Search

Schizophrenia is a severe psychiatric disease while its etiology and effective treatment are not completely clear. A rat model of schizophrenia was previously established by transfecting EGR3 gene into the hippocampus of rats. This study aimed to investigate the behavioral and cerebral alterations of the schizophrenic model rats and the risperidone effects. Twenty-six rats were divided into 3 groups: schizophrenia model group (E group), risperidone treatment group (T group), and healthy control group (H group). Morris water maze and open field test were used as behavioral tests, resting-state functional magnetic resonance imaging (fMRI) was performed after EGR3 gene transfection and risperidone therapy. Graph analyses were used for examining cerebral alterations of the rats. Behavioral tests demonstrated reduced spatial working memory and exploring unfamiliar space ability in schizophrenic model rats. Graph analyses revealed reduced regional architectures in the olfactory bulb, nucleus accumbens, and pineal gland in group E compared to group H (p

Magnetic particle imaging is a new medical imaging modality which is based on the non-linear response of magnetic nanoparticles. The reconstruction task is an inverse problem and ill-posed in nature. To overcome the problem, we propose to use the least absolute shrinkage and selection operator (LASSO) regularization model. In order to reach a good result with a short reconstruction time, we use the truncated system matrix and the truncated measurement based on two threshold setting methods for reconstruction research. In this paper, we study the reconstruction quality of different threshold values and different regularization parameter values. We compare the reconstruction performance of the proposed model with the Tikhonov model from visualization and performance indicators. The conducted study illustrated that the proposed method yields significantly higher reconstruction quality than the state-of-the-art reconstruction method based on Tikhonov model.

Stroke is a serious manifestation of various cerebrovascular diseases and one of the most dangerous diseases in the world today. Volume quantification and location detection of chronic stroke lesions provide vital biomarkers for stroke rehabilitation. Recently, deep learning has seen a rapid growth, with a great potential in segmenting medical images. In this work, unlike most deep learning-based segmentation methods utilizing only magnetic resonance (MR) images as the input, we propose and validate a novel stroke lesion segmentation approach named multi-inputs UNet (MI-UNet) that incorporates brain parcellation information, including gray matter (GM), white matter (WM) and lateral ventricle (LV). The brain parcellation is obtained from 3D diffeomorphic registration and is concatenated with the original MR image to form two-channel inputs to the subsequent MI-UNet. Effectiveness of the proposed pipeline is validated using a dataset consisting of 229 T1-weighted MR images. Experiments are conducted via a five-fold cross-validation. The proposed MI-UNet performed significantly better than UNet in both 2D and 3D settings. Our best results obtained by 3D MI-UNet has superior segmentation performance, as measured by the Dice score, Hausdorff distance, average symmetric surface distance, as well as precision, over other state-of-the-art methods.

Wilson's disease (WD) is an inherited autosomal recessive disorder of copper metabolism, and its neurological and neuropsychiatric manifestations are associated with copper accumulation in brain. A few neuroimaging studies have shown that gray matter atrophy in WD affects both subcortical structures and cortex. This study aims to quantitatively evaluate the morphometric brain abnormalities in patients with WD in terms of whole brain volume and cortical thickness and their associations with clinical severity of WD. Thirty patients clinically diagnosed as WD with neurological manifestations and 25 healthy controls (HC) were recruited. 3D T1-weighted images were segmented into 276 whole-brain regions of interest (ROIs) and 68 cortical ROIs. WD-vs-HC group comparisons were then conducted for each ROI. The associations between those morphometric measurements and the Global Assessment Scale (GAS) score for WD were analyzed. Compared with HC, significant WD-related volumetric decreases were found in the bilateral subcortical nuclei (putamen, globus pallidus, caudate nucleus, substantia nigra, red nucleus and thalamus), diffuse white matter and several gray matter regions. WD patients showed reduced cortical thickness in the left precentral gyrus and the left insula. Further, the volumes of the right globus pallidus, bilateral putamen, right external capsule and left superior longitudinal fasciculus were negatively correlated with GAS. Our results indicated that significant WD-related morphometric abnormalities were quantified in terms of whole-brain volumes and cortical thicknesses, some of which correlated significantly to the clinical severity of WD. Those morphometrics may provide a potentially effective biomarker of WD.

Chronic graft-versus-host disease (cGVHD) is major cause of morbidity and mortality following allogeneic hematopoietic cell transplantation (HCT). Ixazomib is an oral, second-generation, proteasome inhibitor that has been shown in preclinical models to prevent GVHD. We conducted a phase I/II trial in 57 patients to evaluate the safety and efficacy of ixazomib administration for cGVHD prophylaxis in patients undergoing allogeneic HCT. Oral ixazomib was administered on a weekly basis for a total of 4 doses, beginning days +60 through +90, to recipients of matched related donor (MRD, n = 25) or matched unrelated donor (MUD, n = 26) allogeneic HCT in phase II portion of the study, once the recommended phase II dose of 4 mg was identified in phase I (n = 6). All patients received peripheral blood graft and standard GVHD prophylaxis of tacrolimus and methotrexate. Ixazomib administration was safe and well tolerated, with thrombocytopenia, leukopenia, gastrointestinal complaints, and fatigue the most common adverse events (>10%). In phase II (n = 51), the cumulative incidence of cGVHD at 1 year was 36% (95% confidence interval [CI], 19% to 54%) in the MRD cohort and 39% (95% CI, 21% to 56%) in the MUD cohort. One-year cumulative incidence of nonrelapse mortality (NRM) and relapse was 0% and 20% (95% CI, 8% to 36%) in the MRD cohort, respectively. In the MUD cohort, the respective NRM and relapse rates were 4% (0% to 16%) and 34% (17% to 52%). The outcomes on the study were compared post hoc with contemporaneous matched Center for International Blood and Marrow Transplant Research (CIBMTR) controls. This post hoc analysis showed no significant improvement in cGVHD rates in both the MRD (hazard ratio [HR] = 0.85, P = .64) or MUD cohorts (HR = 0.68, P = .26) on the study compared with CIBMTR controls. B cell activating factor plasma levels were significantly higher after ixazomib dosing in those who remained cGVHD free compared with those developed cGVHD. This study shows that the novel strategy of short-course oral ixazomib following allogeneic HCT is safe but did not demonstrate significant improvement in cGVHD incidence in recipients of MRD and MUD transplantation compared with matched CIBMTR controls. This study is registered at www.clinicaltrials.gov as NCT02250300.

Automated infection measurement and COVID-19 diagnosis based on Chest X-ray (CXR) imaging is important for faster examination, where infection segmentation is an essential step for assessment and quantification. However, due to the heterogeneity of X-ray imaging and the difficulty of annotating infected regions precisely, learning automated infection segmentation on CXRs remains a challenging task. We propose a novel approach, called DRR4Covid, to learn COVID-19 infection segmentation on CXRs from digitally reconstructed radiographs (DRRs). DRR4Covid consists of an infection-aware DRR generator, a segmentation network, and a domain adaptation module. Given a labeled Computed Tomography scan, the infection-aware DRR generator can produce infection-aware DRRs with pixel-level annotations of infected regions for training the segmentation network. The domain adaptation module is designed to enable the segmentation network trained on DRRs to generalize to CXRs. The statistical analyses made on experiment results have indicated that our infection-aware DRRs are significantly better than standard DRRs in learning COVID-19 infection segmentation (p

In this paper, we proposed an efficient approach for large deformation diffeomorphic metric mapping (LDDMM) for brain images by utilizing GPU-based parallel computing and a mixture automatic step size estimation method for gradient descent (MAS-GD). We systematically evaluated the proposed approach in terms of two matching cost functions, including the Sum of Squared Differences (SSD) and the Cross-Correlation (CC). The registration accuracy and computational efficiency on two datasets inducing respective 120 and 1,560 registration maps were evaluated and compared between CPU-based LDDMM-SSD and GPU-based LDDMM-SSD both utilizing backtracking line search for gradient descent (BLS-GD), GPU-based LDDMM (BLS-GD) and GPU-based LDDMM (MAS-GD) with each of the two matching cost functions being used. In addition, we compared our GPU-based LDDMM-CC (MAS-GD) with another widely-used state-of-the-art image registration algorithm, the symmetric diffeomorphic image registration with CC (SyN-CC). The GPU-based LDDMM-SSD was about 94 times faster than the CPU-based version (8.78 mins versus 828.35 mins) without sacrificing the Dice accuracy (0.8608 versus 0.8609). The computational time of LDDMM with MAS-GD for SSD and CC were shorter than that of LDDMM with BLS-GD (5.29 mins versus 8.78 mins for SSD and 6.69 mins versus 65.87 mins for CC), and the corresponding Dice scores were higher, especially for CC (0.8672 versus 0.8633). Compared with SyN-CC, the proposed algorithm, GPU-based LDDMM-CC (MAS-GD) had a higher registration accuracy (0.8672 versus 0.8612 and 0.7585 versus 0.7537 for the two datasets) and less computational time (6.80 mins versus 25.97 mins and 6.58 mins versus 26.23 mins for the two datasets).

Carbon ion radiation therapy (CIRT) is the most advanced radiation therapy (RT) available and offers new opportunities to improve cancer treatment and research. CIRT has a unique physical and biological advantage that allow them to kill tumor cells more accurately and intensively. So far, CIRT has been used in almost all types of malignant tumors, and showed good feasibility, safety and acceptable toxicity, indicating that CIRT has a wide range of development and application prospects. In addition, in order to improve the biological effect of CIRT, scientists are also trying to investigate related sensitizing agents to enhance the killing ability of tumor cells, which has attracted extensive attention. In this review, we tried to systematically review the rationale, advantages and problems, the clinical applications and the sensitizing agents of the CIRT. At the same time, the prospects of the CIRT in were prospected. We hope that this review will help researchers interested in CIRT, sensitizing agents, and radiotherapy to understand their magic more systematically and faster, and provide data reference and support for bioanalysis, clinical medicine, radiotherapy, heavy ion therapy, and nanoparticle diagnostics.

Background: Previous first-episode schizophrenia (FES) studies have reported abnormalities in the volume and mid-sagittal size of the corpus callosum (CC), but findings have been inconsistent. Besides, the CC shape has rarely been analyzed in FES. Therefore, in this study, we investigated FES-related CC shape abnormalities using 198 participants [92 FES patients and 106 healthy controls (HCs)].Methods: We conducted statistical shape analysis of the mid-sagittal CC curve in a large deformation diffeomorphic metric mapping framework. The CC was divided into the genu, body, and splenium (gCC, bCC, and sCC) to target the key CC sub-regions affected by the FES pathology. Gender effects have been investigated.Results: There were significant area differences between FES and HC in the entire CC and gCC but not in bCC nor sCC. In terms of the localized shape morphometrics, significant region-specific shape inward-deformations were detected in the superior portion of gCC and the anterosuperior portion of bCC in FES. These global area and local shape morphometric abnormalities were restricted to female FES but not male FES.Conclusions: gCC was significantly affected in the neuropathology of FES and this finding was specific to female FES. This study suggests that gCC may be a key sub-region that is vulnerable to the neuropathology of FES, specifically in female patients. The morphometrics of gCC may serve as novel and efficient biomarkers for screening female FES patients.

Artificial intelligence (AI) for medical imaging is a technology with great potential. An in-depth understanding of the principles and applications of magnetic resonance imaging (MRI), machine learning (ML), and deep learning (DL) is fundamental for developing AI-based algorithms that can meet the requirements of clinical diagnosis and have excellent quality and efficiency. Moreover, a more comprehensive understanding of applications and opportunities would help to implement AI-based methods in an ethical and sustainable manner. This review first summarizes recent research advances in ML and DL techniques for classifying human brain magnetic resonance images. Then, the application of ML and DL methods to six typical neurological and psychiatric diseases is summarized, including Alzheimer’s disease (AD), Parkinson’s disease (PD), major depressive disorder (MDD), schizophrenia (SCZ), attention-deficit/hyperactivity disorder (ADHD), and autism spectrum disorder (ASD). Finally, the limitations of the existing research are discussed, and possible future research directions are proposed.

Objectives To investigate the potential for pulpal regeneration via autologous transplantation of deciduous tooth pulp into immature necrotic permanent teeth using an experimental dog model. Methods Experimental apical periodontitis was induced in 60 teeth of six Beagle dogs. Following canal disinfection and pulpotomy, autologous deciduous pulp tissue was transplanted into the root canals (n = 30); as controls, contralateral teeth were treated in accordance with the recommendations of the American Association of Endodontists. Radiographic examinations were performed immediately before transplant, as well as 3 and 6 months after transplant. At the 6-month examination, root samples were collected and histological and immunohistochemical analyses were used to examine tissue regeneration. Results Radiographic analysis showed no significant differences in most histopathological parameters examined; however, apical diameter reduction was greater in the experimental group. Histological and immunohistochemical analyses showed that the canal walls of the experimental group had newly formed dentin-like tissue with dentinal tubules, while the control group had cementum-like deposits along the canal wall and apical foramina. Conclusions Autologous transplantation may be useful for regeneration of dental pulp in necrotic young permanent teeth.

Anomalous basal ganglia morphology may contribute to deficient motor response control in children with attention-deficit/hyperactivity disorder (ADHD). This study expands upon recent evidence of sex differences in subcortical morphology and motor response control deficits among children with ADHD to examine basal ganglia volume and shape in relation to motor response control. Participants included 8–12 year-old children with ADHD (n = 52, 21 girls) and typically developing (TD) controls (n = 45, 19 girls). High resolution T1-weighted 3D MPRAGE images covering the whole brain were acquired for all participants on a 3 T scanner. Participants performed two computer-based go/no-go tasks that differed in the extent to which working memory was necessary to guide response selection. Shape-based morphometric analyses were performed in addition to traditional volumetric comparisons and correlations with measures of motor response control were examined. Boys with ADHD consistently demonstrated increased commission error rate and response variability, regardless of task demands, suggesting broad response control deficits. In contrast, response control deficits among girls with ADHD varied depending on task demands and performance measures. Volumetric reductions and inward deformation (compression) on the dorsal surface of the globus pallidus and within subregions of the putamen receiving projections from limbic, executive and motor cortices were observed in boys, but not girls, with ADHD relative to TD children. Mediation analyses revealed that putamen and globus pallidus volumes mediated the relationship between diagnosis and commission error rate. Furthermore, reduced volumes of these structures and localized inward deformation within executive and motor circuits correlated with poorer response control, particularly under conditions of increased cognitive load. These findings suggest that anomalous basal ganglia morphology is related to impaired motor response control among boys with ADHD.

Background. Subcortical infarcts can result in verbal memory impairment, but the potential underlying mechanisms remain unknown. Objective. We investigated the spatiotemporal deterioration patterns of brain structures in patients with subcortical infarction and identified the regions that contributed to verbal memory impairment. Methods. Cognitive assessment and structural magnetic resonance imaging were performed 1, 4, and 12 weeks after stroke onset in 28 left-hemisphere and 22 right-hemisphere stroke patients with subcortical infarction. Whole-brain volumetric analysis combined with a further-refined shape analysis was conducted to analyze longitudinal morphometric changes in brain structures and their relationship to verbal memory performance. Results. Between weeks 1 and 12, significant volume decreases in the ipsilesional basal ganglia, inferior white matter, and thalamus were found in the left-hemisphere stroke group. Among those 3 structures, only the change rate of the thalamus volume was significantly correlated with that in immediate recall. For the right-hemisphere stroke group, only the ipsilesional basal ganglia survived the week 1 to week 12 group comparison, but its change rate was not significantly correlated with the verbal memory change rate. Shape analysis of the thalamus revealed atrophies of the ipsilesional thalamic subregions connected to the prefrontal, temporal, and premotor cortices in the left-hemisphere stroke group and positive correlations between the rates of those atrophies and the change rate in immediate recall. Conclusions. Secondary damage to the thalamus, especially to the left subregions connected to specific cortices, may be associated with early verbal memory impairment following an acute subcortical infarct.

Background Morphology builds Wilson's disease's clincal basis. Objectives To detect and quantify regional morphometric abnormalities, in terms of both volume and shape, in patients with Wilson's disease. Methods Twenty-seven Wilson's disease patients and 24 healthy controls were enrolled. Specific brain structures, including the bilateral caudate, putamen, globus pallidus, thalamus, amygdala, hippocampus, red nucleus, and substantia nigra (SN), were automatically extracted from each participant's T1 -weighted image. Volume abnormalities and correlations with the modified Young scale were investigated. Furthermore, vertex-based shape analysis was performed to explore region-specific morphometric abnormalities. Results Significant global volume atrophy and local shape abnormalities were detected and quantified in the bilateral caudate, putamen, globus pallidus, thalamus, amygdala, red nucleus, and SN. Morphometric abnormalities of the caudate, putamen, and thalamus were strong, whereas those of the globus pallidus, amygdala, red nucleus, and SN were weaker. No hippocampal abnormalities were observed. The modified Young scale was found to correlate significantly with the volumes of the bilateral putamen and the right globus pallidus. Shape analysis revealed subregion-specific atrophy of the bilateral caudate and putamen. They were concentrated in the subregions that project to the limbic and executive cortices. Significant region-specific atrophy was also detected in the bilateral thalamic subregions that project to the primary motor, sensory, and premotor cortices. Conclusions We found significant morphometric abnormalities of specific structures of interest in patients with Wilson's disease, both globally and locally. These morphometric abnormalities may serve as useful imaging biomarkers for Wilson's disease. © 2019 International Parkinson and Movement Disorder Society.

White matter hyperintensity (WMH) is associated with various aging and neurodegenerative diseases. In this paper, we proposed and validated a fully automatic system which integrates classical image processing and deep neural network for segmenting WHM from fluid attenuation inversion recovery (FLAIR) and T1 magnetic resonance (MR) images. In this system, a novel skip connection U-net (SC U-net) was proposed. In addition, an atlas-based method was introduced in the preprocessing stage to remove non-brain tissues (namely skull-stripping) and thus to improve the segmentation accuracy. Effectiveness of the proposed system was validated on a dataset of 60 paired images based on cross-scanner validation. Our experimental results revealed the effectiveness of the skull-stripping strategy. More importantly, compared to two existing state-of-the-art methods for segmenting WHM, including a U-net-like method and another deep learning method, the proposed SC U-net had a faster convergence, a lower loss and a higher segmentation accuracy. Both quantitative and qualitative analyses (via visual examinations) revealed the superior performance of our proposed SC U-net. The mean dice score of the proposed SC U-net was 78.36% which was much higher than those of a U-net-like method (74.99%) and an alternative deep learning method (74.80%). The software environment and model of the proposed system were made publicly accessible at Dockerhub.

Fundus images of poor quality may seriously influence clinic judgments. Existing fundus image quality enhancement (FIQE) approaches mainly make use of general image features but no prior domain knowledge. In this paper, we proposed and validated an efficient FIQE method with a prior constraint, named Efficient Prior Contrastive unpaired Generative Adversarial Network (EPC-GAN). Inspired by the contrastive unpaired translation framework, we emphasized local features during the enhancing process via contrastive patchwise samples. Moreover, to utilize high-level features in the fundus domain (such as vessels, optic disc/cup, and even lesions), we designed a fundus prior loss to avoid information modification and over-enhancement. Besides, we presented an efficient network architecture to overcome the high consumption in terms of both time and GPU-memory. Through both qualitative and quantitative experiments on a public dataset EyeQ, we demonstrated the superior performance of our proposed method.

Precise quantification of the corneal nerve plexus morphology is of great importance in diagnosing peripheral diabetic neuropathy and assessing the progression of various eye-related systemic diseases, wherein segmentation of corneal nerves is an essential component. In this paper, we proposed and validated a novel pipeline for corneal nerve segmentation, comprising corneal confocal microscopy (CCM) image synthesis, image quality enhancement and nerve segmentation. Our goal was to address three major problems existing in most CCM datasets, namely inaccurate annotations, non-uniform illumination and contrast variations. In our synthesis and enhancement steps, we employed multilayer and patchwise contrastive learning based Generative Adversarial Network (GAN) frameworks, which took full advantage of multi-scale local features. Through both qualitative and quantitative experiments on two publicly available CCM datasets, our pipeline has achieved overwhelming enhancement performance compared to several state-of-the-art methods. Moreover, the segmentation results showed that models trained on our synthetic images performed much better than those trained on a real CCM dataset, which clearly identified the effectiveness of our synthesis method. Overall, our proposed pipeline can achieve satisfactory segmentation performance for poor-quality CCM images without using any manual labels and can effectively enhance those images.

Magnetic particle imaging (MPI) is a novel non-invasive molecular imaging technology that images the distribution of superparamagnetic iron oxide nanoparticles (SPIONs). It is not affected by imaging depth, with high sensitivity, high resolution, and no radiation. The MPI reconstruction with high precision and high quality is of enormous practical importance, and many studies have been conducted to improve the reconstruction accuracy and quality. MPI reconstruction based on the system matrix (SM) is an important part of MPI reconstruction. In this review, the principle of MPI, current construction methods of SM and the theory of SM-based MPI are discussed. For SM-based approaches, MPI reconstruction mainly has the following problems: the reconstruction problem is an inverse and ill-posed problem, the complex background signals seriously affect the reconstruction results, the field of view cannot cover the entire object, and the available 3D datasets are of relatively large volume. In this review, we compared and grouped different studies on the above issues, including SM-based MPI reconstruction based on the state-of-the-art Tikhonov regularization, SM-based MPI reconstruction based on the improved methods, SM-based MPI reconstruction methods to subtract the background signal, SM-based MPI reconstruction approaches to expand the spatial coverage, and matrix transformations to accelerate SM-based MPI reconstruction. In addition, the current phantoms and performance indicators used for SM-based reconstruction are listed. Finally, certain research suggestions for MPI reconstruction are proposed, expecting that this review will provide a certain reference for researchers in MPI reconstruction and will promote the future applications of MPI in clinical medicine.

Computed tomography (CT) images are currently being adopted as the visual evidence for COVID-19 diagnosis in clinical practice. Automated detection of COVID-19 infection from CT images based on deep models is important for faster examination. Unfortunately, collecting large-scale training data systematically in the early stage is difficult. To address this problem, we explore the feasibility of learning deep models for lung and COVID-19 infection segmentation from a single radiological image by resorting to synthesizing diverse radiological images. Specifically, we propose a novel conditional generative model, called CoSinGAN, which can be learned from a single radiological image with a given condition, i.e., the annotation mask of the lungs and infected regions. Our CoSinGAN is able to capture the conditional distribution of the single radiological image, and further synthesize high-resolution (512 &times, 512) and diverse radiological images that match the input conditions precisely. We evaluate the efficacy of CoSinGAN in learning lung and infection segmentation from very few radiological images by performing 5-fold cross validation on COVID-19-CT-Seg dataset (20 CT cases) and an independent testing on the MosMed dataset (50 CT cases). Both 2D U-Net and 3D U-Net, learned from four CT slices by using our CoSinGAN, have achieved notable infection segmentation performance, surpassing the COVID-19-CT-Seg-Benchmark, i.e., the counterparts trained on an average of 704 CT slices, by a large margin. Such results strongly confirm that our method has the potential to learn COVID-19 infection segmentation from few radiological images in the early stage of COVID-19 pandemic.

Started during December 2019, following the emergence of several COVID-19 cases in Wuhan City, Hubei Province, there was a rapid surge and spread of new COVID-19 cases throughout China. The disease has since been included in the Class B infectious diseases category, as stipulated in the Law of the People's Republic of China on the Prevention and Treatment of Infectious Diseases and shall be managed according to Class A infectious diseases. During the early phases of COVID-19 infection, no specific pulmonary imaging features may be evident, or features overlapping with other pneumonia may be observed. Although CT is not the gold standard for the diagnosis of COVID-19, it nonetheless is a convenient and fast method, and its application can be deployed in community hospitals. Furthermore, CT can be used to render a suggestive diagnosis and evaluate the severity as well as the effects of therapeutic interventions for typical cases of COVID-19. The mobile emergency special CT device described in this document (also known as Emergency Mobile Cabin CT) has several unique characteristics, including its mobility, flexibility, and networking capabilities. Furthermore, it adopts a fully independent isolation design to avoid cross-infection between patients and medical staff. It can play an important role in screening suspected cases presenting with imaging features of COVID-19 in hospitals of various levels that provide care to suspected or confirmed COVID-19 patients as part of the first line procedures of epidemic prevention and control.

It is still unknown if the EEG phase-locking value (PLV) on the boundary between brain hemispheres is associated with sleep stages or not. Totally 39 EEG recordings were analyzed from the Expanded Sleep Database in EDF. Original EEG was decomposed into four bands. PLV was derived from Fpz-Cz and Pz-Oz. Using support-vector machine classifier for sleep-wakefulness classification, accuracies were 90.0% and 90.7% with linear kernel and radial basis function kernel, respectively. The phase-locking value derived from EEG bipolar leads between brain hemispheres are highly associated to sleep-wakefulness stages.

Alzheimer's disease (AD) is a common and incurable dementia, so it is particularly important to correctly distinguish AD from normal people. In recent years, the development of deep learning has pointed out a new direction for the study of AD classification. This paper proposes a 3D residual densely connected convolutional network for AD and mild cognitive impairment (MCI) diagnosis. First, the Residual Dense Block (RDB) is used to expand the information flow to avoid the disappearance of gradients. Then we use the global feature fusion method to comprehensively consider the shallow and deep features to improve the accuracy of classification. This paper mainly uses the MRI data of the ADNI dataset for experiments to prove the superior performance of the proposed model.

Working memory has been examined extensively using the N-back task. However, less is known about the neural bases underlying individual variation in the accuracy rate (AR) and reaction time (RT) as metrics of N-back performance. Whereas AR indexes the overall performance, RT may more specifically reflect the efficiency in updating target identify. Further, studies have associated fluid intelligence (Gf) with working memory, but the cerebral correlates shared between Gf and N-back performance remain unclear. We addressed these issues using the Human Connectome Project dataset. We quantified the differences in AR (critical success index or CSI) and RT between 2- and 0-backs (CSI2–0 and RT2–0) and identified the neural correlates of individual variation in CSI2–0, RT2–0, and Gf, as indexed by the number of correct items scored in the Raven’s Standard Progressive Matrices (RSPM) test. The results showed that CSI2–0 and RT2–0 were negatively correlated, suggesting that a prolonged response time did not facilitate accuracy. At voxel p 2–0 and positive correlation with RT2–0. In contrast, a cluster in the dorsal anterior cingulate cortex (dACC) bordering the SMA showed activities in positive correlation with CSI2–0 and negative correlation with RT2–0. Further, path analyses showed a significant fit of the model dACC → RT2–0 → CSI2–0, suggesting a critical role of target switching in determining performance accuracy. Individual variations in RT2–0 and Gf were positively correlated, although the effect size was small (f2 = 0.0246). RT2–0 and Gf shared activities both in positive correlation with the preSMA, biFPC, rAI, and dorsal precuneus. These results together suggest inter-related neural substrates of individual variation in N-back performance and highlight a complex relationship in the neural processes supporting 2-back and RSPM performance.

In this study, we investigated and quantified the amygdalar and hippocampal morphometry abnormalities exerted by first-episode schizophrenia using a total of 92 patients and 106 healthy control participants. Magnetic resonance imaging (MRI) based automated segmentation was conducted to obtain the amygdalar and hippocampal segmentations. Disease-versus-control volume differences of the bilateral amygdalas and hippocampi were quantified. In addition, deformation-based statistical shape analysis was employed to quantify the region-specific shape abnormalities of each structure of interest. To better identify the key relevant areas in the pathology of first-episode schizophrenia, each structure was divided into four subregions; CA1, CA2, CA3 combined with dentate gyrus for the hippocampus in each hemisphere and basolateral, basomedial, centromedial, and lateral nucleus for the amygdala in each hemisphere. We observed significant global volume reduction and localized shape atrophy in each of the four structures of interest. The amygdalar shape abnormalities mainly occurred at the basolateral and centromedial subregions, whereas the hippocampal shape abnormalities mainly concentrated on the CA1 and CA2 subregions. For the same structure, the one on the right hemisphere was affected more by the disease pathology than that on the left hemisphere. To conclude, we have successfully quantified the global and local morphometric abnormalities of the bilateral amygdalas and hippocampi using a sophisticated statistical analysis pipeline and high-field subregion segmentations, with MRI data of a considerable sample size. This study is one of the very first of such kind in first-episode schizophrenia analyses.

In this paper, we proposed and validated a probability distribution guided network for segmenting optic disc (OD) and optic cup (OC) from fundus images. Uncertainty is inevitable in deep learning, as induced by different sensors, insufficient samples, and inaccurate labeling. Since the input data and the corresponding ground truth label may be inaccurate, they may actually follow some potential distribution. In this study, a variational autoencoder (VAE) based network was proposed to estimate the joint distribution of the input image and the corresponding segmentation (both the ground truth segmentation and the predicted segmentation), making the segmentation network learn not only pixel-wise information but also semantic probability distribution. Moreover, we designed a building block, namely the Dilated Inception Block (DIB), for a better generalization of the model and a more effective extraction of multi-scale features. The proposed method was compared to several existing state-of-the-art methods. Superior segmentation performance has been observed over two datasets (ORIGA and REFUGE), with the mean Dice overlap coefficients being 96.57% and 95.81% for OD and 88.46% and 88.91% for OC.

Previous work suggests sex differences in reward sensitivity. However, it remains unclear how men and women differ in the neural processes of reward-driven impulsivity. With a data set of 968 subjects (502 women) curated from the Human Connectome Project, we investigated sex differences in regional activations to reward and to punishment in a gambling task. Individual variations in reward-driven impulsivity were quantified by the difference in reaction time between reward and punishment blocks in the gambling task, as well as by a behavioral measure of delay discounting. At a corrected threshold, men and women exhibited significant differences in regional activations to reward and to punishment. Longer reaction times during reward versus punishment blocks, indicative of more cautious responding, were associated with left-hemispheric lateral prefrontal cortical activation to reward in men but not women. Steeper discounting was associated with higher activation to reward in the right-hemispheric dorsal anterior cingulate cortex and angular gyrus in women but not men. These sex differences were confirmed in slope tests. Together, the results highlight the sex-specific neural processes of reward-driven impulsivity with left-hemispheric prefrontal cortex supporting impulse control in men and right-hemispheric saliency circuit playing a more important role in diminished impulse control in women.

Social interaction is critical to emotional well-being. Previous studies have suggested sex differences in the perception of social interaction. However, the findings depend on the nature of interactions and whether it involves facial emotions. Here, we explored sex differences in neural responses to the perception of social interaction using the Human Connectome Project data. Participants (n = 969, 505 women) were engaged in a social cognition task with geometric objects moving and colliding to simulate social interaction. Behaviorally, men relative to women demonstrated higher accuracy in perceiving social vs. random interactions. Men vs. women showed higher activation in the right superior temporal gyrus, bilateral occipital and posterior cingulate cortex and precuneus, and women vs. men showed higher activation in the right inferior frontal cortex, during exposure to social vs. random interactions. In whole-brain regressions, the differences in accuracy rate in identifying social vs. random interactions (AR SOC - AR RAN ) were associated with higher activation in the paracentral lobule (PCL) and lower activation in bilateral anterior insula (AI), pre-supplementary motor area (preSMA), and left middle frontal gyrus (MFG) in men and women combined, lower activation in bilateral AI, preSMA and left MFG in men alone, and higher activation in the PCL and the medial orbitofrontal cortex in women alone. The latter sex differences were confirmed by slope tests. Further, the PCL activity mediated the correlation between an internalizing syndromal score, as assessed by the Achenbach Self-Report, and (AR SOC - AR RAN ) across all subjects. These findings highlighted sex differences in the behavioral and neural processes underlying the perception of social interaction, as well as the influence of internalizing traits on these processes.

Subjective cognitive decline (SCD) is the preclinical stage of Alzheimer's disease (AD), the most common neurodegenerative disease in the elderly. We collected resting-state functional MRI data and applied novel graph-theoretical analyses to investigate the dynamic spatiotemporal cerebral connectivities in 63 individuals with SCD and 67 normal controls (NC). Temporal flexibility and spatiotemporal diversity were mapped to reflect dynamic time-varying functional interactions among the brain regions within and outside communities. Temporal flexibility indicates how frequently a brain region interacts with regions of other communities across time; spatiotemporal diversity describes how evenly a brain region interacts with regions belonging to other communities. SCD and NC differed in large-scale brain dynamics characterized by the two measures, which, with support vector machine, demonstrated higher classification accuracies than conventional static parameters and structural metrics. The findings characterize dynamic network dysfunction that may serve as a biomarker of the preclinical stage of AD.

In this paper, we propose and validate a location prior guided automatic pancreas segmentation framework based on 3D convolutional neural network (CNN). To guide pancreas segmentation, centroid of the pancreas used to determine its bounding box is calculated using the location of the liver which is firstly segmented by a 2D CNN. A linear relationship between centroids of the pancreas and the liver is proposed. After that, a 3D CNN is employed the input of which is the bounding box of the pancreas to get the final segmentation. A publicly accessible pancreas dataset including 54 subjects is used to quantify the performance of the proposed framework. Experimental results reveal outstanding performance of the proposed method in terms of both computational efficiency and segmentation accuracy compared to non location guided segmentation. To be specific, the running time is 15 times faster and the segmentation accuracy in terms of Dice is higher by 4.29% (76.42% versus 80.71%).

In this paper, we proposed and validated a novel and effective pipeline for automatically detecting hemorrhage from coarsely-annotated fundus images in diabetic retinopathy. The proposed framework consisted of three parts: image pre-processing, training data refining, and object detection using a convolutional neural network with label smoothing. Contrast limited adaptive histogram equalization and adaptive gamma correction with weighting distribution were adopted to improve image quality by enhancing image contrast and correcting image illumination. To refine coarsely-annotated training data, we designed a bounding box refining network (BBR-net) to provide more accurate bounding box annotations. Combined with label smoothing, RetinaNet was implemented to alleviate mislabeling issues and automatically detect hemorrhages. The proposed method was trained and evaluated on a publicly available IDRiD dataset and also one of our private datasets 11This dataset will be released soon.. Experimental results showed that our BBR-net could effectively refine manually-delineated coarse hemorrhage annotations, with the average IoU being 0.8715 when compared with well-annotated bounding boxes. The proposed hemorrhage detection pipeline was compared to pure RetinaNet and superior performance was observed.

In this paper, we propose and validate a novel level-set method integrating an enhanced edge indicator and an automatically derived initial curve for CT based liver tumor segmentation. In the beginning, a 2D U-net is used to localize the liver and a 3D fully convolutional network (FCN) is used to refine the liver segmentation as well as to localize the tumor. The refined liver segmentation is used to remove non-liver tissues for subsequent tumor segmentation. Given that the tumor segmentation obtained from the aforementioned 3D FCN is typically imperfect, we adopt a novel level-set method to further improve the tumor segmentation. Specifically, the probabilistic distribution of the liver tumor is estimated using fuzzy c- means clustering and then utilized to enhance the object indication function used in level-set. The proposed segmentation pipeline was found to have an outstanding performance in terms of both liver and liver tumor.

Schizophrenia is a type of neurodevelopmental psychiatric disorder. However, to date, scientists have not discovered the etiology and effective treatment of this condition. We injected the early growth response gene (EGR3) into the bilateral hippocampus to build a schizophrenia rat model. Behavioral phenotyping and resting-state functional magnetic resonance imaging (rs-fMRI) were used to analyze the behavioral and cerebral alterations in the schizophrenia rat model. The efficacy of risperidone therapy was also evaluated. We divided 34 rats into four groups: schizophrenia model group (E group), sham-operation group (FE group), healthy control group (H group), and risperidone therapy group (T group). Open field test and Morris water maze were conducted as behavioral experiments. Next, we performed rs-fMRI after four weeks of EGR3 transfection and risperidone treatment and analyzed imaging data using regional homogeneity (ReHo), the amplitude of low-frequency fluctuations (ALFF), and functional connectivity (FC). We examined the difference in behavioral and neural activation among the four groups and considered the correlations between behavior and imaging results. EGR3 gene transfection decreased the total moved distance in the open field test and the duration in the Q5 zone of the Morris water maze. Risperidone treatment reversed the trend and improved the performance of rats in these behavioral tests. Schizophrenia induced several neural alterations in ALFF and ReHo metrics of the rat brain, and risperidone could partly reverse these alterations. The results suggest that similar research is required for schizophrenia and that risperidone may be a novel treatment for dysregulated neural activation in schizophrenia.

Neuroinflammation is a key aspect of various injuries and diseases of the central nervous system and brain, including stroke, Alzheimer’s, Parkinson’s, multiple sclerosis, etc. Phoenixin-14 is a naturally occurring pleiotropic peptide involved in reproduction, anxiety, pain, and other functions. Primary astrocytes were isolated from new-born pups of c57bl/6 mice. The gene expression of GPR173, CHOP, and GADD34 was measured by real-time PCR. Protein expression was assessed by western blot analysis. Secretions of IL-1β and IL-18 were determined by ELISA. Phoenixin-14 (PNX-14) is a ligand for the G protein-coupled receptor GPR173, which we demonstrate to be expressed in astrocytes and suppressed by exposure to lipopolysaccharide (LPS). Endoplasmic reticulum (ER) stress resulting from injury or disease leads to the unfolded protein response, which is mediated by the activation of transcription factors including eIF-2α, ATF4, and CHOP, and regulated by GADD34. ER stress also leads to a robust neuroinflammatory response, which is mediated by HMGB1-induced activation of the NLRP3 inflammasome and subsequent production of IL-1β and IL-18. In the present study, we demonstrate that PNX-14 could attenuate LPS-induced ER stress response and NLRP3 inflammasome activation in mouse cerebral astrocytes. Our findings show that PNX-14 could suppress the production of ROS as well as the decrease in SOD induced by LPS. PNX-14 also inhibited HMGB1-mediated NLRP3 inflammasome activation and production of IL-1β and IL-18. Through a GPR173 siRNA knockdown experiment, we further demonstrate that GPR173 knockdown abolished the effects of PNX-14 on LPS-induced NLRP3 expression and IL-18 production. These findings suggest that PNX-14 may have potential in the treatment of neuroinflammation.

In this paper, we propose and validate a deep learning framework that incorporates both multi-atlas registration and level-set for segmenting pancreas from CT volume images. The proposed segmentation pipeline consists of three stages, namely coarse, fine, and refine stages. Firstly, a coarse segmentation is obtained through multi-atlas based 3D diffeomorphic registration and fusion. After that, to learn the connection feature, a 3D patch-based convolutional neural network (CNN) and three 2D slice-based CNNs are jointly used to predict a fine segmentation based on a bounding box determined from the coarse segmentation. Finally, a 3D level-set method is used, with the fine segmentation being one of its constraints, to integrate information of the original image and the CNN-derived probability map to achieve a refine segmentation. In other words, we jointly utilize global 3D location information (registration), contextual information (patch-based 3D CNN), shape information (slice-based 2.5D CNN) and edge information (3D level-set) in the proposed framework. These components form our cascaded coarse-fine-refine segmentation framework. We test the proposed framework on three different datasets with varying intensity ranges obtained from different resources, respectively containing 36, 82 and 281 CT volume images. In each dataset, we achieve an average Dice score over 82%, being superior or comparable to other existing state-of-the-art pancreas segmentation algorithms.

Corneal ulcer is a common ophthalmic symptom. Segmentation algorithms are needed to identify and quantify corneal ulcers from ocular staining images. Developments of such algorithms have been obstructed by a lack of high quality datasets (the ocular staining images and the corresponding gold-standard ulcer segmentation labels), especially for supervised learning based segmentation algorithms. In such context, we prepare a dataset containing 712 ocular staining images and the associated segmentation labels of flaky corneal ulcers. In addition to segmentation labels for flaky corneal ulcers, we also provide each image with three-fold class labels: firstly, each image has a label in terms of its general ulcer pattern; secondly, each image has a label in terms of its specific ulcer pattern; thirdly, each image has a label indicating its ulcer severity degree. This dataset not only provides an excellent opportunity for investigating the accuracy and reliability of different segmentation and classification algorithms for corneal ulcers, but also advances the development of new supervised learning based algorithms especially those in the deep learning framework., Measurement(s)corneal ulcerTechnology Type(s)stainingFactor Type(s)ulcer severity • ulcer patternSample Characteristic - OrganismHomo sapiens Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.11371803

In this paper, we proposed and validated a novel and accurate pipeline for automatically segmenting flaky corneal ulcer areas from fluorescein staining images. The ulcer area was segmented within the cornea by employing a joint method of Otsu and Gaussian Mixture Modeling (GMM). In the GMM based segmentation, the total number of Gaussians was determined intelligently using an information theory based algorithm. And the fluorescein staining images were processed in the HSV color model rather than the original RGB color model, aiming to improve the segmentation results’ robustness and accuracy. In the Otsu based segmentation, the images were processed in the grayscale space with Gamma correction being conducted before the Otsu binarization. Afterwards, morphological operations and median filtering were employed to further improve the Otsu segmentation result. The GMM and Otsu segmentation results were then intersected, for which post-processing was conducted by identifying and filling holes through a fast algorithm using priority queues of pixels. The proposed pipeline has been validated on a total of 150 clinical images. Accurate ulcer segmentation results have been obtained, with the mean Dice Similarity Coefficient (DSC) being 0.88 when comparing the automatic segmentation result with the manually-delineated gold standard. For images in the RGB color space, the mean DSC was 0.83, being much lower than that of the images in the HSV color space.

Objective: In this study, we investigated the influence that the pathology of Alzheimer’s disease (AD) exerts upon the corpus callosum (CC) using a total of 325 mild cognitive impairment (MCI) subjects, 155 AD subjects, and 185 healthy control (HC) subjects. Method: Regionally-specific morphological CC abnormalities, as induced by AD, were quantified using a large deformation diffeomorphic metric curve mapping based statistical shape analysis pipeline. We also quantified the association between the CC shape phenotype and two cognitive measures; the Mini Mental State Examination (MMSE) and the Alzheimer’s Disease Assessment Scale-Cognitive Behavior Section (ADAS-cog). To identify AD-relevant areas, CC was sub-divided into three subregions; the genu, body, and splenium (gCC, bCC, and sCC). Results: We observed significant shape compressions in AD relative to that in HC, mainly concentrated on the superior part of CC, across all three sub-regions. The HC-vs-MCI shape abnormalities were also concentrated on the superior part, but mainly occurred on bCC and sCC. The significant MCI-vs-AD shape differences, however, were only detected in part of sCC. In the shape-cognition association, significant negative correlations to ADAS-cog were detected for shape deformations at regions belonging to gCC and sCC and significant positive correlations to MMSE at regions mainly belonging to sCC. Conclusion: Our results suggest that the callosal shape deformation patterns, especially those of sCC, linked tightly to the cognitive decline in AD, and are potentially a powerful biomarker for monitoring the progression of AD.

Two-dimensional reconstructed phase space (RPS) of single lead Electrocardiogram (ECG) is usually implemented by plotting the ECG amplitude x(t + τ) versus x(t) into the two-dimensional coordinate system, where the value of time delay τ determined the morphology of the reconstructed trajectory. However, the value of τ is very difficult to select because different theories derived different τ. In this paper, a novel approach to phase space reconstruction of single lead ECG without using τ is proposed. The first two coordinates (x, y) from (x, y, t) were projected into the x-y coordinate system, where x is the amplitude of the ECG and y is the first order difference of x. Besides, time t is corresponding to the sampling time moment. As QRS complex is usually the most striking waveform that dominant with the highest amplitude or the highest slope, the largest semi-circle in the RPS is usually derived from QRS complex. The location of QRS complex in the original ECG is determined by the time coordinate t that corresponds to the largest semi-circle in the x-y coordinate system. The algorithm was developed at the MIT-BIH Arrhythmia Database (109494 beats within 24 h in total) and was tested on the Long-term ST Database (8897780 beats within 1991.8 h in total). The accuracy (ACC), the sensitivity (SEN) and the positive predictivity value (PPV) for the MIT-BIH Arrhythmia Database were 99.81%, 99.87% and 99.93%, respectively; while the corresponding values for the Long-term ST Database were 99.87%, 99.96% and 99.91%, respectively. Meanwhile, the consuming time was only 6.73 ms for processing 6 s’ ECG data. Furthermore, the anti-noise ability of the proposed method was tested on the MIT-BIH Noise Stress Test Database (4265 beats in total at each noise level for one lead ECG). Both ACC and PPV were higher than 85% and the SEN was higher than 99% even when the signal-to-noise ratio (SNR) was as low as 0 dB. In conclusion, the proposed algorithm achieves better performance on QRS complex detection when in comparison with the state-of-the-art methods, and it is suited for the detection of QRS complex in the ECG associated with poor signal quality and severe arrhythmia.

In aortic endovascular repair, the prediction of stented vessel remodeling informs treatment plans and risk evaluation; however, there are no highly accurate and efficient methods to quantitatively simulate stented vessels. This study developed a fast virtual stenting algorithm to simulate stent-induced aortic remodeling to assist in real-time thoracic endovascular aortic repair planning. Methods: The virtual stenting algorithm was established based on simplex deformable mesh and mechanical contact analysis. The key parameters of the mechanical contact analysis were derived from mechanical tests on aortic tissue (n=40) and commonly used stent-grafts (n=6). Genetic algorithm was applied to select weighting parameters. Testing and validation of the algorithm were performed using pre- and post-treatment computed tomography angiography datasets of type-B aortic dissection cases (n=66). Results: The algorithm was efficient in simulating stent-induced aortic deformation (mean computing time on a single processor: 13.78±2.80s) and accurate at the morphological (curvature difference: 1.57±0.57%; cross-sectional area difference: 4.11±0.85%) and hemodynamic (similarity of wall shear stress-derived parameters: 90.16-90.94%) levels. Stent-induced wall deformation was higher (p

Graphic theoretical metrics have become increasingly popular in characterizing functional connectivity of neural networks and how network connectivity is compromised in neuropsychiatric illnesses. Here, we add to this literature by describing dynamic network connectivities of 78 cocaine dependent (CD) and 85 non-drug using healthy control (HC) participants who underwent fMRI during performance of a stop signal task (SST). Compared to HC, CD showed prolonged stop signal reaction time (SSRT), consistent with deficits in response inhibition. In graph theoretical analysis of dynamic functional connectivity, we examined temporal flexibility and spatiotemporal diversity of 14 networks covering the whole brain. Temporal flexibility quantifies how frequently a brain region interacts with regions of other communities across time, with high temporal flexibility indicating that a region interacts predominantly with regions outside its own community. Spatiotemporal diversity quantifies how uniformly a brain region interacts with regions in other communities over time, with high spatiotemporal diversity indicating that the interactions are more evenly distributed across communities. Compared to HC, CD exhibited decreased temporal flexibility and increased spatiotemporal diversity in the great majority of neural networks. The graph metric measures of the default mode network negatively correlated with SSRT in CD but not HC. The findings are consistent with diminished temporal flexibility and a compensatory increase in spatiotemporal diversity, in association with impairment of a critical executive function, in cocaine addiction. More broadly, the findings suggest that graph theoretical metrics provide new insights for connectivity analyses to elucidate network dysfunction that may elude conventional measures., Highlights • Cocaine addiction (CA) is associated with prolonged stop signal reaction time (SSRT). • CA is associated with decreased temporal flexibility (TF) of neural networks. • CA is associated with increased spatial temporal diversity (STD) of neural networks. • The TF and STD of default mode network correlated negatively with SSRT in CA. • Dynamic connectivity captures network dysfunction in link with inhibition deficits in CA.

Magnetic particle imaging (MPI) is an emerging medical imaging modality that is based on the non-linear response of magnetic nanoparticles. The reconstruction task is an inverse problem and ill-posed in nature. The reconstruction results based on the state-of-the-art regularization model have many artifacts, and the time resolution should be improved significantly for real-time imaging. To this end, we first propose to use the elastic net (EN) regularization for MPI reconstruction. To obtain a good result with a short reconstruction time, we use the truncated system matrix and the truncated measurement for reconstruction research. We study the reconstruction quality by varying the threshold values and regularization parameters. We compare the reconstruction performance of the proposed model with the Tikhonov model and the least absolute shrinkage and selection operator (LASSO) model in terms of visualization and performance indicators. The MPI reconstruction results based on the EN have largely no artifacts, and the time resolution is approximately 10 times that of the LASSO model and 20 times that of the Tikhonov model. The conducted study demonstrated that the proposed method yields a significantly higher reconstruction quality and a higher time resolution than the state-of-the-art reconstruction methods based on the Tikhonov and LASSO models.

Background Peer influences figure prominently in young adult binge drinking. Women have trended to show a level of alcohol use on par with men during the last decades. It would be of interest to investigate the neural processes of social cognition that may underlie binge drinking and the potential sex differences. Methods Here, we examined the data of the Human Connectome Project where we identified a total of 175 binge drinkers (125 men) and 285 non-binge drinkers (97 men) performing a social cognition task during brain imaging. We analyzed the imaging data with published routines and evaluated the results at a corrected threshold. Results Both male and female binge relative to non-binge drinkers showed higher perceived friendship. Binge relative to non-binge drinkers demonstrated diminished activations in the anterior medial orbitofrontal cortex (amOFC) during perception of social vs. random interaction, with a more prominent effect size in women. Further, whole-brain regression identified activity of the right posterior insula (rPI) in negative correlation with perceived friendship score in non-binge drinking women. Post-hoc analyses showed significant correlation of rPI activity with perceived friendship, amOFC activity, and a summary measure of alcohol use severity identified by principal component analysis, across all subjects. Mediation and path analysis demonstrated a significant model: amOFC activity → rPI activity → perceived friendship → severity of alcohol use. Conclusions These findings support peer influences on binge drinking and suggest neural correlates that may relate altered social cognitive processing to alcohol misuse in young adults.

// Tianyi Yan 1, 2 , Wenhui Wang 1, 2 , Tiantian Liu 1, 2 , Duanduan Chen 1 , Changming Wang 3 , Yulong Li 4 , Xudong Ma 5 , Xiaoying Tang 1 , Jinglong Wu 2 , Yiming Deng 6, 7 and Lun Zhao 8 1 School of Life Science, Beijing Institute of Technology, Beijing, China 2 Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology, Beijing, China 3 Beijing Key Laboratory of Mental Disorders, Beijing Anding Hospital, Capital Medical University, Beijing, China 4 Beijing National Day School, Beijing, China 5 Guang Zhou Clifford School, Guang Dong, China 6 Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing Key Laboratory of Translational Medicine for Cerebrovascular Disease, Beijing, China 7 China National Clinical Research Center for Neurological Diseases, Beijing, China 8 School of Education, Beijing Normal University Zhuhai, Zhuhai, China Correspondence to: Tianyi Yan, email: yantianyi@bit.edu.cn Yiming Deng, email: parkerdeng@163.com Keywords: schizophrenia, facial processing, dynamic brain network, phase synchrony, graph theory Received: April 09, 2017 Accepted: June 12, 2017 Published: September 01, 2017 ABSTRACT Schizophrenia is often considered to be a disconnection syndrome. The abnormal interactions between large-scale functional brain networks result in cognitive and perceptual deficits. The present study investigated event-related functional connectivity networks to compare facial processing in individuals with and without schizophrenia. Faces and tables were presented to participants, and event-related phase synchrony, represented by the phase lag index (PLI), was calculated. In addition, cortical oscillatory dynamics may be useful for understanding the neural mechanisms underlying the disparate cognitive and functional impairments in schizophrenic patients. Therefore, the dynamic graph theoretical networks related to facial processing were compared between individuals with and without schizophrenia. Our results showed that event-related phase synchrony was significantly reduced in distributed networks, and normalized clustering coefficients were significantly increased in schizophrenic patients relative to those of the controls. The present data suggest that schizophrenic patients have specific alterations, indicated by increased local connectivity in gamma oscillations during facial processing.

Atrial fibrillation (AF) monitoring and diagnosis require automatic AF detection methods. In this paper, a novel image-based AF detection method was proposed. The map was constructed by plotting changes of RR intervals (△RR) into grid panes. First, the map was divided into grid panes with 20 ms fixed resolution in y-axes and 15-60 s step length in x-axes. Next, the blank pane ratio (BPR), the entropy and the probability density distribution were processed using linear support-vector machine (LSVM) to classify AF and non-AF episodes. The performance was evaluated based on four public physiological databases. The Cohen's Kappa coefficients were 0.87, 0.91 and 0.64 at 50 s step length for the long-term AF database, the MIT-BIH AF database and the MIT-BIH arrhythmia database, respectively. Best results were achieved as follows: (1) an accuracy of 93.7%, a sensitivity of 95.1%, a specificity of 92.0% and a positive predictive value (PPV) of 93.5% were obtained for the long-term AF database at 60 s step length. (2) An accuracy of 95.9%, a sensitivity of 95.3%, a specificity of 96.3% and a PPV of 94.1% were obtained for the MIT-BIH AF database at 40 s step length. (3) An accuracy of 90.6%, a sensitivity of 94.5%, a specificity of 90.0% and a PPV of 55.0% were achieved for the MIT-BIH arrhythmia database at 60 s step length. (4) Both accuracy and specificity were 96.0% for the MIT-BIH normal sinus rhythm database at 40 s step length. In conclusion, the intuitive grid map of delta RR intervals offers a new approach to achieving comparable performance with previously published AF detection methods.

Purpose To assess the region-specific atrophy of precentral gyrus (PrCG) and its correlation to clinical function score in amyotrophic lateral sclerosis (ALS). Materials and Methods Twenty-eight patients with sporadic ALS and 28 healthy controls underwent high-resolution 3D T1-BRAVO magnetic resonance imaging at 3T. The bilateral PrCG segmentations were automatically obtained from a validated segmentation pipeline based on diffeomorphic multi-atlas likelihood fusion. Patients with ALS were further subclassified into early-stage (ALS-e, n = 22) and late-stage (ALS-l, n = 6) groups, with 12 months as a disease duration cutoff. Vertex-based shape analysis was performed to quantify the region-specific abnormalities of PrCG in ALS subgroups as compared to controls. In addition, we tested the statistical association between altered PrCG morphometry and clinical disability in ALS as evaluated by the revised ALS Functional Rating Scale (ALSFRS-r). Results Compared to controls, vertex-wise analysis showed that both ALS-e and ALS-l had significant atrophy of the dorsal-lateral part of PrCG (P

In this article, we present a unified statistical pipeline for analyzing the white matter (WM) tracts morphometry and microstructural integrity, both globally and locally within the same WM tract, from diffusion tensor imaging. Morphometry is quantified globally by the volumetric measurement and locally by the vertexwise surface areas. Meanwhile, microstructural integrity is quantified globally by the mean fractional anisotropy (FA) and trace values within the specific WM tract and locally by the FA and trace values defined at each vertex of its bounding surface. The proposed pipeline consists of four steps: (1) fully automated segmentation of WM tracts in a multi-contrast multi-atlas framework; (2) generation of the smooth surface representations for the WM tracts of interest; (3) common template surface generation on which the localized morphometric and microstructural statistics are defined and a variety of statistical analyses can be conducted; (4) multiple comparison correction to determine the significance of the statistical analysis results. Detailed herein, this pipeline has been applied to the corpus callosum in Alzheimer's disease (AD) with significantly decreased FA values and increased trace values, both globally and locally, being detected in patients with AD when compared to normal aging populations. A subdivision of the corpus callosum in both hemispheres revealed that the AD pathology primarily affects the body and splenium of the corpus callosum. Validation analyses and two multiple comparison correction strategies are provided. Hum Brain Mapp 38:1875-1893, 2017. © 2017 Wiley Periodicals, Inc.

Wilson’s disease (WD) is a progressive autosomal-recessive genetic disorder of copper metabolism that can induce cognitive, physical and psychiatric symptoms. Despite the wide use of machine learning methods in neuroimaging analysis, WD-related research has been very rare. In this work, we proposed and validated an efficient pipeline for an automated WD classification based on whole brain segmentation volumes and cortical thicknesses obtained from T1-weighted magnetic resonance images (MRIs). Three well-known supervised machine learning algorithms, including support vector machine (SVM), linear discriminant analysis (LDA), and logistic regression (LR), were evaluated and compared in the setting of WD classification. A total of 51 images, including 27 acquired from WD patients and 24 from age-matched healthy controls, were used in the validation analysis. Univariate feature selection was conducted to eliminate non-relevant features and retain features contributing to the classification performance. Two nested leave-one-out cross validations were adopted, with the inner folder used for optimal parameter estimation and the outer folder for classification performance evaluation. Experimental results showed that when employing volume features, SVM significantly outperformed both LDA and LR, yielding an overall accuracy of 96.1%, a sensitivity of 92.6% and a specificity of 100%. LR could also reach such best classification performance when using a combination of volumes and thicknesses as input features. This study provides a new non-invasive tool (MRI-based) for an automated detection of WD.s

We proposed and validated a fully-automated classification procedure for amyotrophic lateral sclerosis (ALS) using structural magnetic resonance imaging; specifically, T1-weighted images from 28 ALS subjects and 28 healthy control (HC) subjects were used. The raw features were obtained from a validated multi-granularity whole-brain analysis pipeline, providing multi-level whole-brain segmentation volumes. We employed the support vector machine as our classification algorithm with several feature selection techniques analyzed. According to our leave-one-out cross validation experiment results, the whole-brain structural volumes from Level 4, followed by a feature selection utilizing the standardized Wilcoxon two-sample rank sum statistic, yielded the best classification performance; overall accuracy: 83.93%, sensitivity: 85.71%, specificity: 82.14%, and the area under the receiver operating characteristic curve: 0.8380. The feature selection procedure revealed that the volumes of the thalamus, especially that on the left hemisphere, are the most important (of highest ranking) in the ALS-vs-HC discrimination.

Mutations in genes encoding isocitrate dehydrogenases (IDH) 1 and 2 are common cancer-related genetic abnormalities. Malignancies with mutated IDHs exhibit similar pathogenesis, metabolic pattern, and resistance signature. However, an effective therapy against IDH1-mutated solid tumor remains unavailable. In this study, we showed that acquisition of IDH1 mutation results in the disruption of NADP+/NADPH balance and an increased demand for glutathione (GSH) metabolism. Moreover, the nuclear factor erythroid 2–related factor 2 (Nrf2) plays a key protective role in IDH1-mutated cells by prompting GSH synthesis and reactive oxygen species scavenging. Pharmacologic inhibition of the Nrf2/GSH pathway via brusatol administration exhibited a potent tumor suppressive effect on IDH1-mutated cancer in vitro and in vivo. Our findings highlight a possible therapeutic strategy that could be valuable for IDH1-mutated cancer treatment.

In this paper, we proposed and validated a novel and fully automatic pipeline for simultaneous tissue classification and lateral ventricle segmentation via a 2D U-net. The 2D U-net was driven by a 3D fully convolutional neural network (FCN). Multiple T1-weighted atlases which had been pre-segmented into six whole-brain regions including the gray matter (GM), white matter (WM), cerebrospinal fluid (CSF), lateral ventricles (LVs), skull, and the background of the entire image were used. In the proposed pipeline, probability maps of the six whole-brain regions of interest (ROIs) were obtained after a pre-segmentation through a trained 3D patch-based FCN. To further capture the global context of the entire image, the to-be-segmented image and the corresponding six probability maps were input to a trained 2D U-net in a 2D slice fashion to obtain the final segmentation map. Experiments were performed on a dataset consisting of 18 T1-weighted images. Compared to the 3D patch-based FCN on segmenting five ROIs (GM, WM, CSF, LVs, skull) and another two classical methods (SPM and FSL) on segmenting GM and WM, the proposed pipeline showed a superior segmentation performance. The proposed segmentation architecture can also be extended to other medical image segmentation tasks.