Deep Learning Combined with Radiologist's Intervention Achieves Accurate Segmentation of Hepatocellular Carcinoma in Dual-Phase Magnetic Resonance Images.

Purpose: Segmentation of hepatocellular carcinoma (HCC) is crucial; however, manual segmentation is subjective and time-consuming. Accurate and automatic lesion contouring for HCC is desirable in clinical practice. In response to this need, our study introduced a segmentation approach for HCC combining deep convolutional neural networks (DCNNs) and radiologist intervention in magnetic resonance imaging (MRI). We sought to design a segmentation method with a deep learning method that automatically segments using manual location information for moderately experienced radiologists. In addition, we verified the viability of this method to assist radiologists in accurate and fast lesion segmentation. Method: In our study, we developed a semiautomatic approach for segmenting HCC using DCNN in conjunction with radiologist intervention in dual-phase gadolinium-ethoxybenzyl-diethylenetriamine penta-acetic acid- (Gd-EOB-DTPA-) enhanced MRI. We developed a DCNN and deep fusion network (DFN) trained on full-size images, namely, DCNN-F and DFN-F. Furthermore, DFN was applied to the image blocks containing tumor lesions that were roughly contoured by a radiologist with 10 years of experience in abdominal MRI, and this method was named DFN-R. Another radiologist with five years of experience (moderate experience) performed tumor lesion contouring for comparison with our proposed methods. The ground truth image was contoured by an experienced radiologist and reviewed by an independent experienced radiologist. Results: The mean DSC of DCNN-F, DFN-F, and DFN-R was 0.69 ± 0.20 (median, 0.72), 0.74 ± 0.21 (median, 0.77), and 0.83 ± 0.13 (median, 0.88), respectively. The mean DSC of the segmentation by the radiologist with moderate experience was 0.79 ± 0.11 (median, 0.83), which was lower than the performance of DFN-R. Conclusions: Deep learning using dual-phase MRI shows great potential for HCC lesion segmentation. The radiologist-aided semiautomated method (DFN-R) achieved improved performance compared to manual contouring by the radiologist with moderate experience, although the difference was not statistically significant.

Discrepancy between inter- and intra-subject variability in EEG-based motor imagery brain-computer interface: Evidence from multiple perspectives.

Introduction: Inter- and intra-subject variability are caused by the variability of the psychological and neurophysiological factors over time and across subjects. In the application of in Brain-Computer Interfaces (BCI), the existence of inter- and intra-subject variability reduced the generalization ability of machine learning models seriously, which further limited the use of BCI in real life. Although many transfer learning methods can compensate for the inter- and intra-subject variability to some extent, there is still a lack of clear understanding about the change of feature distribution between the cross-subject and cross-session electroencephalography (EEG) signal. Methods: To investigate this issue, an online platform for motor-imagery BCI decoding has been built in this work. The EEG signal from both the multi-subject (Exp1) and multi-session (Exp2) experiments has been analyzed from multiple perspectives. Results: Firstly we found that with the similar variability of classification results, the time-frequency response of the EEG signal within-subject in Exp2 is more consistent than cross-subject results in Exp1. Secondly, the standard deviation of the common spatial pattern (CSP) feature has a significant difference between Exp1 and Exp2. Thirdly, for model training, different strategies for the training sample selection should be applied for the cross-subject and cross-session tasks. Discussion: All these findings have deepened the understanding of inter- and intra-subject variability. They can also guide practice for the new transfer learning methods development in EEG-based BCI. In addition, these results also proved that BCI inefficiency was not caused by the subject's unable to generate the event-related desynchronization/synchronization (ERD/ERS) signal during the motor imagery.

To explore the mechanism of tobacco addiction using structural and functional MRI: a preliminary study of the role of the cerebellum-striatum circuit.

Previous studies have found that the striatum and the cerebellum played important roles in nicotine dependence, respectively. In heavy smokers, however, the effect of resting-state functional connectivity of cerebellum-striatum circuits in nicotine dependence remained unknown. This study aimed to explore the role of the circuit between the striatum and the cerebellum in addiction in heavy smokers using structural and functional magnetic resonance imaging. The grey matter volume differences and the resting-state functional connectivity differences in cerebellum-striatum circuits were investigated between 23 heavy smokers and 23 healthy controls. The cigarette dependence in heavy smokers and healthy controls were evaluated by using Fagerström Test. Then, we applied mediation analysis to test whether the resting-state functional connectivity between the striatum and the cerebellum mediates the relationship between the striatum morphometry and the nicotine dependence in heavy smokers. Compared with healthy controls, the heavy smokers' grey matter volumes decreased significantly in the cerebrum (bilateral), and increased significantly in the caudate (bilateral). Seed-based resting-state functional connectivity analysis showed significantly higher resting-state functional connectivity among the bilateral caudate, the left cerebellum, and the right middle temporal gyrus in heavy smokers. The cerebellum-striatum resting-state functional connectivity fully mediated the relationship between the striatum morphometry and the nicotine dependence in heavy smokers. Heavy smokers showed abnormal interactions and functional connectivity between the striatum and the cerebellum, which were associated with the striatum morphometry and nicotine dependence. Such findings could provide new insights into the neural correlates of nicotine dependence in heavy smokers.

Prenatal inflammation exposure-programmed hypertension exhibits multi-generational inheritance via disrupting DNA methylome.

The multi-generation heredity trait of hypertension in human has been reported, but the molecular mechanisms underlying multi-generational inheritance of hypertension remain obscure. Recent evidence shows that prenatal inflammatory exposure (PIE) results in increased incidence of cardiovascular diseases, including hypertension. In this study we investigated whether and how PIE contributed to multi-generational inheritance of hypertension in rats. PIE was induced in pregnant rats by intraperitoneal injection of LPS or Poly (I:C) either once on gestational day 10.5 (transient stimulation, T) or three times on gestational day 8.5, 10.5, and 12.5 (persistent stimulation, P). Male offspring was chosen to study the paternal inheritance. We showed that PIE, irrespectively induced by LPS or Poly (I:C) stimulation during pregnancy, resulted in multi-generational inheritance of significantly increased blood pressure in rat descendants, and that prenatal LPS exposure led to vascular remodeling and vasoconstrictor dysfunction in both thoracic aorta and superior mesenteric artery of adult F2 offspring. Furthermore, we revealed that PIE resulted in global alteration of DNA methylome in thoracic aorta of F2 offspring. Specifically, PIE led to the DNA hypomethylation of G beta gamma (Gßγ) signaling genes in both the F1 sperm and the F2 thoracic aorta, and activation of PI3K/Akt signaling was implicated in the pathologic changes and dysregulated vascular tone of aortic tissue in F2 LPS-P offspring. Our data demonstrate that PIE reprogrammed DNA methylome of cells from the germline/mature gametes contributes to the development of hypertension in F2 PIE offspring. This study broadens the current knowledge regarding the multi-generation effect of the cumulative early life environmental factors on the development of hypertension.

Mortality prediction for patients with acute respiratory distress syndrome based on machine learning: a population-based study.

BACKGROUND: Traditional scoring systems for patients' outcome prediction in intensive care units such as Oxygenation Saturation Index (OSI) and Oxygenation Index (OI) may not reliably predict the clinical prognosis of patients with acute respiratory distress syndrome (ARDS). Thus, none of them have been widely accepted for mortality prediction in ARDS. This study aimed to develop and validate a mortality prediction method for patients with ARDS based on machine learning using the Medical Information Mart for Intensive Care (MIMIC-III) and Telehealth Intensive Care Unit (eICU) Collaborative Research Database (eICU-CRD) databases. METHODS: Patients with ARDS were selected based on the Berlin definition in MIMIC-III and eICU-CRD databases. The APPS score (using age, PaO2/FiO2, and plateau pressure), Simplified Acute Physiology Score II (SAPS-II), Sepsis-related Organ Failure Assessment (SOFA), OSI, and OI were calculated. With MIMIC-III data, a mortality prediction model was built based on the random forest (RF) algorithm, and the performance was compared to those of existing scoring systems based on logistic regression. The performance of the proposed RF method was also validated with the combined MIMIC-III and eICU-CRD data. The performance of mortality prediction was evaluated by using the area under the receiver operating characteristics curve (AUROC) and performing calibration using the Hosmer-Lemeshow test. RESULTS: With the MIMIC-III dataset (308 patients, for comparisons with the existing scoring systems), the RF model predicted the in-hospital mortality, 30-day mortality, and 1-year mortality with an AUROC of 0.891, 0.883, and 0.892, respectively, which were significantly higher than those of the SAPS-II, APPS, OSI, and OI (all P<0.001). In the multi-source validation (the combined dataset of 2,235 patients in MIMIC-III and 331 patients in eICU-CRD), the RF model achieved an AUROC of 0.905 and 0.736 for predicting in-hospital mortality for the MIMIC-III and eICU-CRD datasets, respectively. The calibration plots suggested good fits for our RF model and these scoring systems for predicting mortality. The platelet count and lactate level were the strongest predictive variables for predicting in-hospital mortality. CONCLUSIONS: Compared to the existing scoring systems, machine learning significantly improved performance for predicting ARDS mortality. Validation with multi-source datasets showed a relatively robust generalisation ability of our prediction model.

Analysis of the primary presenting symptoms and hematological findings of COVID-19 patients in Bangladesh.

INTRODUCTION: SARS-Cov-2 infection or COVID-19 is a global pandemic. In this manuscript, we investigated the primary symptoms and basic hematological presentations of SARS-CoV-2 infection among the Bangladeshi patients. METHODOLOGY: This was a multicentre cross-sectional study done on COVID-19 patients tested positive by RT PCR in Bangladesh. Clinical features of mild to moderate degree of COVID-19 patients; hematological and biochemical admission day laboratory findings of moderate to severe degree hospitalized COVID-19 patients were analyzed. RESULTS: COVID-19 patients in Bangladesh commonly presented with fever, cough, fatigue, shortness of breath, and sore throat. But symptoms like myalgia, diarrhea, skin rash, headache, Abdominal pain/cramp, nausea, vomiting, restlessness, and a higher temperature of >100°F have a greater presentation rate and more frequent than other published studies. CRP and Prothrombin time was found to increase in all the patients. Serum ferritin, ESR, SGPT, and D-Dimer were increased among 53.85%, 80.43, 44%, and 25% patients. 17.39% of the patients had leucocytosis and neutrophilia, 28.26% presented with lymphocytopenia, and 62.52% had mild erythrocytopenia. The difference between the decrease hemoglobin count (higher in the male) and increased SGPT (higher in female) against gender was significant. CONCLUSIONS: Our study had evaluated a different expression in presenting symptoms of COVID-19 patients in Bangladesh. CRP, Prothrombin time, serum ferritin, ESR, SGPT, D-Dimer, erythrocytopenia, and lymphocytopenia can be assessments for diagnosis and prognosis of COVID-19 disease. Decrease hemoglobin count (higher in the male) and increased SGPT (higher in female) establish these two markers as a good candidate for diagnostic value against gender.

Deep Semantic Segmentation Feature-Based Radiomics for the Classification Tasks in Medical Image Analysis.

Recently, an emerging trend in medical image classification is to combine radiomics framework with deep learning classification network in an integrated system. Although this combination is efficient in some tasks, the deep learning-based classification network is often difficult to capture an effective representation of lesion regions, and prone to face the challenge of overfitting, leading to unreliable features and inaccurate results, especially when the sizes of the lesions are small or the training dataset is small. In addition, these combinations mostly lack an effective feature selection mechanism, which makes it difficult to obtain the optimal feature selection. In this paper, we introduce a novel and effective deep semantic segmentation feature-based radiomics (DSFR) framework to overcome the above-mentioned challenges, which consists of two modules: the deep semantic feature extraction module and the feature selection module. Specifically, the extraction module is utilized to extract hierarchical semantic features of the lesions from a trained segmentation network. The feature selection module aims to select the most representative features by using a novel feature similarity adaptation algorithm. Experiments are extensively conducted to evaluate our method in two clinical tasks: the pathological grading prediction in pancreatic neuroendocrine neoplasms (pNENs), and the prediction of thrombolytic therapy efficacy in deep venous thrombosis (DVT). Experimental results on both tasks demonstrate that the proposed method consistently outperforms the state-of-the-art approaches by a large margin.

An LSTM-Based Prediction Method for Lower Limb Intention Perception by Integrative Analysis of Kinect Visual Signal.

Recently, computer vision and deep learning technology has been applied in various gait rehabilitation researches. Considering the long short-term memory (LSTM) network has been proved an excellent performance in learn sequence feature representations, we proposed a lower limb joint trajectory prediction method based on LSTM for conducting active rehabilitation on a rehabilitation robotic system. Our approach based on synergy theory exploits that the follow-up lower limb joint trajectory, i.e. limb intention, could be generated by joint angles of the previous swing process of upper limb which were acquired from Kinect platform, an advanced computer vision platform for motion tracking. A customize Kinect-Treadmill data acquisition platform was built for this study. With this platform, data acquisition on ten healthy subjects is processed in four different walking speeds to acquire the joint angles calculated by Kinect visual signals of upper and lower limb swing. Then, the angles of hip and knee in one side which were presented as lower limb intentions are predicted by the fore angles of the elbow and shoulder on the opposite side via a trained LSTM model. The results indicate that the trained LSTM model has a better estimation of predicting the lower limb intentions, and the feasibility of Kinect visual signals has been validated as well.

A comprehensive hierarchical classification based on multi-features of breast DCE-MRI for cancer diagnosis.

Computer-aided diagnosis (CAD) is widely used for early diagnosis of breast cancer. The commonly used morphological feature (MF), dynamic feature (DF), and texture feature (TF) from breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) have been proved very valuable and are studied in this paper. However, previous studies ignored the prior knowledge that most of the benign lesions have clearer and smoother edges than malignant ones. Therefore, two new TFs are proposed. To obtain an optimal feature subset and an accurate classification result, feature selection is applied in this paper. Moreover, most existing CAD models with simple structure only focus on common lesions and ignore hard-to-spot lesions so that a satisfied performance can be obtained for common lesions but there are some contradictions for those hard-to-spot lesions. Therefore, in this paper, a comprehensive hierarchical model is proposed to deal with contradictions and predict all kinds of lesions. The experimental result shows that the new features obviously increase ACC of TF from 0.7788 to 0.8584 and feature selection increases ACC of DF form 0.6991 to 0.7345. More importantly, compared with the existing CAD models and deep learning method, the proposed model which provides a higher performance for both common and hard-to-spot lesions significantly increases the classification performance with sensitivity of 0.9452 and specificity of 0.9000. Graphical abstract.

Using Eye Aspect Ratio to Enhance Fast and Objective Assessment of Facial Paralysis.

A rapid and objective assessment of the severity of facial paralysis allows rehabilitation physicians to choose the optimal rehabilitation treatment regimen for their patients. In this study, patients with facial paralysis were enrolled as study objects, and the eye aspect ratio (EAR) index was proposed for the eye region. The correlation between EAR and the facial nerve grading system 2.0 (FNGS 2.0) score was analyzed to verify the ability of EAR to enhance FNGS 2.0 for the rapid and objective assessment of the severity of the facial paralysis. Firstly, in order to accurately calculate the EAR, we constructed a landmark detection model based on the face images of facial paralysis patients (FP-FLDM). Evaluation results showed that the error rate of facial feature point detection in patients with facial paralysis of FP-FLDM is 17.1%, which was significantly superior to the landmark detection model based on normal face images (NF-FLDM). Secondly, in this study, the Fréchet distance was used to calculate the difference in bilateral EAR of facial paralysis patients and to verify the correlation between this difference and the corresponding FNGS 2.0 score. The results showed that the higher the FNGS 2.0 score , the greater the difference in bilateral EAR. The correlation coefficient between the bilateral EAR difference and the corresponding FNGS 2.0 score was 0.9673, indicating a high correlation. Finally, through a 10-fold crossvalidation, we can know that the accuracy of scoring the eyes of patients with facial paralysis using EAR was 85.7%, which can be used to enhance the objective and rapid assessment of the severity of facial paralysis by FNGS 2.0.

[Comparison of the effects of injured vertebra pedicle fixation combined with vertebroplasty and vertebra pedicle screw fixation combined with vertebroplasty in the treatment of osteoporotic thoracolumbar burst fractures].

OBJECTIVE: To assess the curative effects of injured vertebra pedicle fixation combined with vertebroplasty and short-segment pedicle screw fixation combined with vertebroplasty in treatment of osteoporotic thoracolumbar burst fractures. METHODS: Seventy patients with osteoporotic thoracolumbar burst fractures who met the inclusion criteria were collected in the study from January 2015 to December 2017. Among them, 35 patients were treated with injured vertebra pedicle fixation combined with vertebroplasty (group A), including 20 males and 15 females, aged from 55 to 74 years with an average of (64.03± 7.82) years. Twenty-six cases were type A3 and 9 cases were type A4 according to the AO typing;another 35 patients were treated with short segment pedicle screw fixation combined with vertebroplasty (group B), including 18 males and 17 females, aged from 54 to 72 years with an average of (62.78±6.40) years. Twenty-eight cases were type A3 and 7 cases were type A4 according to AO typing. Operation length, intraoperative bleeding volume, complication, imaging parameters and clinical effects were compared between the two groups. RESULTS: All the patients were followed up for at least 12 months. There were no significant differences in gender, age, injury site, preoperative VAS, Cobb angle, and injured vertebral height before surgery. There were no significant differences in operation length, intraoperative bleeding volume between two groups. In terms of VAS scores before surgery, 1 week after surgery, and at the final follow up, group A was 5.5 ±2.5, 1.8 ±0.8, 0.9 ±0.4, group B was 5.4 ± 2.3, 1.7±0.6, 1.2±1.8, respectively;injured vertebral height was (40.4±8.8)%, (92.0±4.9)%, (87.1±3.8)% in group A, and (41.2±6.6)%, (93.2±4.6)%, (80.0±4.3)% in group B;Cobb angle was (18.4±6.9) °, (2.8±2.2) °, (4.2±2.6) ° in group A, and (16.8±7.2) °, (2.7±2.5) °, (6.0±2.4) ° in group B. There were significant differences in the 3 parameters above before the operation and at the final follow up in all groups (P<0.05). There were significant differences in the Cobb angle and injured vertebral height between 1 week after operation and at the final follow up (P<0.05). At the final follow up, injured vertebral height in group A was obviously better than that in group B (P<0.05). Internal fixation failure occurred in 2 cases from the group A, and occurred in 4 cases from the group B. There were no neurological complications in both groups. CONCLUSION: For osteoporotic thoracolumbar vertebral burst fractures, injured vertebra pedicle fixation combined with vertebroplasty and vertebra pedicle screw fixation combined with vertebroplasty can achieve good clinical effects. However, injured vertebra pedicle fixation combined with vertebroplasty is better at maintaining postoperative vertebral height and sagittal arrangement, and reducing internal fixation related complications. The treatment strategy is worthy of application and promotion.

Case report on a misleading case of appendiceal perforation presented with severe generalized convulsion.

Appendicitis and convulsions are two common pathologies among children. Though appendicitis has some certain symptoms, they might present with atypical symptoms in young ages. Here we present a misleading case of a perforated appendix that presented with severe generalized convulsion, no significant abdominal symptoms and had a recent history of mild gastrointestinal problems. The primary symptoms and the related examination findings guided the differential diagnosis as viral encephalitis, febrile convulsion, and Epilepsy. The initial treatment was started accordingly with an aim to prevent further convulsion. But this case was later diagnosed as a case of peritonitis following perforated appendix and was operated successfully. After surgery, the patient recovered with no further attack of convulsion even following the postoperative withdrawal of sedative therapy. He was discharged on the 7th postoperative day and there were no major complaints on his follow-ups. Such misleading cases usually lead to misdiagnosis and might cause morbidity, even endanger the life of the patient. Therefore regarding children of sudden generalized convulsion with even minute abdominal findings or recent gastrointestinal history, it is necessary to pay attention and evaluate the abdomen by a CT or MRI besides the nervous system at the first impression.

Characterizing the Structural Pattern of Heavy Smokers Using Multivoxel Pattern Analysis.

Background: Smoking addiction is a major public health issue which causes a series of chronic diseases and mortalities worldwide. We aimed to explore the most discriminative gray matter regions between heavy smokers and healthy controls with a data-driven multivoxel pattern analysis technique, and to explore the methodological differences between multivoxel pattern analysis and voxel-based morphometry. Methods: Traditional voxel-based morphometry has continuously contributed to finding smoking addiction-related regions on structural magnetic resonance imaging. However, voxel-based morphometry has its inherent limitations. In this study, a multivoxel pattern analysis using a searchlight algorithm and support vector machine was applied on structural magnetic resonance imaging to identify the spatial pattern of gray matter volume in heavy smokers. Results: Our proposed method yielded a voxel-wise accuracy of at least 81% for classifying heavy smokers from healthy controls. The identified regions were primarily located at the temporal cortex and prefrontal cortex, occipital cortex, thalamus (bilateral), insula (left), anterior and median cingulate gyri, and precuneus (left). Conclusions: Our results suggested that several regions, which were seldomly reported in voxel-based morphometry analysis, might be latently correlated with smoking addiction. Such findings might provide insights for understanding the mechanism of chronic smoking and the creation of effective cessation treatment. Multivoxel pattern analysis can be efficient in locating brain discriminative regions which were neglected by voxel-based morphometry.

Stretchable MoS2 Electromechanical Sensors with Ultrahigh Sensitivity and Large Detection Range for Skin-on Monitoring.

Although two-dimensional (2D) layered molybdenum disulfide (MoS2) has widespread electrical applications in catalysis, energy storage, display, and photodetection, very few reports are available to achieve MoS2 for electromechanical sensing. Here, we report a novel solution-processed MoS2 strain sensor by constructing nanojunctions between layered MoS2 nanosheets and high-conductivity silver nanofibers (AgNFs) inside an elastic film. Benefiting from the outstanding lubrication property of layered MoS2 nanosheets, these nanojunctions can be easily separated by strains, giving rise to excellent electromechanical response. The resulting MoS2 strain sensor for the first time exhibits ultrahigh sensitivity with a gauge factor of 3,300 in a large detection range over 10%. The pronounced strain-sensing ability, combined with fast response speed and good operational stability, enables the MoS2 sensor for real-time and skin-on monitorings of various physiological signals such as finger movements, pulse, and breath. Our results may pave the way to extend 2D materials in novel applications such as soft robotics and human-machine interfaces.

Dynamic Contrast-enhanced Magnetic Resonance Imaging for Differentiating Between Primary Tumor, Metastatic Node and Normal Tissue in Head and Neck Cancer.

OBJECTIVE: To study the difference of the Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) parameters among the primary tumor, metastatic node and peripheral normal tissue of head and neck cancer. MATERIALS AND METHODS: Consecutive newly-diagnosed head and neck cancer patients with nodal metastasis between December 2010 and July 2013 were recruited, and 25 patients (8 females; 24~63,mean 43±11 years old) were enrolled. DCE-MRI was performed in the primary tumor region including the regional lymph nodes on a 3.0-T MRI system. Three quantitative parameters: Ktrans (volume transfer constant), ve (volume fraction of extravascular extracellular space) and kep (the rate constant of contrast transfer) were calculated for the largest node. A repeated-measure ANOVA with a Greenhouse-Geisser correction and post hoc tests using the Bonferroni correction were used to evaluate the differences in Ktrans, ve and kep among primary tumors, metastatic nodes and normal tissue. RESULTS: The values of both Ktrans and ve of normal tissue differed significantly from those of nodes (both P < 0.001) and primary tumors (both P < 0.001) respectively, while no significant differences of Ktrans and ve were observed between nodes and primary tumors (P = 0.075 and 0.365 respectively). The kep values of primary tumors were significantly different from those of nodes (P = 0.001) and normal tissue (P = 0.002), while no significant differences between nodes and normal tissue (P > 0.999). CONCLUSION: The DCE-MRI parameters were different in the tumors, metastatic nodes and normal tissue in head and neck cancer. These findings may be useful in the characterization of head and neck cancer.

Clinicopathological Features and Increased Expression of Toll-Like Receptor 4 of Gastric Cardia Cancer in a High-Risk Chinese Population.

The incidence of gastric cardia cancer (GCC) is high in China. However, the clinicopathological characteristics and the carcinogenesis of GCC are unclear. Toll-like receptor 4 (TLR4) is an important innate immunity receptor and has a role in non-GCC (NGCC). We compared the clinicopathological characteristics of GCC patients from a high-risk area in China to esophageal cancer (EC) patients. Immunohistochemistry for TLR4 was performed in 201 histological samples of normal gastric cardia mucosa (n = 11), gastric cardia inflammation (n = 87), and GCC (n = 103). We included 84 patients with EC and 99 with GCC. GCC tissue was more poorly differentiated than EC tissue and more invasive, with more histomorphologic variation. Lymph node metastasis was more frequent in GCC than in EC. The Helicobacter pylori infection rate was higher but not significantly with GCC than EC. Survival was shorter with lymph node metastasis. We found a statistically significant trend for progressive increase of TLR4 expression from normal mucosa to inflammation in GCC. GCC in this high-risk area displays clinicopathologic characteristics different from those of EC and different from those of gastroesophageal junction carcinomas in other countries, although this was not analyzed statistically. Increased TLR4 expression in gastric cardia lesions may be associated with GCC tumorigenesis.

An Unobtrusive Computerized Assessment Framework for Unilateral Peripheral Facial Paralysis.

Unilateral peripheral facial paralysis (UPFP) is a form of facial nerve paralysis and clinically classified according to conditions of facial symmetry. Prompt and precise assessment is crucial to neural rehabilitation of UPFP. The prevalent House-Brackmann (HB) grading system relies on subjective judgments with significant interobservation variation. Therefore, to explore an objective method for the UPFP assessment, clinical image sequences are captured using a web camera setup while 5 healthy and 27 UPFP subjects perform a group of predefined actions, including keeping expressionless, raising brows, closing eyes, bulging cheek, and showing teeth in turn. First, facial region is decided using Haar cascade classifier, and then landmark points are acquired by a supervised descent method. Second, these landmark points are used to generate a group of features reflecting the structural parameters of regions of eyebrows, eyes, nose, and mouth, respectively. Third, correlation coefficients are computed between the raw features HB scores. To reduce feature dimensions, only those with correlation coefficients larger than an empirically selected value, 0.35, are input into a support vector machine to generate a classifier. With the classifier, exact match (discrepancy = 0 between result from proposed method and HB scores) rate at 49.9%, and loose match (discrepancy = 1) rate at 87.97% are achieved on the experiment data. After sample augmentation, the final rate is increased to 90.01%, outperformed previous reports. In conclusion, it is demonstrated with an unobtrusive web camera setup, encouraging results have been generated with the proposed framework in this exploratory study.

An Individual Finger Gesture Recognition System Based on Motion-Intent Analysis Using Mechanomyogram Signal.

Motion-intent-based finger gesture recognition systems are crucial for many applications such as prosthesis control, sign language recognition, wearable rehabilitation system, and human-computer interaction. In this article, a motion-intent-based finger gesture recognition system is designed to correctly identify the tapping of every finger for the first time. Two auto-event annotation algorithms are firstly applied and evaluated for detecting the finger tapping frame. Based on the truncated signals, the Wavelet packet transform (WPT) coefficients are calculated and compressed as the features, followed by a feature selection method that is able to improve the performance by optimizing the feature set. Finally, three popular classifiers including naive Bayes (NBC), K-nearest neighbor (KNN), and support vector machine (SVM) are applied and evaluated. The recognition accuracy can be achieved up to 94%. The design and the architecture of the system are presented with full system characterization results.

Head and Neck Cancer Tumor Segmentation Using Support Vector Machine in Dynamic Contrast-Enhanced MRI.

Objective: We aimed to propose an automatic method based on Support Vector Machine (SVM) and Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) to segment the tumor lesions of head and neck cancer (HNC). Materials and Methods: 120 DCE-MRI samples were collected. Five curve features and two principal components of the normalized time-intensity curve (TIC) in 80 samples were calculated as the dataset in training three SVM classifiers. The other 40 samples were used as the testing dataset. The area overlap measure (AOM) and the corresponding ratio (CR) and percent match (PM) were calculated to evaluate the segmentation performance. The training and testing procedure was repeated for 10 times, and the average performance was calculated and compared with similar studies. Results: Our method has achieved higher accuracy compared to the previous results in literature in HNC segmentation. The average AOM with the testing dataset was 0.76 ± 0.08, and the mean CR and PM were 79 ± 9% and 86 ± 8%, respectively. Conclusion: With improved segmentation performance, our proposed method is of potential in clinical practice for HNC.

A Meta-Analytic Study of the Neural Systems for Auditory Processing of Lexical Tones.

The neural systems of lexical tone processing have been studied for many years. However, previous findings have been mixed with regard to the hemispheric specialization for the perception of linguistic pitch patterns in native speakers of tonal language. In this study, we performed two activation likelihood estimation (ALE) meta-analyses, one on neuroimaging studies of auditory processing of lexical tones in tonal languages (17 studies), and the other on auditory processing of lexical information in non-tonal languages as a control analysis for comparison (15 studies). The lexical tone ALE analysis showed significant brain activations in bilateral inferior prefrontal regions, bilateral superior temporal regions and the right caudate, while the control ALE analysis showed significant cortical activity in the left inferior frontal gyrus and left temporo-parietal regions. However, we failed to obtain significant differences from the contrast analysis between two auditory conditions, which might be caused by the limited number of studies available for comparison. Although the current study lacks evidence to argue for a lexical tone specific activation pattern, our results provide clues and directions for future investigations on this topic, more sophisticated methods are needed to explore this question in more depth as well.