Automated facial-vestibulocochlear nerve complex identification based on data-driven tractography clustering.

Small size and intricate anatomical environment are the main difficulties facing tractography of the facial-vestibulocochlear nerve complex (FVN), and lead to challenges in fiber orientation distribution (FOD) modeling, fiber tracking, region-of-interest selection, and fiber filtering. Experts need rich experience in anatomy and tractography, as well as substantial labor costs, to identify the FVN. Thus, we present a pipeline to identify the FVN automatically, in what we believe is the first study of the automated identification of the FVN. First, we created an FVN template. Forty high-resolution multishell data were used to perform data-driven fiber clustering based on the multishell multitissue constraint spherical deconvolution FOD model and deterministic tractography. We selected the brainstem and cerebellum (BS-CB) region as the seed region and removed the fibers that reach other brain regions. We then performed spectral fiber clustering twice. The first clustering was to create a BS-CB atlas and separate the fibers that pass through the cerebellopontine angle, and the other one was to extract the FVN. Second, we registered the subject-specific fibers in the space of the FVN template and assigned each fiber to the closest cluster to identify the FVN automatically by spectral embedding. We applied the proposed method to different acquirement sites, including two different healthy datasets and two tumor patient datasets. Experimental results showed that our automatic identification results have ideal colocalization with expert manual identification in terms of spatial overlap and visualization. Importantly, we successfully applied our method to tumor patient data. The FVNs identified by the proposed method were in agreement with intraoperative findings.

An Effective 3D Shape Descriptor for Object Recognition with RGB-D Sensors.

RGB-D sensors have been widely used in various areas of computer vision and graphics. A good descriptor will effectively improve the performance of operation. This article further analyzes the recognition performance of shape features extracted from multi-modality source data using RGB-D sensors. A hybrid shape descriptor is proposed as a representation of objects for recognition. We first extracted five 2D shape features from contour-based images and five 3D shape features over point cloud data to capture the global and local shape characteristics of an object. The recognition performance was tested for category recognition and instance recognition. Experimental results show that the proposed shape descriptor outperforms several common global-to-global shape descriptors and is comparable to some partial-to-global shape descriptors that achieved the best accuracies in category and instance recognition. Contribution of partial features and computational complexity were also analyzed. The results indicate that the proposed shape features are strong cues for object recognition and can be combined with other features to boost accuracy.

Immunogenicity of a cell culture-derived inactivated vaccine against a common virulent isolate of grass carp reovirus.

Grass carp (Ctenopharyngodon idella) hemorrhagic disease, caused by grass carp reovirus (GCRV), is emerging as a serious problem in grass carp aquaculture. There is no available antiviral therapy and vaccination is the primary method of disease control. In the present study, the immunological effects and protective efficacy of an inactivated HuNan1307 vaccine in grass carp were evaluated. The GCRV isolate HuNan1307 was produced by replication onto the grass carp PSF cell line, and inactivated with 1% ß-propiolactone for 60 h at 4 °C. Grass carp were injected with inactivated GCRV vaccine, followed by challenge with the isolate HuNan1307. The results showed that the minimum dosage of the inactivated vaccine was 10(5.5) TCID50/0.2 mL to induce immune protection. All grass carp immunized with the inactivated vaccine produced a high titer of serum antibodies and GCRV-specific neutralizing antibody. Moreover, the inactivated vaccine injection increased the expression of 6 immune-related genes in the spleen and head kidney, which indicated that a immune response was induced by the HuNan1307 vaccine. In addition, grass carp immunized with the inactivated vaccine showed a survival rate above 80% after the viral challenge, equal to that of grass carp immunized with a commercial attenuated vaccine, and the protection lasted at least for one year. The data in this study suggested that the inactivated HuNan1307 vaccine may represent an efficient method to induce immunity against GCRV infection and the induced disease in grass carp.

Learning Spatio-Temporal Pulse Representation With Global-Local Interaction and Supervision for Remote Prediction of Heart Rate.

Recent studies have demonstrated the benefit of extracting and fusing pulse signals from multi-scale region-of-interests (ROIs). However, these methods suffer from heavy computational load. This paper aims to effectively utilize multi-scale rPPG features with a more compact architecture. Inspired by recent research works exploring two-path architecture that leverages global and local information with bidirectional bridge in between. This paper designs a novel architecture Global-Local Interaction and Supervision Network (GLISNet), which uses a local path to learn representations in the original scale and a global path to learn representations in the other scale capturing multi-scale information. A light-weight rPPG signal generation block is attached to the output of each path that maps the pulse representation to the pulse output. A hybrid loss function is utilized enabling the local and global representations to learn directly from the training data. Extensive experiments are conducted on two publicly available datasets, and results demonstrate that GLISNet achieves superior performance in terms of signal-to-noise ratio (SNR), mean absolute error (MAE), and root mean squared error (RMSE). In terms of SNR, GLISNet has an increase of 4.41% compared with the second best algorithm PhysNet on PURE dataset. The MAE has a decrease of 13.16% compared with the second best algorithm DeeprPPG on UBFC-rPPG dataset. The RMSE has a decrease of 26.29% compared with the second best algorithm PhysNet on UBFC-rPPG dataset. Experiments on MIHR dataset demonstrates the robustness of GLISNet under low-light environment.

Challenges and prospects of visual contactless physiological monitoring in clinical study.

The monitoring of physiological parameters is a crucial topic in promoting human health and an indispensable approach for assessing physiological status and diagnosing diseases. Particularly, it holds significant value for patients who require long-term monitoring or with underlying cardiovascular disease. To this end, Visual Contactless Physiological Monitoring (VCPM) is capable of using videos recorded by a consumer camera to monitor blood volume pulse (BVP) signal, heart rate (HR), respiratory rate (RR), oxygen saturation (SpO2) and blood pressure (BP). Recently, deep learning-based pipelines have attracted numerous scholars and achieved unprecedented development. Although VCPM is still an emerging digital medical technology and presents many challenges and opportunities, it has the potential to revolutionize clinical medicine, digital health, telemedicine as well as other areas. The VCPM technology presents a viable solution that can be integrated into these systems for measuring vital parameters during video consultation, owing to its merits of contactless measurement, cost-effectiveness, user-friendly passive monitoring and the sole requirement of an off-the-shelf camera. In fact, the studies of VCPM technologies have been rocketing recently, particularly AI-based approaches, but few are employed in clinical settings. Here we provide a comprehensive overview of the applications, challenges, and prospects of VCPM from the perspective of clinical settings and AI technologies for the first time. The thorough exploration and analysis of clinical scenarios will provide profound guidance for the research and development of VCPM technologies in clinical settings.

Weighted combination and singular spectrum analysis based remote photoplethysmography pulse extraction in low-light environments.

Camera-based vital signs monitoring in recent years has attracted more and more researchers and the results are promising. However, a few research works focus on heart rate extraction under extremely low illumination environments. In this paper, we propose a novel framework for remote heart rate estimation under low-light conditions. This method uses singular spectrum analysis (SSA) to decompose the filtered signal into several reconstructed components. A spectral masking algorithm is utilized to refine the preliminary candidate components on the basis of a reference heart rate. The contributive components are fused into the final pulse signal. To evaluate the performance of our framework in low-light conditions, the proposed approach is tested on a large-scale multi-illumination HR dataset (named MIHR). The test results verify that the proposed method has stronger robustness to low illumination than state-of-the-art methods, effectively improving the signal-to-noise ratio and heart rate estimation precision. We further perform experiments on the PUlse RatE detection (PURE) dataset which is recorded under normal light conditions to demonstrate the generalization of our method. The experiment results show that our method can stably detect pulse rate and achieve comparative results. The proposed method pioneers a new solution to the remote heart rate estimation in low-light conditions.

Deep-Learned Regularization and Proximal Operator for Image Compressive Sensing.

Deep learning has recently been intensively studied in the context of image compressive sensing (CS) to discover and represent complicated image structures. These approaches, however, either suffer from nonflexibility for an arbitrary sampling ratio or lack an explicit deep-learned regularization term. This paper aims to solve the CS reconstruction problem by combining the deep-learned regularization term and proximal operator. We first introduce a regularization term using a carefully designed residual-regressive net, which can measure the distance between a corrupted image and a clean image set and accurately identify to which subspace the corrupted image belongs. We then address a proximal operator with a tailored dilated residual channel attention net, which enables the learned proximal operator to map the distorted image into the clean image set. We adopt an adaptive proximal selection strategy to embed the network into the loop of the CS image reconstruction algorithm. Moreover, a self-ensemble strategy is presented to improve CS recovery performance. We further utilize state evolution to analyze the effectiveness of the designed networks. Extensive experiments also demonstrate that our method can yield superior accurate reconstruction (PSNR gain over 1 dB) compared to other competing approaches while achieving the current state-of-the-art image CS reconstruction performance. The test code is available at https://github.com/zjut-gwl/CSDRCANet.

Local White Matter Fiber Clustering Differentiates Parkinson's Disease Diagnoses.

Scans without evidence of dopaminergic deficit (SWEDD) patients are often misdiagnosed with Parkinson's disease (PD) but have normal dopamine transporter scans. We hypothesised that white matter tracts associated with motor and cognition functions may be affected differently by SWEDD and PD. Automatically annotated fibre clustering (AAFC) is a novel clustering method based on diffusion magnetic resonance imaging (dMRI) tractography that enables highly robust reconstruction of white matter tracts that are composed of corresponding clusters. This study aimed to investigate the white matter properties in the subdivisions of white matter tracts among SWEDD and PD groups. We applied AAFC to identify white matter tracts related to motion and cognition functions in the dataset consisting of SWEDD (n = 22), PD (n = 30) and normal control (NC) (n = 30). Then, we resampled 200 nodes along fibres of cluster, and the diffusion metric values corresponding to each node were calculated and used for comparison. Compared with NC, PD showed significant difference (p < 0.05) in two clusters in thalamo-frontal (TF), one cluster in thalamo-parietal (TP) and one cluster in thalamo-occipital (TO), whereas SWEDD presented no significant difference. Three clusters in cingulum bundle (CB) commonly exhibited significant differences in PD versus SWEDD and NC versus SWEDD. The support vector machine classifier achieved high accuracies in PD-NC, PD-SWEDD and NC-SWEDD classifications. This outcome validated these local white matter differences were useful to separate the three groups. These results suggest that PD exerts more significant effects on thalamo tracts than SWEDD, and unique microstructural changes occur in CB tract in SWEDD.

Investigation of local white matter abnormality in Parkinson's disease by using an automatic fiber tract parcellation.

The deficits of white matter (WM) microstructure are involved during Parkinson's disease (PD) progression. Most current methods identify key WM tracts relying on cortical regions of interest (ROIs). However, such ROI methods can be challenged due to low diffusion anisotropy near the gray matter (GM), which could result in a low sensitivity of tract identification. This work proposes an automatic WM parcellation method to improve the accuracy of WM tract identification and locate abnormal tracts by using sensitive features. The proposed method consists of 1) whole brain WM parcellation using an established fiber clustering method, without using any ROIs, 2) features of fasciculus were calculated to quantify diffusion measures at each equal cross-section along the whole cluster. Then, we use the proposed features to investigate the WM difference in PD compared with healthy controls (HC). We also use these features to investigate the relationship of clinical symptoms and specific fiber tracts. The novelty of the proposed method is that it automatically identifies the abnormal WM fibers in cluster degree. Experiment results indicated that the proposed method had advantage in detecting the local WM abnormality by performing between-group statistical analysis in 30 patients with PD and 28 HC. We found 13 hemisphere clusters and 8 commissural clusters had significant group difference (p < 0.05, corrected by FDR method) in local regions, which belonged to multiple fiber tracts including cingulum bundle (CB), inferior occipito-frontal fasciculus (IoFF), corpus callosum (CC), external capsule (EC), uncinate fasciculus (UF), superior longitudinal fasciculus (SLF) and thalamo front (TF). We also found clusters that had relevance with clinical indices of cognitive function (2 clusters), athletic function (6 clusters), and depressive state (2 clusters) in these significant clusters. From the experiment results, it confirmed the ability of the proposed method to identify potential WM microstructure abnormality.

Study on Immune Response of Organs of Epinephelus coioides and Carassius auratus After Immersion Vaccination With Inactivated Vibrio harveyi Vaccine.

Immersion vaccination relies on the response of fish mucosa-associated lymphoid tissues, the Crucian carp (Carassius auratus) and Grouper (Epinephelus coioides) were researched in this paper to examine local mucosal immune responses and associated humoral system responses following immersion vaccination. We administered 1.5 × 107 CFU/ml formalin-inactivated Vibrio harveyi cells and measured mucus and serum antibody titers as well as IgM, MHC II mRNA levels in immune organs. The mucosal antibody response preceded the serum response indicating a role for local mucosal immunity in immersion vaccination. IgM and MHC II mRNA levels were relatively greater for the spleen and head kidney indicating the importance and central position of systemic immunity. Expression levels were also high for the gills while skin levels were the lowest. IgM and MHC II mRNA levels were altered over time following vaccination and the hindgut, liver and spleen were similar indicating a close relationship, so the absolute value of r is used to analyze the correlation among different organs immunized. It can be inferred the existence of an internal immune molecular mechanism for Immune synergy hindgut-liver-spleen, from the peak time (14th day), the relative ratio of genes expression in the same tissues between the immunized grouper and the control group (26 times), and Pearson correlation coefficient (0.8<|r|<1). Injection challenges with live V. harveyi indicated that the relative protection rates for the crucian carp and Grouper was basically the same at 44.4% and 47.4%, respectively. It is believe that crucian carp may be used as a substitute for the valuable grouper in immunity experiment, just from aspect of the relative percent survival (RPS) and how it changes with time. But they were not consistent about the IgM mRNA expression between that of crucian carp and grouper after immersion the Vibrio vaccine.