Assessment of Water Intake among Chinese Toddlers: The Report of a Survey.

Toddlerhood (aged 13~36 months) is a period of dietary transition, with water intake being significantly influenced by parental feeding patterns, cultural traditions, and the availability of beverages and food. Nevertheless, given the lack of applicable data, it is challenging to guide and evaluate the water intake of toddlers in China. In this study, our objectives were to assess the daily total water intake (TWI), evaluate the consumption patterns of various beverages and food sources contributing to the TWI, determine the conformity of participants to the adequate intake (AI) recommendation of water released by the Chinese Nutrition Society, and analyze the various contributors to the daily total energy intake (TEI). The data for the assessment of water and dietary intake were obtained from the cross-sectional dietary intake survey of infants and young children (DSIYC, 2018-2019). A total of 1360 eligible toddlers were recruited in the analysis. The differences in related variables between two age groups were compared by Mann-Whitney U test and Chi-Square test. The potential correlation between water and energy intake was examined utilizing age-adjusted partial correlation. Toddlers consumed a median daily TWI of 1079 mL, with 670 mL (62.3%, r = 0.752) derived from beverages and 393 mL (37.7%, r = 0.716) from foods. Plain water was the primary beverage source, contributing 300 mL (52.2%, r = 0.823), followed by milk and milk derivatives (MMDs) at 291 mL (45.6%, r = 0.595). Notably, only 28.4% of toddlers managed to reach the recommended AI value. Among these, toddlers obtain more water from beverages than from foods. The median daily TEI of toddlers was 762 kcal, including 272 kcal from beverages (36.4%, r = 0.534) and 492 kcal from foods (63.6%, r = 0.894). Among these, the median daily energy intake from MMDs was 260 kcal, making up 94.6% of the energy intake from beverages (r = 0.959). As the pioneer survey on TWI of toddlers in China based on nationally representative data, attention to the quality and quantity of water intake and actions to better guide parents by both individuals and authorities are eagerly anticipated. Additionally, the revision of the reference value of TWI for Chinese toddlers is urgently required.

Association between weight-adjusted-waist index and depression in US adults: A cross-sectional study.

BACKGROUND: Current evidence implicates a significant association between depression and obesity and related metabolic dysfunction. The weight-adjusted-waist index (WWI) was recently identified as an ideal index that integrates total body fat, muscle mass, and bone mass. This study investigated the relationship between WWI and depressive symptoms in adults. METHODS: Participants from the National Health and Nutrition Examination Survey (2005-2018) were enrolled. Depressive symptom severity was measured with the Patient Health Questionnaire-9 (PHQ-9). Survey-weighted multivariable logistic regression, subgroup analysis, and generalized additive models were used to determine the relationship between WWI and depressive symptoms. RESULTS: A total of 34,575 participants were included, with a mean WWI of 11.01; 2,979 participants were suspected of having depressive symptoms (PHQ-9 score ≥ 10). A significant positive association was identified between WWI and depressive symptoms (odds ratio = 1.416, 95 % confidence interval: 1.303-1.539, P < 0.0001). Subgroup analyses suggested that the association between WWI and depressive symptoms was stronger in individuals who were female, overweight, divorced, middle-aged or older (over 40 years old), and had diabetes. Furthermore, the non-linear multivariable regression revealed an inflection point for the WWI at 11.438, and the association was only significant when the WWI was higher than this point. LIMITATIONS: This study was retrospective and only included participants from the United States; therefore, further validation is needed from studies in other countries, especially middle-to-low-income countries, using longitudinal cohorts. CONCLUSIONS: This study identified a significant positive association between WWI and depressive symptoms.

Deep integrated fusion of local and global features for cervical cell classification.

Cervical cytology image classification is of great significance to the cervical cancer diagnosis and prognosis. Recently, convolutional neural network (CNN) and visual transformer have been adopted as two branches to learn the features for image classification by simply adding local and global features. However, such the simple addition may not be effective to integrate these features. In this study, we explore the synergy of local and global features for cytology images for classification tasks. Specifically, we design a Deep Integrated Feature Fusion (DIFF) block to synergize local and global features of cytology images from a CNN branch and a transformer branch. Our proposed method is evaluated on three cervical cell image datasets (SIPaKMeD, CRIC, Herlev) and another large blood cell dataset BCCD for several multi-class and binary classification tasks. Experimental results demonstrate the effectiveness of the proposed method in cervical cell classification, which could assist medical specialists to better diagnose cervical cancer.

OIF-Net: An Optical Flow Registration-Based PET/MR Cross-Modal Interactive Fusion Network for Low-Count Brain PET Image Denoising.

The short frames of low-count positron emission tomography (PET) images generally cause high levels of statistical noise. Thus, improving the quality of low-count images by using image postprocessing algorithms to achieve better clinical diagnoses has attracted widespread attention in the medical imaging community. Most existing deep learning-based low-count PET image enhancement methods have achieved satisfying results, however, few of them focus on denoising low-count PET images with the magnetic resonance (MR) image modality as guidance. The prior context features contained in MR images can provide abundant and complementary information for single low-count PET image denoising, especially in ultralow-count (2.5%) cases. To this end, we propose a novel two-stream dual PET/MR cross-modal interactive fusion network with an optical flow pre-alignment module, namely, OIF-Net. Specifically, the learnable optical flow registration module enables the spatial manipulation of MR imaging inputs within the network without any extra training supervision. Registered MR images fundamentally solve the problem of feature misalignment in the multimodal fusion stage, which greatly benefits the subsequent denoising process. In addition, we design a spatial-channel feature enhancement module (SC-FEM) that considers the interactive impacts of multiple modalities and provides additional information flexibility in both the spatial and channel dimensions. Furthermore, instead of simply concatenating two extracted features from these two modalities as an intermediate fusion method, the proposed cross-modal feature fusion module (CM-FFM) adopts cross-attention at multiple feature levels and greatly improves the two modalities' feature fusion procedure. Extensive experimental assessments conducted on real clinical datasets, as well as an independent clinical testing dataset, demonstrate that the proposed OIF-Net outperforms the state-of-the-art methods.

Association between weight-adjusted-waist index with hepatic steatosis and liver fibrosis: a nationally representative cross-sectional study from NHANES 2017 to 2020.

Background: The negative effects of obesity on hepatic steatosis and fibrosis have received considerable attention in recent years. The weight-adjusted-waist index (WWI) reflects weight-independent centripetal obesity. Herein, we provide the first investigation of a link between WWI, hepatic steatosis, and liver fibrosis. Methods: We used data from the National Health and Nutrition Examination Survey 2017-2020 to conduct a cross-sectional study. The linear relationship between WWI, controlled attenuation parameters, and liver stiffness measurements (LSM) was investigated using multivariate linear regression models. The nonlinear relationship was described using fitted smoothed curves and threshold effect analyses. Subgroup analyses were performed based on gender, age, body mass index, diabetes, hypertension, drinking, and smoking. Results: This population-based study included 7,594 people, 50.74% of whom were men and 49.26% of whom were women. Multivariate linear regression analysis revealed a significant positive relationship between WWI and hepatic steatosis [CAP, ß=7.60, 95% confidence interval (CI) (4.42, 10.78), P<0.0001]. This positive association was stronger when excessive alcohol intake was present compared to when it was absent (P for interaction = 0.031), and when hypertension was present compared to when it was not (P for interaction = 0.014). The linear relationship between WWI and liver fibrosis was not statistically significant on multiple regression analysis [LSM, ß=0.03, 95% CI (-0.26, 0.32), P=0.84]. However, a U-shaped association was seen between WWI and LSM, with a negative correlation when WWI< 10.92 and a positive correlation when WWI > 10.92. Conclusion: We report a strong association between WWI and hepatic steatosis, and suggest that it may potentially be used as a simple anthropometric index to predict hepatic steatosis.

A multi-modal deep neural network for multi-class liver cancer diagnosis.

Liver disease is a potentially asymptomatic clinical entity that may progress to patient death. This study proposes a multi-modal deep neural network for multi-class malignant liver diagnosis. In parallel with the portal venous computed tomography (CT) scans, pathology data is utilized to prognosticate primary liver cancer variants and metastasis. The processed CT scans are fed to the deep dilated convolution neural network to explore salient features. The residual connections are further added to address vanishing gradient problems. Correspondingly, five pathological features are learned using a wide and deep network that gives a benefit of memorization with generalization. The down-scaled hierarchical features from CT scan and pathology data are concatenated to pass through fully connected layers for classification between liver cancer variants. In addition, the transfer learning of pre-trained deep dilated convolution layers assists in handling insufficient and imbalanced dataset issues. The fine-tuned network can predict three-class liver cancer variants with an average accuracy of 96.06% and an Area Under Curve (AUC) of 0.832. To the best of our knowledge, this is the first study to classify liver cancer variants by integrating pathology and image data, hence following the medical perspective of malignant liver diagnosis. The comparative analysis on the benchmark dataset shows that the proposed multi-modal neural network outperformed most of the liver diagnostic studies and is comparable to others.

A Two-Branch Neural Network for Short-Axis PET Image Quality Enhancement.

The axial field of view (FOV) is a key factor that affects the quality of PET images. Due to hardware FOV restrictions, conventional short-axis PET scanners with FOVs of 20 to 35 cm can acquire only low-quality PET (LQ-PET) images in fast scanning times (2-3 minutes). To overcome hardware restrictions and improve PET image quality for better clinical diagnoses, several deep learning-based algorithms have been proposed. However, these approaches use simple convolution layers with residual learning and local attention, which insufficiently extract and fuse long-range contextual information. To this end, we propose a novel two-branch network architecture with swin transformer units and graph convolution operation, namely SW-GCN. The proposed SW-GCN provides additional spatial- and channel-wise flexibility to handle different types of input information flow. Specifically, considering the high computational cost of calculating self-attention weights in full-size PET images, in our designed spatial adaptive branch, we take the self-attention mechanism within each local partition window and introduce global information interactions between nonoverlapping windows by shifting operations to prevent the aforementioned problem. In addition, the convolutional network structure considers the information in each channel equally during the feature extraction process. In our designed channel adaptive branch, we use a Watts Strogatz topology structure to connect each feature map to only its most relevant features in each graph convolutional layer, substantially reducing information redundancy. Moreover, ensemble learning is adopted in our SW-GCN for mapping distinct features from the two well-designed branches to the enhanced PET images. We carried out extensive experiments on three single-bed position scans for 386 patients. The test results demonstrate that our proposed SW-GCN approach outperforms state-of-the-art methods in both quantitative and qualitative evaluations.

Total-body low-dose CT image denoising using a prior knowledge transfer technique with a contrastive regularization mechanism.

PURPOSE: Reducing the radiation exposure experienced by patients in total-body computed tomography (CT) imaging has attracted extensive attention in the medical imaging community. A low radiation dose may result in increased noise and artifacts that greatly affect the subsequent clinical diagnosis. To obtain high-quality total-body low-dose CT (LDCT) images, previous deep learning-based research works developed various network architectures. However, most of these methods only employ normal-dose CT (NDCT) images as ground truths to guide the training process of the constructed denoising network. As a result of this simple restriction, the reconstructed images tend to lose favorable image details and easily generate oversmoothed textures. This study explores how to better utilize the information contained in the feature spaces of NDCT images to guide the LDCT image reconstruction process and achieve high-quality results. METHODS: We propose a novel intratask knowledge transfer (KT) method that leverages the knowledge distilled from NDCT images as an auxiliary component of the LDCT image reconstruction process. Our proposed architecture is named the teacher-student consistency network (TSC-Net), which consists of teacher and student networks with identical architectures. By employing the designed KT loss, the student network is encouraged to emulate the teacher network in the representation space and gain robust prior content. In addition, to further exploit the information contained in CT scans, a contrastive regularization mechanism (CRM) built upon contrastive learning is introduced. The CRM aims to minimize and maximize the L2 distances from the predicted CT images to the NDCT samples and to the LDCT samples in the latent space, respectively. Moreover, based on attention and the deformable convolution approach, we design a dynamic enhancement module (DEM) to improve the network capability to transform input information flows. RESULTS: By conducting ablation studies, we prove the effectiveness of the proposed KT loss, CRM, and DEM. Extensive experimental results demonstrate that the TSC-Net outperforms the state-of-the-art methods in both quantitative and qualitative evaluations. Additionally, the excellent results obtained for clinical readings also prove that our proposed method can reconstruct high-quality CT images for clinical applications. CONCLUSIONS: Based on the experimental results and clinical readings, the TSC-Net has better performance than other approaches. In our future work, we may explore the reconstruction of LDCT images by fusing the positron emission tomography (PET) and CT modalities to further improve the visual quality of the reconstructed CT images.

Construction and Clinical Translation of Causal Pan-Cancer Gene Score Across Cancer Types.

Pan-cancer strategy, an integrative analysis of different cancer types, can be used to explain oncogenesis and identify biomarkers using a larger statistical power and robustness. Fine-mapping defines the casual loci, whereas genome-wide association studies (GWASs) typically identify thousands of cancer-related loci and not necessarily have a fine-mapping component. In this study, we develop a novel strategy to identify the causal loci using a pan-cancer and fine-mapping assumption, constructing the CAusal Pan-cancER gene (CAPER) score and validating its performance using internal and external validation on 1,287 individuals and 985 cell lines. Summary statistics of 15 cancer types were used to define 54 causal loci in 15 potential genes. Using the Cancer Genome Atlas (TCGA) training set, we constructed the CAPER score and divided cancer patients into two groups. Using the three validation sets, we found that 19 cancer-related variables were statistically significant between the two CAPER score groups and that 81 drugs had significantly different drug sensitivity between the two CAPER score groups. We hope that our strategies for selecting causal genes and for constructing CAPER score would provide valuable clues for guiding the management of different types of cancers.