A high-efficiency, nondestructive, rapid, and automatic crop disease classification method is essential for the modernization of agriculture. To more accurately extract and fit citrus disease image ...features, we designed a new 13-layer convolutional neural network (CNN13) consisting of multiple convolutional layer stacks and dropout in this study. To address the problem created by the uneven number of disease images in each category, we used the VGG16 network module for transfer learning, which we combined with the proposed CNN13 to form a new joint network, which we called OplusVNet. To verify the performance of the proposed OplusVNet network, we collected 1869 citrus pest and disease images and 202 normal citrus images from the field. The experimental results showed that the proposed OplusVNet can more effectively solve the problem caused by uneven data volume and has higher recognition accuracy, especially for image categories with a relatively small data volume. Compared with the state of the art networks, the generalization ability of the proposed OplusVNet network is stronger for classifying diseases. The classification accuracy of the model prediction results was 0.99, indicating the model can be used as a reference for crop image classification.
Bio-organic fertilizers (BOF) containing both organic amendments and beneficial microorganisms have been consistently shown to improve soils fertility and yield. However, the exact mechanisms which ...link amendments and yields remain disputed, and the complexity of bio-organic fertilizers may work in parallel in several ways. BOF may directly improve yield by replenishing soil nutrients or introducing beneficial microbial genes or indirectly by altering the soil microbiome to enrich native beneficial microorganisms. In this work, we aim to disentangle the relative contributions of direct and indirect effects on pear yield. We treated pear trees with either chemical fertilizer or organic fertilizer with/without the plant-beneficial bacterium Bacillus velezensis SQR9. We then assessed, in detail, soil physicochemical and biological properties (metagenome sequencing) as well as pear yield. We then evaluated the relative importance of direct and indirect effects of soil amendments on pear yield. Both organic treatments increased plant yield by up to 20%, with the addition of bacteria tripling the increase driven by organic fertilizer alone. This increase could be linked to alterations in soil physicochemical properties, bacterial community function, and metabolism. Supplementation of organic fertilizer SQR9 increased rhizosphere microbiome richness and functional diversity. Fertilizer-sensitive microbes and functions responded as whole guilds. Pear yield was most positively associated with the
- and
-dominated ecological clusters and with gene clusters involved in ion transport and secondary metabolite biosynthesis. Together, these results suggested that bio-organic fertilizers mainly act indirectly on plant yield by creating soil chemical properties which promote a plant-beneficial microbiome.
Bio-organic fertilization is a widely used, eco-friendly, sustainable approach to increasing plant productivity in the agriculture and fruit industries. However, it remains unclear whether the promotion of fruit productivity is related to specific changes in microbial inoculants, the resident microbiome, and/or the physicochemical properties of rhizosphere soils. We found that bio-organic fertilizers alter soil chemical properties, thus manipulating specific microbial taxa and functions within the rhizosphere microbiome of pear plants to promote yield. Our work unveils the ecological mechanisms which underlie the beneficial impacts of bio-organic fertilizers on yield promotion in fruit orchards, which may help in the design of more efficient biofertilizers to promote sustainable fruit production.
Anaerobic ammonium oxidation (anammox) plays an important role in nitrogen removal in coastal seas, and ladderanes, as specific biomarkers of anammox bacteria, can be used to indicate the anammox ...activity. However, the origins of ladderanes and their controlling factors in the coastal seas influenced by anthropogenic activities are still not well constrained. To address this, we reported ladderanes, long-chain
n
-alkanols (terrestrial biomarker) and sterols (marine biomarker) in suspended particulates from the estuaries and inner area of Laizhou Bay in North China, to study ladderane sources and its distribution patterns. This study proposed a novel index, R
lad
, using ladderane ratio of ladderane III to ladderane IV, and by correlating this index with other biomarker distributions to evaluate the source of ladderanes. High R
lad
values (> 0.9) indicated biosynthesis by terrestrial anammox bacteria
Ca.
Brocadia and
Ca.
Kuenenia, while low R
lad
values (< 0.9) indicated biosynthesis by marine anammox bacteria
Ca.
Scalindua. High R
lad
values and high ladderane concentrations in particulates from the estuaries and nearshore area of Laizhou Bay revealed sources from the terrestrial input
via
riverine inflow as well as
in situ
production in oxygen-depleted estuaries, supported by high concentrations of terrestrial biomarkers; Low R
lad
values and low ladderane concentrations in particulates from offshore area indicated sources from marine environment
via
the cold hypoxia water input by the Bohai circulation. Comparison of ladderane concentrations of our study with previously published results from a wide range of environments with human influences from Chinese coastal area revealed that high ladderane concentrations synthesized by terrestrial anammox bacteria could contribute significantly to coastal seas, and the anammox process in river-estuary-bay system might be underestimated. This study provides new understandings about the evaluation of the source and distribution of ladderanes under anthropogenic influences in coastal seas.
To prospectively evaluate the efficiency of daily providing complementary food supplements decreasing malnutrition and anemia prevalence in elder infants and young children living in areas affected ...by Wenchuan Earthquake.
Using promotional probability sampling method, 250 to 300 children from six-randomized townships (30 to 50 children in each township) in Kang County affected by the Earthquake were randomly chosen for follow up to evaluate intervention effectiveness using anthropometric measurement and hemoglobin level at six, twelve and eighteen months after start of intervention.
All children from 6 to 18 months of age in Kang County (in North Western China) were daily provided with complementary food supplements containing multiple vitamins and minerals for up to 24 months of age. The intervention period lasted for one and half year.
At beginning of intervention, malnutrition prevalence, including underweight, stunting and wasting were respectively 4.5%, 8.9% and 3.5%; anemia prevalence was 74.3%. After one and half year intervention, the growth and anemia status were significantly improved; the percentages of wasting, stunting underweight prevalence were decreased from 3.5%, 8.9% and 4.5% to 1.7%, 5.0% and 3.3% respectively, and the anemia rates were significantly decreased.
Our results indicated that an intervention using complementary food supplements could improve nutritional status and elevate hemoglobin level in elder infants and young children, which would significantly decrease the prevalence of malnutrition and anemia.
The comparatively low 25 hydroxyvitamin D 25(OH)D levels have been reported in patients with metabolic syndrome (MetS). Herein we investigated the cross-sectional and longitudinal relationships ...between serum 25(OH)D levels and MetS risk profile in northern middle-aged Chinese subjects without vitamin D supplementation.
A cohort of 211 participants including 151 MetS patients and 60 controls at 20-69 years of age were enrolled from suburban Beijing, China. The recruited MetS patients were subjected to diet and exercise counselling for 1-year. All subjects at baseline and MetS patients after intervention underwent clinical evaluations.
Serum 25(OH)D levels were significantly decreased in MetS patients. 25(OH)D levels were inversely related to MetS score, fasting blood glucose (FBG) and triglyceride-glucose index (TyG) after adjusting for cofounders (all P < 0.05). Participants in the lowest tertile of 25(OH)D levels had increased odds for MetS (P = 0.045), elevated FBG (P = 0.004) in all subjects, and one MetS score gain in MetS patients (P = 0.005). Longitudinally, the metabolic statuses as well as 25(OH)D levels of MetS patients were significantly improved (all P < 0.05), and the increase of 25(OH)D levels were inversely related to MetS scores, total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), FBG, and TyG, while positively related to high-density lipoprotein cholesterol (HDL-C) after adjusting for confounders.
25(OH)D levels were significantly decreased in MetS patients, and it was negatively associated with metabolic dysfunctions at baseline and 1-year after. Metabolic aberrations of MetS patients were significantly ameliorated with 1-year follow-up counselling accompanying by notably elevated 25(OH)D levels.
In order to evaluate micronutrient status of children aged 24-60 months living in rural disaster areas after one year of the earthquake in Wenchuan.
After one year of Wenchuan Earthquake, using PPS ...sampling methods, a total of 270 children from six-randomized townships near seismic center, in each township sample size consisted of 30 to 50 children, were sampled for evaluating Z-score of children's growth status, anemia prevalence, vitamin A, vitamin D, vitamin B12, folic acid status. Final sample consisted of 152 boys and 118 girls, and blood samples were drawn from 206 children.
The stunting (HAZ<2SD) and wasting (WHZ<2SD) were respectively 14.7% and 0.7%. Prevalence of anemia was 17.3% and percentage of iron deficiency was 45.7%. The prevalence of vitamin A deficiency and marginal deficiency was 15.4% and 30.3%, respectively. The sum of vitamin D deficiency and marginal deficiency was near 90%. Percentages of Zinc deficiency including marginal and deficiency were 65.5%. Percentages of vitamin B12 marginal and deficiency were 8.6% and 10.6% and the prevalence of marginal deficiency was significantly higher in boys than in girls. Folic acid deficiency was not found in surveyed children using serum folic acid level <16.9 ng/ml.
In areas affected by Earthquake, preschool children had higher stunting prevalence and a relatively higher prevalence suffered from micronutrient deficiencies, including iron-deficiency anemia, and deficiencies of iron, zinc, vitamin A and vitamin B12.
Purpose
Coronary computed tomographic angiography (CCTA) plays a vital role in the diagnosis of cardiovascular diseases, among which automatic coronary artery segmentation (CAS) serves as one of the ...most challenging tasks. To computationally assist the task, this paper proposes a novel end‐to‐end deep learning‐based (DL) solution for automatic CAS.
Methods
Inspired by the Di‐Vnet network, a fully automatic multistage DL solution is proposed. The new solution aims to preserve the integrity of blood vessels in terms of both their shape details and continuity. The solution is developed using 338 CCTA cases, among which 133 cases (33865 axial images) have their ground‐truth cardiac masks pre‐annotated and 205 cases (53365 axial images) have their ground‐truth coronary artery (CA) masks pre‐annotated. The solution's accuracy is measured using dice similarity coefficient (DSC), 95th percentile Hausdorff Distance (95% HD), Recall, and Precision scores for CAS.
Results
The proposed solution attains 90.29% in DSC, 2.11 mm in 95% HD, 97.02% in Recall, and 92.17% in Precision, respectively, which consumes 0.112 s per image and 30 s per case on average. Such performance of our method is superior to other state‐of‐the‐art segmentation methods.
Conclusions
The novel DL solution is able to automatically learn to perform CAS in an end‐to‐end fashion, attaining a high accuracy, efficiency and robustness simultaneously.
•A novel deep neural network, titled Multi-scale Residual Encoding and Decoding network (Ms RED), is proposed for skin lesion segmentation.•A pair of multi-scale residual feature fusion modules is ...further proposed to collectively augment the capability of the overall network in exploiting multi-scale perceptual context and characteristics.•A novel Multi-scale, Multi-channel Feature Fusion module is additionally proposed, which is able to further boost Ms RED capability in hierarchically extracting and adaptively learning from perceptual characteristics latent in an input image.
Display omitted
Computer-Aided Diagnosis (CAD) for dermatological diseases offers one of the most notable showcases where deep learning technologies display their impressive performance in acquiring and surpassing human experts. In such the CAD process, a critical step is concerned with segmenting skin lesions from dermoscopic images. Despite remarkable successes attained by recent deep learning efforts, much improvement is still anticipated to tackle challenging cases, e.g., segmenting lesions that are irregularly shaped, bearing low contrast, or possessing blurry boundaries. To address such inadequacies, this study proposes a novel Multi-scale Residual Encoding and Decoding network (Ms RED) for skin lesion segmentation, which is able to accurately and reliably segment a variety of lesions with efficiency. Specifically, a multi-scale residual encoding fusion module (MsR-EFM) is employed in an encoder, and a multi-scale residual decoding fusion module (MsR-DFM) is applied in a decoder to fuse multi-scale features adaptively. In addition, to enhance the representation learning capability of the newly proposed pipeline, we propose a novel multi-resolution, multi-channel feature fusion module (M2F2), which replaces conventional convolutional layers in encoder and decoder networks. Furthermore, we introduce a novel pooling module (Soft-pool) to medical image segmentation for the first time, retaining more helpful information when down-sampling and getting better segmentation performance. To validate the effectiveness and advantages of the proposed network, we compare it with several state-of-the-art methods on ISIC 2016, 2017, 2018, and PH2. Experimental results consistently demonstrate that the proposed Ms RED attains significantly superior segmentation performance across five popularly used evaluation criteria. Last but not least, the new model utilizes much fewer model parameters than its peer approaches, leading to a greatly reduced number of labeled samples required for model training, which in turn produces a substantially faster converging training process than its peers. The source code is available at https://github.com/duweidai/Ms-RED.
Objective
To assess rates and determinants of prevalence, awareness, treatment and control of hypertension in rural north-western China.
Methods
Adults were recruited from five surveillance areas in ...Gansu Province using a three-stage cluster sampling plan. A combination of household and community–based surveys was employed and two methods of surveillance (questionnaire and physical measurement) were undertaken.
Results
A total of 3000 subjects were included; 1100 (36.7%) had hypertension. Hypertension was associated with older age, lower educational levels and being overweight or obese. Only 407 (37%) subjects with hypertension were aware of their condition. Multiple logistic regression showed significant correlations between hypertension awareness and age, obesity and central obesity. Antihypertensive treatment was received by 31.2% of participants with hypertension. Obesity, smoking and older age were associated with treatment. Blood pressure was controlled in 18.1% of participants receiving antihypertensive treatment and in 5.6% of subjects with hypertension overall.
Conclusion
In conclusion, prevalence of hypertension is rapidly increasing in rural north-western China. Rates of awareness and treatment of hypertension remain low and blood pressure is poorly controlled.
The rare earth element doped germanium cluster represents a fundamental nanomaterial and exhibits potential in next‐generation industrial electronic nanodevices and applied semiconductors. Herein, ...the cerium‐doped germanium anionic nanocluster CeGen− (n = 5–17) has been comprehensively investigated by the double hybrid density functional theory of mPW2PLYP associated with the unbiased global searching technique of artificial bee colony algorithm. The cluster's growth pattern undergoes three stages: n = 5–9 with the replaced structure, n = 10–15 with the linked structure, and n ≥ 16 forming a Ce‐encapsulated in Ge inner cage motif. The clusters' PES, IR, and Raman spectra were simulated, and their HOMO‐LUMO gap, magnetism, charge transfer, and relative stability were predicted. These theoretical values can serve as a reference for future experiments to some extent. Moreover, the special D2d symmetry cage geometry of CeGe16− leads to a higher stability and preferred energy gap, making it an ideal candidate for further studies on its aromaticity, UV–vis spectra, and chemical bonding characteristics. In summary, CeGe16− has excellent optical activity that can be potentially employed as a building block in the development of optoelectronic functional materials.
Nanocluster CeGen− (n = 5–17) was investigated by mPW2PLYP quantum calculation associated with the ABCluster unbiased global searching technique. The structure growth pattern and various physicochemical properties of the clusters were predicted. The result shows CeGe16− has good stability, aromaticity, and broad sunlight absorption range.