A comprehensive approach to lifestyle intervention based on a calorie-restricted diet ameliorates liver fat in overweight/obese patients with NAFLD: a multicenter randomized controlled trial in China.

BACKGROUND: Nonalcoholic fatty liver disease (NAFLD) is a globally increasing health epidemic. Lifestyle intervention is recommended as the main therapy for NAFLD. However, the optimal approach is still unclear. This study aimed to evaluate the effects of a comprehensive approach of intensive lifestyle intervention (ILI) concerning enhanced control of calorie-restricted diet (CRD), exercise, and personalized nutrition counseling on liver steatosis and extrahepatic metabolic status in Chinese overweight and obese patients with NAFLD. METHODS: This study was a multicenter randomized controlled trial (RCT) conducted across seven hospitals in China. It involved 226 participants with a body mass index (BMI) above 25. These participants were randomly assigned to two groups: the ILI group, which followed a low carbohydrate, high protein CRD combined with exercise and intensive counseling from a dietitian, and a control group, which adhered to a balanced CRD along with exercise and standard counseling. The main measure of the study was the change in the fat attenuation parameter (FAP) from the start of the study to week 12, analyzed within the per-protocol set. Secondary measures included changes in BMI, liver stiffness measurement (LSM), and the improvement of various metabolic indexes. Additionally, predetermined subgroup analyses of the FAP were conducted based on variables like gender, age, BMI, ethnicity, hyperlipidemia, and hypertension. RESULTS: A total of 167 participants completed the whole study. Compared to the control group, ILI participants achieved a significant reduction in FAP (LS mean difference, 16.07 [95% CI: 8.90-23.25] dB/m) and BMI (LS mean difference, 1.46 [95% CI: 1.09-1.82] kg/m2) but not in LSM improvement (LS mean difference, 0.20 [95% CI: -0.19-0.59] kPa). The ILI also substantially improved other secondary outcomes (including ALT, AST, GGT, body fat mass, muscle mass and skeletal muscle mass, triglyceride, fasting blood glucose, fasting insulin, HbA1c, HOMA-IR, HOMA-ß, blood pressure, and homocysteine). Further subgroup analyses showed that ILI, rather than control intervention, led to more significant FAP reduction, especially in patients with concurrent hypertension (p < 0.001). CONCLUSION: In this RCT, a 12-week intensive lifestyle intervention program led to significant improvements in liver steatosis and other metabolic indicators in overweight and obese Chinese patients suffering from nonalcoholic fatty liver disease. Further research is required to confirm the long-term advantages and practicality of this approach. TRIAL REGISTRATION: This clinical trial was registered on ClinicalTrials.gov (registration number: NCT03972631) in June 2019.

LRSCnet: Local Reference Semantic Code learning for breast tumor classification in ultrasound images.

PURPOSE: This study proposed a novel Local Reference Semantic Code (LRSC) network for automatic breast ultrasound image classification with few labeled data. METHODS: In the proposed network, the local structure extractor is firstly developed to learn the local reference which describes common local characteristics of tumors. After that, a two-stage hierarchical encoder is developed to encode the local structures of lesion into the high-level semantic code. Based on the learned semantic code, the self-matching layer is proposed for the final classification. RESULTS: In the experiment, the proposed method outperformed traditional classification methods and AUC (Area Under Curve), ACC (Accuracy), Sen (Sensitivity), Spec (Specificity), PPV (Positive Predictive Values), and NPV(Negative Predictive Values) are 0.9540, 0.9776, 0.9629, 0.93, 0.9774 and 0.9090, respectively. In addition, the proposed method also improved matching speed. CONCLUSIONS: LRSC-network is proposed for breast ultrasound images classification with few labeled data. In the proposed network, a two-stage hierarchical encoder is introduced to learn high-level semantic code. The learned code contains more effective high-level classification information and is simpler, leading to better generalization ability.

Automated Screening of COVID-19-Based Tongue Image on Chinese Medicine.

Objective: Artificial intelligence-powered screening systems of coronavirus disease 2019 (COVID-19) are urgently demanding since the ongoing outbreak of SARS-CoV-2 worldwide. Chest CT or X-ray is not sufficient to support the large-scale screening of COVID-19 because mildly-infected patients do not have imaging features on these images. Therefore, it is imperative to exploit supplementary medical imaging strategies. Traditional Chinese medicine has played an essential role in the fight against COVID-19. Methods: In this paper, we conduct two kinds of verification experiments based on a newly-collected multi-modality dataset, which consists of three types of modalities: tongue images, chest CT scans, and X-ray images. First, we study a binary classification experiment on tongue images to verify the discriminative ability between COVID-19 and non-COVID-19. Second, we design extensive multimodality experiments to validate whether introducing tongue image can improve the screening accuracy of COVID-19 based on chest CT or X-ray images. Results: Tongue image screening of COVID-19 showed that the accuracy (ACC), sensitivity (SEN), specificity (SPEC), and Matthew correlation coefficient (MCC) of the improved AlexNet and Googlenet both reached 98.39%, 98.97%, 96.67%, and 99.11%. The fusion of chest CT and tongue images used a tandem multimodal classifier fusion strategy to achieve optimal classification, and the results and screening accuracy of COVID-19 reached 98.98%, resulting in a significant improvement of 4.75% the highest accuracy in 375 years compared with the single-modality model. The fusion of chest x-rays and tongue images also had good classification accuracy. Conclusions: Both experimental results demonstrate that tongue image not only has an excellent discriminative ability for screening COVID-19 but also can improve the screening accuracy based on chest CT or X-rays. To the best of our knowledge, it is the first work that verifies the effectiveness of tongue image on screening COVID-19. This paper provides a new perspective and a novel solution that contributes to large-scale screening toward fast stopping the pandemic of COVID-19.

Modality-correlation embedding model for breast tumor diagnosis with mammography and ultrasound images.

The fusion of mammography and ultrasound images helps to improve tumor classification accuracy. However, traditional fusion models ignore the correlation between these two modalities, resulting in limited performance improvement. To address this problem, a modality-correlation embedding model was proposed for breast tumor diagnosis by combining mammography and ultrasound imaging. By jointly optimizing the correlation between mammography and ultrasound and classification loss of individual modalities, two mappings are learned to project mammography and ultrasound from their original feature spaces into a common label space. A novel modality-correlation term is introduced to maintain the pairwise closeness of multimodal data in the common label space. Contrary to previous studies that did not consider the correlation between multimodal data, the proposed term can exploit the learned correlation information in the fusion process, which guarantees the consistency of the diagnosis results of multimodal images from the same patient. The proposed method was evaluated on our dataset, which contained ultrasound and mammography images from 73 patients. The area under the ROC curve, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were 95.83, 95, 91.67, 95.83, 95.83, and 88.89%, respectively. The experimental results also demonstrate that the proposed method outperforms traditional fusion methods.

A Discriminative Level Set Method with Deep Supervision for Breast Tumor Segmentation.

BACKGROUND: Breast tumor segmentation in B-mode ultrasound imaging is important for analyzing, identifying, and diagnosing tumors. The level set is an approach most widely used in breast segmentation, and the refinement is still in progress. However, its effectiveness is harmed by a dearth of semantic information. On the other hand, deep networks contain rich semantic information but loss much influential low-level details. METHOD: This paper proposes a novel deep-feature embedded level set group to exploit semantically enriched features for breast tumor segmentation. First, a UNet-based network is trained to extract different features at different stages. Each stage has unique features depiction. Then, a novel level-set method is integrated at the end of each stage to approach more accurate and precise features maps. A new feature-discriminator is devised in the energy function of the level set method to refine the low confidence pixels at the boundaries. Lastly, the outputs of the level set method at different stages are incorporated into final feature maps to further empower the segmentation process. Two datasets comprising 349 breast ultrasound images from various hospitals have been utilized to assess the proposed approach's performance. The model's effectiveness is estimated on different metrics, including Accuracy, Sensitivity or True Positive rate, Specificity or True Negative rate, False Positive rate Dice, and IoU values for both datasets. Furthermore, the efficiency of the model is investigated by performing a comparison with several state-of-the-art classic segmentation methods and deep learning methods. RESULT: The proposed method outperformed segmenting breast ultrasound tumors in terms of Dice and IoU for datasets A and B (with p-value < 0.005 against compared methods). Additionally, the performance of the proposed approach is evaluated using the Area Under Receiver Operating Characteristics curve (AUC) and Mean Absolute Error (MAE). Our findings indicate that the proposed method seems to gain superiority over other methods by obtaining a lower MAE rate with the highest value of the AUC. CONCLUSION: Experiments determine that our method has obtained the best cut-off to deal with the noticeable glitches present in other approaches and generates more accurate segmentation results for tumors in complex images. Hence, the results confirm the proposed method's effectiveness compared to classic segmentation methods over ultrasound images with blurry boundaries, noise, and intensity inhomogeneity. Moreover, our approach gives unprecedented prediction accuracy and similarity for malignant tumors.

SMBFT: A Modified Fuzzy c-Means Algorithm for Superpixel Generation.

Most traditional superpixel segmentation methods used binary logic to generate superpixels for natural images. When these methods are used for images with significantly fuzzy characteristics, the boundary pixels sometimes cannot be correctly classified. In order to solve this problem, this paper proposes a Superpixel Method Based on Fuzzy Theory (SMBFT), which uses fuzzy theory as a guide and traditional fuzzy c-means clustering algorithm as a baseline. This method can make full use of the advantage of the fuzzy clustering algorithm in dealing with the images with the fuzzy characteristics. Boundary pixels which have higher uncertainties can be correctly classified with maximum probability. The superpixel has homogeneous pixels. Meanwhile, the paper also uses the surrounding neighborhood pixels to constrain the spatial information, which effectively alleviates the negative effects of noise. The paper tests on the images from Berkeley database and brain MR images from the Brain web. In addition, this paper proposes a comprehensive criterion to measure the weights of two kinds of criterions in choosing superpixel methods for color images. An evaluation criterion for medical image data sets employs the internal entropy of superpixels which is inspired by the concept of entropy in the information theory. The experimental results show that this method has superiorities than traditional methods both on natural images and medical images.

Research on the application of health management model based on the perspective of mobile health.

The aim of the present study was to explore the application and its effect of mobile medical treatment to chronic disease health management in physical examination population, and to provide references for comprehensive intervention and management of chronic diseases.From January to December 2016, 300 medical examiners in a general hospital health management center were randomly divided into health management group (155 cases) and control group (145 cases). The control group completed routine physical examination and health-risk assessment and provided corresponding reports, repeated annual physical examination and health-risks assessment. In addition to the routine physical examination and health-risk assessment, the health management group reminded the examiners to pay attention to their lifestyle and dietary habits by moving online and offline dynamic health interventions and provide targeted guidance for high-risk population such as diabetes, obesity, hypertension, etc. A review was made after 2 years. The clinical indexes and chronic disease behavior of patients before and after management were compared, and the effect was evaluated by statistical analysis.After management, all the clinical indexes were significantly improved, and the patients' dietary structure, bad living habits, psychologic state, and other chronic disease behaviors were obviously improved. The proportion of patients with high risk of hypertension, diabetes, and obesity in health management group was significantly lower than that before intervention and control group (P < .05).Using mobile network online, offline dynamic health intervention model can reduce the risk of common chronic diseases in health management objects, this health management model of chronic disease is worth popularizing.

Expression of IL-17 and its gene promoter methylation status are associated with the progression of chronic hepatitis B virus infection.

To explore interleukin-17 (IL-17) and its epigenetic regulation during the progression of chronic hepatitis B virus (HBV) infection.A total of 162 patients with chronic HBV infection, including 75 with chronic hepatitis B (CHB), 54 with hepatitis B-associated liver cirrhosis and 33 with hepatitis B-associated hepatocellular carcinoma (HBV-HCC), were enrolled in this study. Thirty healthy adults of the same ethnicity were enrolled in the control group. Whole venous blood was obtained from the patients and normal controls (n = 30). Clinical and laboratory parameters were assessed, and we performed enzyme-linked immunosorbent assay and quantitative real-time PCR to measure the serum levels and relative mRNA expression of IL-17, respectively. IL-17 promoter methylation in peripheral blood mononuclear cells was assessed by methylation-specific PCR. We analyzed the serum and mRNA levels of IL-17 and IL-17 promoter methylation in the 4 groups as well as the effect of methylation on serum IL-17 levels. Correlations between the IL-17 promoter methylation status and clinical parameters were analyzed by Spearman correlation analysis.Compared to the normal control group, the patient groups exhibited significantly higher serum and relative mRNA levels of IL-17. The methylation distribution among the patients was significantly lower than that among the normal controls (P < .05), with the HBV-HCC group showing the lowest IL-17 gene methylation frequency. The average IL-17 promoter CG methylation level was negatively correlated with IL-17 mRNA expression (r = -0.39, P = .03), and negative correlations between IL-17 promoter methylation and prothrombin time activity (r = -0.585, P = .035), alanine aminotransferase (r = -0.522, P < .01), aspartate aminotransferase (r = -0.315, P < .05), and the model for end-stage liver disease score (r = -0.461, P < .05) were observed. IL-17 serum levels in the methylated-promoter groups were significantly lower than those in the unmethylated-promoter groups.IL-17 expression and promoter methylation were associated with chronic HBV infection progression, especially in the HBV-HCC group. The IL-17 promoter status may help clinicians initiate the correct treatment strategy at the CHB stage.

Health status, intention to seek health examination, and participation in health education among taxi drivers in jinan, china.

BACKGROUND: Taxi drivers are exposed to various risk factors such as work overload, stress, an irregular diet, and a sedentary lifestyle, which make these individuals vulnerable to many diseases. This study was designed to assess the health status of this occupational group. OBJECTIVES: The objective was to explore the health status, the intention to seek health examination, and participation in health education among taxi drivers in Jinan, China. PATIENTS AND METHODS: The sample-size was determined scientifically. The systematic sampling procedure was used for selecting the sample. Four hundred taxi drivers were randomly selected from several taxi companies in Jinan. In total, 396 valid questionnaires (from 370 males and 26 females) were returned. Health status, intention to seek health examination, and participation in health education were assessed by a self-designed questionnaire. Other personal information including sex, age, ethnicity, marital status, years of employment as a taxi driver, education level, and habits were also collected. RESULTS: This survey revealed that 54.8% of taxi drivers reported illness in the last two weeks and 44.7% of participants reported chronic diseases. The prevalence rates of hypertension, diabetes mellitus, gastroenteritis, arthritis, and heart disease were 18.2%, 8.8%, 26%, 18.4%, and 4.8% of questioned taxi drivers, respectively. Significant self-reported symptoms included fatigue, waist and back pain, headache, dyspepsia, and dry throat affecting 49.7%, 26.2%, 23.5%, 26%, and 27% of participants, respectively. In total, 90.1% of subjects thought that it was necessary to receive a regular health examination. Only 17.9% of subjects had been given information about health education, and significantly, more than 87% of subjects who had been given information about health education reported that the information had been helpful. CONCLUSIONS: Taxi drivers' health was poor in our survey. Thus, using health education interventions to improve knowledge and change in behaviors are necessary and effective programs that improve the health of individuals in this special occupational group are needed.