adaptive network for gastric tumor segmentation in 3D CT images.

BACKGROUND: Accurate segmentation of gastric tumors from CT scans provides useful image information for guiding the diagnosis and treatment of gastric cancer. However, automated gastric tumor segmentation from 3D CT images faces several challenges. The large variation of anisotropic spatial resolution limits the ability of 3D convolutional neural networks (CNNs) to learn features from different views. The background texture of gastric tumor is complex, and its size, shape and intensity distribution are highly variable, which makes it more difficult for deep learning methods to capture the boundary. In particular, while multi-center datasets increase sample size and representation ability, they suffer from inter-center heterogeneity. METHODS: In this study, we propose a new cross-center 3D tumor segmentation method named Hierarchical Class-Aware Domain Adaptive Network (HCA-DAN), which includes a new 3D neural network that efficiently bridges an Anisotropic neural network and a Transformer (AsTr) for extracting multi-scale context features from the CT images with anisotropic resolution, and a hierarchical class-aware domain alignment (HCADA) module for adaptively aligning multi-scale context features across two domains by integrating a class attention map with class-specific information. We evaluate the proposed method on an in-house CT image dataset collected from four medical centers and validate its segmentation performance in both in-center and cross-center test scenarios. RESULTS: Our baseline segmentation network (i.e., AsTr) achieves best results compared to other 3D segmentation models, with a mean dice similarity coefficient (DSC) of 59.26%, 55.97%, 48.83% and 67.28% in four in-center test tasks, and with a DSC of 56.42%, 55.94%, 46.54% and 60.62% in four cross-center test tasks. In addition, the proposed cross-center segmentation network (i.e., HCA-DAN) obtains excellent results compared to other unsupervised domain adaptation methods, with a DSC of 58.36%, 56.72%, 49.25%, and 62.20% in four cross-center test tasks. CONCLUSIONS: Comprehensive experimental results demonstrate that the proposed method outperforms compared methods on this multi-center database and is promising for routine clinical workflows.

Decreased brain iron deposition based on quantitative susceptibility mapping correlates with reduced neurodevelopmental status in children with autism spectrum disorder.

To investigate potential correlations between the susceptibility values of certain brain regions and the severity of disease or neurodevelopmental status in children with autism spectrum disorder (ASD), 18 ASD children and 15 healthy controls (HCs) were recruited. The neurodevelopmental status was assessed by the Gesell Developmental Schedules (GDS) and the severity of the disease was evaluated by the Autism Behavior Checklist (ABC). Eleven brain regions were selected as regions of interest and the susceptibility values were measured by quantitative susceptibility mapping. To evaluate the diagnostic capacity of susceptibility values in distinguishing ASD and HC, the receiver operating characteristic (ROC) curve was computed. Pearson and Spearman partial correlation analysis were used to depict the correlations between the susceptibility values, the ABC scores, and the GDS scores in the ASD group. ROC curves showed that the susceptibility values of the left and right frontal white matter had a larger area under the curve in the ASD group. The susceptibility value of the right globus pallidus was positively correlated with the GDS-fine motor scale score. These findings indicated that the susceptibility value of the right globus pallidus might be a viable imaging biomarker for evaluating the neurodevelopmental status of ASD children.

Associations of quantitative susceptibility mapping with cortical atrophy and brain connectome in Alzheimer's disease: A multi-parametric study.

Aberrant susceptibility due to iron level abnormality and brain network disconnections are observed in Alzheimer's disease (AD), with disrupted iron homeostasis hypothesized to be linked to AD pathology and neuronal loss. However, whether associations exist between abnormal quantitative susceptibility mapping (QSM), brain atrophy, and altered brain connectome in AD remains unclear. Based on multi-parametric brain imaging data from 30 AD patients and 26 healthy controls enrolled at the China-Japan Friendship Hospital, we investigated the abnormality of the QSM signal and volumetric measure across 246 brain regions in AD patients. The structural and functional connectomes were constructed based on diffusion MRI tractography and functional connectivity, respectively. The network topology was quantified using graph theory analyses. We identified seven brain regions with both reduced cortical thickness and abnormal QSM (p < 0.05) in AD, including the right superior frontal gyrus, left superior temporal gyrus, right fusiform gyrus, left superior parietal lobule, right superior parietal lobule, left inferior parietal lobule, and left precuneus. Correlations between cortical thickness and network topology computed across patients in the AD group resulted in statistically significant correlations in five of these regions, with higher correlations in functional compared to structural topology. We computed the correlation between network topological metrics, QSM value and cortical thickness across regions at both individual and group-averaged levels, resulting in a measure we call spatial correlations. We found a decrease in the spatial correlation of QSM and the global efficiency of the structural network in AD patients at the individual level. These findings may provide insights into the complex relationships among QSM, brain atrophy, and brain connectome in AD.

White matter structural changes before and after microvascular decompression for hemifacial spasm.

Hemifacial spasm (HFS) is a syndrome characterized by involuntary contractions of the facial muscles innervated by the ipsilateral facial nerve. Currently, microvascular decompression (MVD) is an effective treatment for HFS. Diffusion weighted imaging (DWI) is a non-invasive advanced magnetic resonance technique that allows us to reconstruct white matter (WM) virtually based on water diffusion direction. This enables us to model the human brain as a complex network using graph theory. In our study, we recruited 32 patients with HFS and 32 healthy controls to analyze and compare the topological organization of whole-brain white matter networks between the groups. We also explored the potential relationships between altered topological properties and clinical outcomes. Compared to the HC group, the white matter network was disrupted in both preoperative and postoperative groups of HFS patients, mainly located in the somatomotor network, limbic network, and default network (All P < 0.05, FDR corrected). There was no significant difference between the preoperative and postoperative groups (P > 0.05, FDR corrected). There was a correlation between the altered topological properties and clinical outcomes in the postoperative group of patients (All P < 0.05, FDR corrected). Our findings indicate that in HFS, the white matter structural network was disrupted before and after MVD, and that these alterations in the postoperative group were correlated with the clinical outcomes. White matter alteration here described may subserve as potential biomarkers for HFS and may help us identify patients with HFS who can benefit from MVD and thus can help us make a proper surgical patient selection.

Immune-related lncRNAs signature and radiomics signature predict the prognosis and immune microenvironment of glioblastoma multiforme.

BACKGROUND: Glioblastoma multiforme (GBM) is the most common primary malignant brain tumor in adults. This study aimed to construct immune-related long non-coding RNAs (lncRNAs) signature and radiomics signature to probe the prognosis and immune infiltration of GBM patients. METHODS: We downloaded GBM RNA-seq data and clinical information from The Cancer Genome Atlas (TCGA) project database, and MRI data were obtained from The Cancer Imaging Archive (TCIA). Then, we conducted a cox regression analysis to establish the immune-related lncRNAs signature and radiomics signature. Afterward, we employed a gene set enrichment analysis (GSEA) to explore the biological processes and pathways. Besides, we used CIBERSORT to estimate the abundance of tumor-infiltrating immune cells (TIICs). Furthermore, we investigated the relationship between the immune-related lncRNAs signature, radiomics signature and immune checkpoint genes. Finally, we constructed a multifactors prognostic model and compared it with the clinical prognostic model. RESULTS: We identified four immune-related lncRNAs and two radiomics features, which show the ability to stratify patients into high-risk and low-risk groups with significantly different survival rates. The risk score curves and Kaplan-Meier curves confirmed that the immune-related lncRNAs signature and radiomics signature were a novel independent prognostic factor in GBM patients. The GSEA suggested that the immune-related lncRNAs signature were involved in L1 cell adhesion molecular (L1CAM) interactions and the radiomics signature were involved signaling by Robo receptors. Besides, the two signatures was associated with the infiltration of immune cells. Furthermore, they were linked with the expression of critical immune genes and could predict immunotherapy's clinical response. Finally, the area under the curve (AUC) (0.890,0.887) and C-index (0.737,0.817) of the multifactors prognostic model were greater than those of the clinical prognostic model in both the training and validation sets, indicated significantly improved discrimination. CONCLUSIONS: We identified the immune-related lncRNAs signature and tradiomics signature that can predict the outcomes, immune cell infiltration, and immunotherapy response in patients with GBM.

USBDAN: Unsupervised Scale-aware and Boundary-aware Domain Adaptive Network for Gastric Tumor Segmentation.

Accurate segmentation of gastric tumors from computed tomography (CT) images provides useful image information for guiding the diagnosis and treatment of gastric cancer. Researchers typically collect datasets from multiple medical centers to increase sample size and representation, but this raises the issue of data heterogeneity. To this end, we propose a new cross-center 3D tumor segmentation method named unsupervised scale-aware and boundary-aware domain adaptive network (USBDAN), which includes a new 3D neural network that efficiently bridges an Anisotropic neural network and a Transformer (AsTr) for extracting multi-scale features from the CT images with anisotropic resolution, and a scale-aware and boundary-aware domain alignment (SaBaDA) module for adaptively aligning multi-scale features between two domains and enhancing tumor boundary drawing based on location-related information drawn from each sample across all domains. We evaluate the proposed method on an in-house CT image dataset collected from four medical centers. Our results demonstrate that the proposed method outperforms several state-of-the-art methods.

Comparison of MRI radiomics-based machine learning survival models in predicting prognosis of glioblastoma multiforme.

Objective: To compare the performance of radiomics-based machine learning survival models in predicting the prognosis of glioblastoma multiforme (GBM) patients. Methods: 131 GBM patients were included in our study. The traditional Cox proportional-hazards (CoxPH) model and four machine learning models (SurvivalTree, Random survival forest (RSF), DeepSurv, DeepHit) were constructed, and the performance of the five models was evaluated using the C-index. Results: After the screening, 1792 radiomics features were obtained. Seven radiomics features with the strongest relationship with prognosis were obtained following the application of the least absolute shrinkage and selection operator (LASSO) regression. The CoxPH model demonstrated that age (HR = 1.576, p = 0.037), Karnofsky performance status (KPS) score (HR = 1.890, p = 0.006), radiomics risk score (HR = 3.497, p = 0.001), and radiomics risk level (HR = 1.572, p = 0.043) were associated with poorer prognosis. The DeepSurv model performed the best among the five models, obtaining C-index of 0.882 and 0.732 for the training and test set, respectively. The performances of the other four models were lower: CoxPH (0.663 training set / 0.635 test set), SurvivalTree (0.702/0.655), RSF (0.735/0.667), DeepHit (0.608/0.560). Conclusion: This study confirmed the superior performance of deep learning algorithms based on radiomics relative to the traditional method in predicting the overall survival of GBM patients; specifically, the DeepSurv model showed the best predictive ability.

Evaluation of whole-brain oxygen metabolism in Alzheimer's disease using QSM and quantitative BOLD.

OBJECTIVE: The objective of this study was to evaluate the whole-brain pattern of oxygen extraction fraction (OEF), cerebral blood flow (CBF), and cerebral metabolic rate of oxygen consumption (CMRO2) perturbation in Alzheimer's disease (AD) and investigate the relationship between regional cerebral oxygen metabolism and global cognition. METHODS: Twenty-six AD patients and 25 age-matched healthy controls (HC) were prospectively recruited in this study. Mini-Mental State Examination (MMSE) was used to evaluate cognitive status. We applied the QQ-CCTV algorithm which combines quantitative susceptibility mapping and quantitative blood oxygen level-dependent models (QQ) for OEF calculation. CBF map was computed from arterial spin labeling and CMRO2 was generated based on Fick's principle. Whole-brain and regional OEF, CBF, and CMRO2 analyses were performed. The associations between these measures in substructures of deep brain gray matter and MMSE scores were assessed. RESULTS: Whole brain voxel-wise analysis showed that CBF and CMRO2 values significantly decreased in AD predominantly in the bilateral angular gyrus, precuneus gyrus and parieto-temporal regions. Regional analysis showed that CBF value decreased in the bilateral caudal hippocampus and left rostral hippocampus and CMRO2 value decreased in left caudal and rostral hippocampus in AD patients. Considering all subjects in the AD and HC groups combined, the mean CBF and CMRO2 values in the bilateral hippocampus positively correlated with the MMSE score. CONCLUSION: CMRO2 mapping with the QQ-CCTV method - which is readily available in MR systems for clinical practice - can be a potential biomarker for AD. In addition, CMRO2 in the hippocampus may be a useful tool for monitoring cognitive impairment.

Altered coupling of resting-state cerebral blood flow and functional connectivity in Meige syndrome.

Introduction: Meige syndrome (MS) is an adult-onset segmental dystonia disease, mainly manifested as blepharospasm and involuntary movement caused by dystonic dysfunction of the oromandibular muscles. The changes of brain activity, perfusion and neurovascular coupling in patients with Meige syndrome are hitherto unknown. Methods: Twenty-five MS patients and thirty age- and sex-matched healthy controls (HC) were prospectively recruited in this study. All the participants underwent resting-state arterial spin labeling and blood oxygen level-dependent examinations on a 3.0 T MR scanner. The measurement of neurovascular coupling was calculated using cerebral blood flow (CBF)-functional connectivity strength (FCS) correlations across the voxels of whole gray matter. Also, voxel-wised analyses of CBF, FCS, and CBF/FCS ratio images between MS and HC were conducted. Additionally, CBF and FCS values were compared between these two groups in selected motion-related brain regions. Results: MS patients showed increased whole gray matter CBF-FCS coupling relative to HC (t = 2.262, p = 0.028). In addition, MS patients showed significantly increased CBF value in middle frontal gyrus and bilateral precentral gyrus. Conclusion: The abnormal elevated neurovascular coupling of MS may indicate a compensated blood perfusion in motor-related brain regions and reorganized the balance between neuronal activity and brain blood supply. Our results provide a new insight into the neural mechanism underlying MS from the perspective of neurovascular coupling and cerebral perfusion.

Spectrum Sharing Based on a Bertrand Game in Cognitive Radio Sensor Networks.

In the study of power control and allocation based on pricing, the utility of secondary users is usually studied from the perspective of the signal to noise ratio. The study of secondary user utility from the perspective of communication demand can not only promote the secondary users to meet the maximum communication needs, but also to maximize the utilization of spectrum resources, however, research in this area is lacking, so from the viewpoint of meeting the demand of network communication, this paper designs a two stage model to solve spectrum leasing and allocation problem in cognitive radio sensor networks (CRSNs). In the first stage, the secondary base station collects the secondary network communication requirements, and rents spectrum resources from several primary base stations using the Bertrand game to model the transaction behavior of the primary base station and secondary base station. The second stage, the subcarriers and power allocation problem of secondary base stations is defined as a nonlinear programming problem to be solved based on Nash bargaining. The simulation results show that the proposed model can satisfy the communication requirements of each user in a fair and efficient way compared to other spectrum sharing schemes.