Enhanced exon skipping and prolonged dystrophin restoration achieved by TfR1-targeted delivery of antisense oligonucleotide using FORCE conjugation in mdx mice.

Current therapies for Duchenne muscular dystrophy (DMD) use phosphorodiamidate morpholino oligomers (PMO) to induce exon skipping in the dystrophin pre-mRNA, enabling the translation of a shortened but functional dystrophin protein. This strategy has been hampered by insufficient delivery of PMO to cardiac and skeletal muscle. To overcome these limitations, we developed the FORCETM platform consisting of an antigen-binding fragment, which binds the transferrin receptor 1, conjugated to an oligonucleotide. We demonstrate that a single dose of the mouse-specific FORCE-M23D conjugate enhances muscle delivery of exon skipping PMO (M23D) in mdx mice, achieving dose-dependent and robust exon skipping and durable dystrophin restoration. FORCE-M23D-induced dystrophin expression reached peaks of 51%, 72%, 62%, 90% and 77%, of wild-type levels in quadriceps, tibialis anterior, gastrocnemius, diaphragm, and heart, respectively, with a single 30 mg/kg PMO-equivalent dose. The shortened dystrophin localized to the sarcolemma, indicating expression of a functional protein. Conversely, a single 30 mg/kg dose of unconjugated M23D displayed poor muscle delivery resulting in marginal levels of exon skipping and dystrophin expression. Importantly, FORCE-M23D treatment resulted in improved functional outcomes compared with administration of unconjugated M23D. Our results suggest that FORCE conjugates are a potentially effective approach for the treatment of DMD.

The biggest problem confronting oligonucleotide therapeutics is a lack of compounds capable of targeting compounds to diseased tissues. This paper reports a major advance targeting the transferrin receptor to increase the delivery of morpholine oligomers to muscle cells in vivo. This work suggests the possibility for improved treatments of muscular dystrophy and other diseases.

After-school nutrition education programme improves eating behaviour in economically disadvantaged adolescents.

OBJECTIVE: To investigate whether an after-school nutrition education (ASNE) programme can improve the nutrition knowledge and healthy eating behaviour of adolescents from economically disadvantaged families. DESIGN: One-group pretest and posttest design. Nutrition knowledge and dietary intake were collected using a questionnaire, and anthropometric measurements were measured before and after the intervention. Nine components of healthy eating behaviour were assessed with reference to the Dietary Guideline of Taiwan. Pretest and posttest differences were analysed using generalised estimating equations. SETTING: Three after-school programmes in central and southern Taiwan. The ASNE programme comprised three monthly 1-h sessions (20-30-min lecture and 30-40-min interaction). PARTICIPANTS: A total of 153 adolescents aged 10-15 years from economically disadvantaged families (seventy-eight elementary students and seventy-five junior high school students). RESULTS: Elementary and junior high school students' nutrition knowledge scores (range 0-6) increased by 0·28 (+ 5·7 %, P = 0·02) and 0·30 points (+ 6·18 %, P = 0·02), respectively, but their fruit intake decreased by 0·36 serving/d (-22·9 %, P = 0·02) and 0·29 serving/d (-18·9 %, P = 0·03), respectively. Junior high school students' mean snacking frequency and fried food intake dropped to 0·75 d/week (-21·3 %, P = 0·008) and 0·10 serving/d (-28·8 %, P = 0·01), respectively. CONCLUSIONS: Short-term ASNE programmes can increase nutrition knowledge and reduce snacking frequency and fried food intake despite a decrease in fruit intake among adolescents from economically disadvantaged families.

p-Coumaric acid improves oxidative and osmosis stress responses in Caenorhabditis elegans.

BACKGROUND: Stress-response pathways in Caenorhabditis elegans (C. elegans) were found to be closely related to human diseases and aging. Research on stress responses in C. elegans can therefore significantly facilitate understanding of related human diseases. p-Coumaric acid is present in peanuts, carrots, and garlic, and exerts many biological effects, however, its responses to various environmental stressors remain unknown. Thus, in the current study, we employed C. elegans as the in vivo animal model to examine the function of p-coumaric acid under various stressed conditions. RESULTS: Treatment of C. elegans with p-coumaric acid resulted in a significant reduction in the intercellular reactive oxygen species levels, which suggests the in vivo antioxidant capacity of p-coumaric acid. Moreover, p-coumaric acid significantly increased the worms' survival under oxidative and osmosis stressed conditions but had no effect under normal or heat-stressed conditions. The increased oxidative resistance induced by p-coumaric acid was mediated by skn-1, an ortholog of the Nrf2 (nuclear factor erythroid 2-related factor 2) transcriptional factor. Downregulation of the osmosis regulatory gene, osr-1, might contribute to p-coumaric acids' effect on increased resistance to high osmolarity. CONCLUSION: Taken together, our results suggest that p-coumaric acid, an antioxidant agent, ameliorated oxidative and osmosis stresses in C. elegans. © 2018 Society of Chemical Industry.

A living model for obesity and aging research: Caenorhabditis elegans.

Caenorhabditis elegans (C. elegans) is a free-living nematode that has been extensively utilized as an animal model for research involving aging and neurodegenerative diseases, like Alzheimer's and Parkinson's, etc. Compared with traditional animal models, this small nematode possesses many benefits, such as small body size, short lifespan, completely sequenced genome, and more than 65% of the genes associated with human disease. All these characteristics make this organism an ideal living system for obesity and aging studies. This review gives a brief introduction of C. elegans as an animal model, highlights some advantages of research using this model and describes methods to evaluate the effect of treatments on obesity and aging of this organism.

An Online Continuous Human Action Recognition Algorithm Based on the Kinect Sensor.

Continuous human action recognition (CHAR) is more practical in human-robot interactions. In this paper, an online CHAR algorithm is proposed based on skeletal data extracted from RGB-D images captured by Kinect sensors. Each human action is modeled by a sequence of key poses and atomic motions in a particular order. In order to extract key poses and atomic motions, feature sequences are divided into pose feature segments and motion feature segments, by use of the online segmentation method based on potential differences of features. Likelihood probabilities that each feature segment can be labeled as the extracted key poses or atomic motions, are computed in the online model matching process. An online classification method with variable-length maximal entropy Markov model (MEMM) is performed based on the likelihood probabilities, for recognizing continuous human actions. The variable-length MEMM method ensures the effectiveness and efficiency of the proposed CHAR method. Compared with the published CHAR methods, the proposed algorithm does not need to detect the start and end points of each human action in advance. The experimental results on public datasets show that the proposed algorithm is effective and highly-efficient for recognizing continuous human actions.

A Fast Robot Identification and Mapping Algorithm Based on Kinect Sensor.

Internet of Things (IoT) is driving innovation in an ever-growing set of application domains such as intelligent processing for autonomous robots. For an autonomous robot, one grand challenge is how to sense its surrounding environment effectively. The Simultaneous Localization and Mapping with RGB-D Kinect camera sensor on robot, called RGB-D SLAM, has been developed for this purpose but some technical challenges must be addressed. Firstly, the efficiency of the algorithm cannot satisfy real-time requirements; secondly, the accuracy of the algorithm is unacceptable. In order to address these challenges, this paper proposes a set of novel improvement methods as follows. Firstly, the ORiented Brief (ORB) method is used in feature detection and descriptor extraction. Secondly, a bidirectional Fast Library for Approximate Nearest Neighbors (FLANN) k-Nearest Neighbor (KNN) algorithm is applied to feature match. Then, the improved RANdom SAmple Consensus (RANSAC) estimation method is adopted in the motion transformation. In the meantime, high precision General Iterative Closest Points (GICP) is utilized to register a point cloud in the motion transformation optimization. To improve the accuracy of SLAM, the reduced dynamic covariance scaling (DCS) algorithm is formulated as a global optimization problem under the G2O framework. The effectiveness of the improved algorithm has been verified by testing on standard data and comparing with the ground truth obtained on Freiburg University's datasets. The Dr Robot X80 equipped with a Kinect camera is also applied in a building corridor to verify the correctness of the improved RGB-D SLAM algorithm. With the above experiments, it can be seen that the proposed algorithm achieves higher processing speed and better accuracy.

Impact of thermal treatment on proanthocyanidin-pectin binary complexes: Insights from structural, rheological, antioxidant, and astringent properties.

In this study, the effects of thermal treatments on the structural, rheological, water mobility, antioxidant, and astringency properties of proanthocyanidin (PA)-pectin binary complexes were investigated. Thermal treatments (25, 63, or 85 °C) significantly decreased the particle size but increased the molecular weight of PA-pectin complexes, which indicated that heating altered the intermolecular and intramolecular interactions between PA and pectin. The thermal treatments reduced the apparent viscosity of both pectin and PA-pectin complexes, but the presence of proanthocyanidins (PAs) increased the apparent viscosity and water mobility of the PA-pectin complexes. Antioxidant activity analysis showed that the presence of pectin slightly reduced the antioxidant activity of the PAs, but there were no significant changes in the total phenolic content and antioxidant activity after thermal treatment. Finally, we found that pectin reduced the astringency of the PAs by forming PA-pectin complexes. Moreover, the thermal treatments also significantly reduced the astringency of the PA-pectin complexes.

The Association Between Absolute Lymphocyte Count and Long-Term Mortality in Critically Ill Medical Patients: Propensity Score-Based Analyses.

Objective: Absolute lymphocyte count (ALC) has been implicated with short-term outcomes in a number of diseases, and we aimed to investigate the association between week-one ALC and long-term mortality in patients who were admitted to the medical intensive care units (ICUs). Methods: We enrolled patients who were admitted to the medical ICUs at the Taichung Veterans General Hospital, a referral centre located in central Taiwan, between 2015 and 2020 to conduct this retrospective cohort study. The outcome of interest was long-term all-cause mortality, and hazard ratios (HRs) with 95% confidence intervals (CIs) were calculated to determine the association. Furthermore, we employed propensity score-matching (PSM) and weighting techniques, consisting of inverse probability of treatment weighting (IPTW) and covariate balancing propensity score (CBPS), to confirm the association between ALC and mortality. Results: A total of 5722 critically ill patients were enrolled, and the one-year mortality was 44.8%. The non-survivor group had a lower ALC (1549, 1027-2388 vs 1948, 1373-2743 counts/µL, p<0.01) compared with those in the survivor group. Cox regression showed that low ALC was independently associated with mortality (adjHR 1.091, 95% CI 1.050-1.134). Propensity score-based analyses demonstrated the robust association, with adjHRs in the original, PSM, IPTW, and CBPS populations of 1.327 (95% CI 1.224-1.438), 1.301 (95% CI 1.188-1.424), 1.292 (95% CI 1.186-1.407), and 1.297 (95% CI 1.191-1.412), respectively. Sensitivity analyses further showed that the association between low ALC and mortality existed in a dose-response manner. Conclusion: We found that low ALC was associated with long-term mortality in critically ill patients; further studies are warranted to validate and translate these findings into clinical utility.

Effects of pile fermentation on the physicochemical, functional, and biological properties of tea polysaccharides.

This study investigated the influence of pile fermentation on the physicochemical, functional, and biological properties of tea polysaccharides (TPS). Results indicated that the extraction yield, uronic acid content, and polyphenol content of TPS greatly increased from 1.8, 13.1 and 6.3 % to 4.1, 27.9, and 7.8 %, respectively, but the molecular weight markedly decreased from 153.7 to 76.0 kDa after pile fermentation. Additionally, the interfacial, emulsion formation, and emulsion stabilization properties of TPS were significantly improved after pile fermentation. For instance, 1.0 wt% TPS isolated from dark tea (D-TPS) can fabricate 8.0 wt% MCT oil-in-water nanoemulsion (d32 ≈ 159 nm) with potent storage stability. Moreover, the antioxidant and α-glucosidase inhibitory activities of D-TPS was higher than that of TPS isolated from sun-dried raw tea (R-TPS). Overall, this study indicated that pile fermentation markedly affected the physicochemical and structural characteristics of TPS, thereby improving their functional and biological properties.

Enhancement of lycopene bioaccessibility in tomatoes using excipient emulsions: Effect of dark tea polysaccharides.

This study fabricated a novel excipient emulsion by adding dark tea polysaccharides to improve the bioaccessibility of lycopene from tomatoes. Results indicated that addition of tea polysaccharides greatly increased the antioxidant activity of excipient emulsions. Additionally, tea polysaccharides markedly improved the physical stability of excipient emulsion when being mixed with tomato puree and passing through a simulated gastrointestinal tract, contributing to an increase in electrostatic and steric repulsion between the droplets. Besides, certain amount of tea polysaccharides (0.05 - 0.2 wt%) could increase the rate and extent of lipid digestion in tomato-emulsion mixtures. Finally, lycopene bioaccessibility was significantly increased (from 16.95 % to 26.21 %) when 0.1 wt% tea polysaccharides were included, which was mainly ascribed to the ability of tea polysaccharides to increase lipid digestion and reduce carotenoid oxidation within the gastrointestinal tract. These results suggest that well-designed excipient emulsions may increase carotenoids bioavailability in the complex food matrices.

Reinforcing alginate matrixes by tea polysaccharide conjugates or their stabilized nanoemulsion for probiotics encapsulation: Characterization, survival after gastrointestinal digestion and ambient storage.

Tea polysaccharide conjugates (TPC) were used as fillers in the form of biopolymer or colloidal particles (TPC stabilized nanoemulsion, NE) for reinforcing alginate (ALG) beads to improve the probiotic viability. Results demonstrated that adding TPC or NE to ALG beads significantly enhanced the gastrointestinal viability of encapsulated probiotics when compared to free cells. Moreover, the survivability of free and ALG encapsulated probiotics markedly decreased to 2.03 ± 0.05 and 2.26 ± 0.24 log CFU/g, respectively, after 2 weeks ambient storage, indicating pure ALG encapsulation had no effective storage protective capability. However, adding TPC or NE could greatly enhance the ambient storage viability of probiotics, with ALG + NE beads possessing the best protection (8.93 ± 0.06 log CFU/g) due to their lower water activity and reduced porosity. These results suggest that TPC and NE reinforced ALG beads have the potential to encapsulate, protect and colonic delivery of probiotics.

Predicting isocitrate dehydrogenase genotype, histological phenotype, and Ki-67 expression level in diffuse gliomas with an advanced contrast analysis of magnetic resonance imaging sequences.

Background: The present study aimed to establish a robust predictive model based on a machine learning (ML) algorithm providing preoperative noninvasive diagnosis and to further explore the contribution of each magnetic resonance imaging (MRI) sequence to the classification to help select images for future model development. Methods: This was a retrospective cross-sectional study, and consecutive patients with histologically confirmed diffuse gliomas in our hospital from November 2015 to October 2019 were recruited. The participants were grouped into a training and testing set based on a ratio of 8:2. Five MRI sequences were employed to develop the support vector machine (SVM) classification model. An advanced contrast analysis of single-sequence-based classifiers was performed, according to which different sequence combinations were tested, and the best one was selected to form an ultimate classifier. Patients whose MRIs were acquired with other types of scanners formed an additional, independent validation set. Results: A total of 150 patients with gliomas were used in the present study. Contrast analysis revealed that the contribution of the apparent diffusion coefficient (ADC) was the most significant [accuracies were as follows: histological phenotype, 0.640; isocitrate dehydrogenase (IDH) status, 0.656; and Ki-67 expression, 0.699] and that of T1 weighted imaging was limited (accuracies were as follows: histological phenotype, 0.521; IDH status, 0.492; and Ki-67 expression, 0.556). The ultimate classifiers for IDH status, histological phenotype, and Ki-67 expression achieved promising performances with area under the curve (AUC) values of 0.88, 0.93, and 0.93, respectively. The classifiers for the histological phenotype, IDH status, and Ki-67 expression correctly predicted 3 of 5 subjects, 6 of 7 subjects, and 9 of 13 subjects in the additional validation set, respectively. Conclusions: The present study showed satisfactory performance in predicting the IDH genotype, histological phenotype, and Ki-67 expression level. The contrast analysis revealed the contribution of different MRI sequences and suggested that the combination of all the acquired sequences was not the optimal strategy to build the radiogenomics-based classifier.

Thermally Induced Covalent Cross-Linking of Proanthocyanidins and Pectin in Processed Fruit-Based Foods.

The covalent interactions between proanthocyanidins (PAs) and pectin during thermal processing was investigated. An acid-butanol assay clearly showed that PAs were covalently bound to pectin. Computational studies indicated that a nucleophilic substitution reaction occurred between the carbocation generated by the PAs and carboxyl or hydroxyl groups on the pectin, leading to the formation of PAs-pectin adducts. Thermal processing and PAs significantly affected the physicochemical, functional, and biological properties of pectin. Thermal processing reduced the molecular weight and increased the gelling properties of pectin, whereas PAs increased both the molecular weight and the gelling properties. Finally, we found that the covalent attachment of PAs to pectin greatly enhanced its antioxidant, prebiotic, and α-glucosidase inhibitory activity. Overall, our results suggest that the thermal processing of fruits has the potential to induce a covalent interaction between PAs and pectin, which would impact the physicochemical characteristics and functional properties of pectin.

Extraction and characterization of pectic polysaccharides from Choerospondias axillaris peels: Comparison of hot water and ultrasound-assisted extraction methods.

Influences of conventional thermal and innovative non-thermal extraction methods on the physicochemical characteristics and properties of pectic polysaccharides from Choerospondias axillaris peels were investigated. Results showed that ultrasound-assisted extracted polysaccharides (UP) had a heterogeneous nature with lower molecular weight (127.7 kDa) and lower neutral sugar content (35.1%) but higher contents of protein (4.8%) and phenolic compounds (5.1%) than those of polysaccharides extracted by hot water (HP). Additionally, the monosaccharide composition results showed that glucose (77.8%) was the most abundant monosaccharide in HP, while arabinose (67.1%) was the most abundant monosaccharide in UP. The ultrasound significantly induced the degradation of polysaccharide chains but reduced the thermal degradation of phenolics. Finally, we found that UP had higher apparent viscosity, interfacial, emulsifying and antioxidant activity but lower α-glucosidase inhibition activity than those of HP. The results indicated that we could obtain polysaccharides with different functional and biological properties by using different extraction methods.

Ultracentrifugal milling and steam heating pretreatment improves structural characteristics, functional properties, and in vitro binding capacity of cellulase modified soy okara residues.

Soy okara contains high levels of insoluble dietary fiber (IDF). The objective of this work is to investigate the composition, structure changes, and functionality of okara residues after the modification by ultracentrifugal milling (M), milling + steam heating (M + S), or milling + steam heating + enzymatic (M + S + E) treatment. The results showed that the combination of M + S could significantly convert okara IDF into soluble ones, and the highest conversion rate (59%) was achieved with the smallest size (147 µm). The structural characterization revealed that size reduction altered the functional groups and crystallinity of the modified okara residues with irregular and enlarged morphology. More importantly, the functionalities, including water and oil holding capacities, swelling capacity, as well as cholesterol and bile acid binding capacities were improved remarkably in okara residues pretreated by M + S prior to cellulase hydrolysis. The findings provide new insights on the effective biotransformation of okara into valuable food ingredients.

MEDAS: an open-source platform as a service to help break the walls between medicine and informatics.

In the past decade, deep learning (DL) has achieved unprecedented success in numerous fields, such as computer vision and healthcare. Particularly, DL is experiencing an increasing development in advanced medical image analysis applications in terms of segmentation, classification, detection, and other tasks. On the one hand, tremendous needs that leverage DL's power for medical image analysis arise from the research community of a medical, clinical, and informatics background to share their knowledge, skills, and experience jointly. On the other hand, barriers between disciplines are on the road for them, often hampering a full and efficient collaboration. To this end, we propose our novel open-source platform, i.e., MEDAS-the MEDical open-source platform As Service. To the best of our knowledge, MEDAS is the first open-source platform providing collaborative and interactive services for researchers from a medical background using DL-related toolkits easily and for scientists or engineers from informatics modeling faster. Based on tools and utilities from the idea of RINV (Rapid Implementation aNd Verification), our proposed platform implements tools in pre-processing, post-processing, augmentation, visualization, and other phases needed in medical image analysis. Five tasks, concerning lung, liver, brain, chest, and pathology, are validated and demonstrated to be efficiently realizable by using MEDAS. MEDAS is available at http://medas.bnc.org.cn/.

Caenorhabditis elegans as a model for obesity research.

Caenorhabditis elegans, a free-living nematode, is an animal model that has been extensively employed in a variety of research fields, including in the study of obesity. Its favorable features include its compact size, short life cycle, large brood size, easy handling, low cost, availability of complete genetic information, 65% conserved human diseases-associated genes, relatively easy genetic manipulation, and research using Caenorhabditis elegans does not require approvals by the Institutional Animal Care and Use Committee. These advantages make Caenorhabditis elegans a great in vivo model for life science research including obesity research. In this review, we provide graphic overviews of Caenorhabditis elegans' basic anatomy, growth conditions, routes of compound delivery, and fat metabolism, both synthesis and degradation pathways, including major signaling pathways involved. Our aim is to provide an overview for researchers interested in applying C. elegans as an in vivo model for the screening and identification of anti-obesity bioactive compounds prior to testing in vertebrate animal models.

Methylglyoxal influences development of Caenorhabditis elegans via lin-41-dependent pathway.

Methylglyoxal is a highly reactive dicarbonyl compound. It can be obtained either endogenously through biological enzymatic/non-enzymatic pathways or exogenously via the uptake of certain foods and beverages, such as Manuka honey. Studies about its biological properties are quite controversial, though the majority reported a positive association between methylglyoxal and certain pathologies. In this report, we tested if methylglyoxal can alter the development of animals using Caenorhabditis elegans as the in vivo model. Treatment of methylglyoxal at 0.1 and 1 mmol/L for 2 days significantly inhibited the development of Caenorhabditis elegans, particularly targeting the transition from L3 stage. Pharyngeal pumping rate, the food intake marker was also significantly reduced by methylglyoxal at both 0.1 and 1 mmol/L. Additionally, treatment of 0.1 mmol/L methylglyoxal increased, while 1 mmol/L methylglyoxal decreased the nematodes' average moving speed. The effect of methylglyoxal on development was in part due to the modulation of lin-41, which encodes a homolog of human TRIM71. The mutation of lin-41 could alleviate or abolish the effects of methylglyoxal on growth rate, body size, pumping rate and locomotive activity. In summary, these results suggested that methylglyoxal influenced the development of Caenorhabditis elegans, which is in part via the lin-41-dependent pathway.

An Effective Multimodal Image Fusion Method Using MRI and PET for Alzheimer's Disease Diagnosis.

Alzheimer's disease (AD) is an irreversible brain disease that severely damages human thinking and memory. Early diagnosis plays an important part in the prevention and treatment of AD. Neuroimaging-based computer-aided diagnosis (CAD) has shown that deep learning methods using multimodal images are beneficial to guide AD detection. In recent years, many methods based on multimodal feature learning have been proposed to extract and fuse latent representation information from different neuroimaging modalities including magnetic resonance imaging (MRI) and 18-fluorodeoxyglucose positron emission tomography (FDG-PET). However, these methods lack the interpretability required to clearly explain the specific meaning of the extracted information. To make the multimodal fusion process more persuasive, we propose an image fusion method to aid AD diagnosis. Specifically, we fuse the gray matter (GM) tissue area of brain MRI and FDG-PET images by registration and mask coding to obtain a new fused modality called "GM-PET." The resulting single composite image emphasizes the GM area that is critical for AD diagnosis, while retaining both the contour and metabolic characteristics of the subject's brain tissue. In addition, we use the three-dimensional simple convolutional neural network (3D Simple CNN) and 3D Multi-Scale CNN to evaluate the effectiveness of our image fusion method in binary classification and multi-classification tasks. Experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset indicate that the proposed image fusion method achieves better overall performance than unimodal and feature fusion methods, and that it outperforms state-of-the-art methods for AD diagnosis.

Multi-Modal Co-Learning for Liver Lesion Segmentation on PET-CT Images.

Liver lesion segmentation is an essential process to assist doctors in hepatocellular carcinoma diagnosis and treatment planning. Multi-modal positron emission tomography and computed tomography (PET-CT) scans are widely utilized due to their complementary feature information for this purpose. However, current methods ignore the interaction of information across the two modalities during feature extraction, omit the co-learning of the feature maps of different resolutions, and do not ensure that shallow and deep features complement each others sufficiently. In this paper, our proposed model can achieve feature interaction across multi-modal channels by sharing the down-sampling blocks between two encoding branches to eliminate misleading features. Furthermore, we combine feature maps of different resolutions to derive spatially varying fusion maps and enhance the lesions information. In addition, we introduce a similarity loss function for consistency constraint in case that predictions of separated refactoring branches for the same regions vary a lot. We evaluate our model for liver tumor segmentation using a PET-CT scans dataset, compare our method with the baseline techniques for multi-modal (multi-branches, multi-channels and cascaded networks) and then demonstrate that our method has a significantly higher accuracy ( ) than the baseline models.