UR-Net: An Integrated ResUNet and Attention Based Image Enhancement and Classification Network for Stain-Free White Blood Cells.

The differential count of white blood cells (WBCs) can effectively provide disease information for patients. Existing stained microscopic WBC classification usually requires complex sample-preparation steps, and is easily affected by external conditions such as illumination. In contrast, the inconspicuous nuclei of stain-free WBCs also bring great challenges to WBC classification. As such, image enhancement, as one of the preprocessing methods of image classification, is essential in improving the image qualities of stain-free WBCs. However, traditional or existing convolutional neural network (CNN)-based image enhancement techniques are typically designed as standalone modules aimed at improving the perceptual quality of humans, without considering their impact on advanced computer vision tasks of classification. Therefore, this work proposes a novel model, UR-Net, which consists of an image enhancement network framed by ResUNet with an attention mechanism and a ResNet classification network. The enhancement model is integrated into the classification model for joint training to improve the classification performance for stain-free WBCs. The experimental results demonstrate that compared to the models without image enhancement and previous enhancement and classification models, our proposed model achieved a best classification performance of 83.34% on our stain-free WBC dataset.

Label-free white blood cells classification using a deep feature fusion neural network.

White blood cell (WBC) classification is a valuable diagnostic approach for identifying diseases. However, conventional methods for WBC detection, such as flow cytometers, have limitations in terms of their high cost, large system size, and laborious staining procedures. As a result, deep learning-based label-free WBC image analysis methods are gaining popularity. Nevertheless, most existing deep learning WBC classification techniques fail to effectively utilize the subtle differences in the internal structures of WBCs observed under a microscope. To address this issue, we propose a neural network with feature fusion in this study, which enables the detection of label-free WBCs. Unlike conventional convolutional neural networks (CNNs), our approach combines low-level features extracted by shallow layers with high-level features extracted by deep layers, generating fused features for accurate bright-field WBC identification. Our method achieves an accuracy of 80.3 % on the testing set, demonstrating a potential solution for deep-learning-based biomedical diagnoses. Considering the proposed method simplifies the cell detection process and eliminates the need for complex operations like fluorescent staining, we anticipate that this automatic and label-free WBC classification network could facilitate more precise and effective analysis, and it could contribute to the future adoption of miniatured flow cytometers for point-of-care (POC) diagnostics applications.

De novo transcriptome assembly and metabolomic analysis of three tissue types in Cinnamomum cassia.

Objective: The barks, leaves, and branches of Cinnamomum cassia have been historically used as a traditional Chinese medicine, spice, and food preservative, in which phenylpropanoids are responsible compounds. However phenylpropanoid biosynthesis pathways are not clear in C. cassia. We elucidated the pathways by descriptive analyses of differentially expressed genes related to phenylpropanoid biosynthesis as well as to identify various phenylpropanoid metabolites. Methods: Chemical analysis, metabolome sequencing, and transcriptome sequencing were performed to investigate the molecular mechanisms underlying the difference of active components content in the barks, branches and leaves of C. cassia. Results: Metabolomic analysis revealed that small amounts of flavonoids, coumarine, and cinnamaldehyde accumulated in both leaves and branches. Transcriptome analysis showed that genes associated with phenylpropanoid and flavonoid biosynthesis were downregulated in the leaves and branches relative to the barks. The observed differences in essential oil content among the three tissues may be attributable to the differential expression of genes involved in the phenylpropanoid and flavonoid metabolic pathways. Conclusion: This study identified the key genes in the phenylpropanoid pathway controling the flavonoid, coumarine, and cinnamaldehyde contents in the barks, branches and leaves by comparing the transcriptome and metabolome. These findings may be valuable in assessing phenylpropanoid and flavonoid metabolites and identifying specific candidate genes that are related to the synthesis of phenylpropanoids and flavonoids in C. cassia.

Long-term continuous and real-time in situ monitoring of Pb(II) toxic contaminants in wastewater using solid-state ion selective membrane (S-ISM) Pb and pH auto-correction assembly.

Lead (Pb) contaminants in wastewater have inhibited microbial activities and thus exerted high energy consumption in wastewater treatment plants (WWTPs). Current Pb monitoring has been conducted ex situ and off line, unable to affect real-time proactive control and operation. This study targets the crucial challenge of better and faster Pb monitoring by developing novel mm-sized screen-printed solid-state ion-selective membrane (S-ISM) Pb sensors with low-cost, high accuracy and long-term durability and that enable real-time in situ monitoring of Pb(II) ion contamination down to low concentrations (15 ppb-960 ppb) in wastewater. An innovative pH auto-correction data-driven model was built to overcome the inextricable pH inferences on Pb(II) ISM sensors in wastewater. Electrochemical impedance spectroscopy (EIS) and cyclic voltammograms (CV) analysis showed (3,4-ethylenedioxythiophene, EDOT) deposited onto the mm-sized screen-printed carbon electrodes using electropolymerization effectively alleviated the interferences from dissolved oxygen and improved long-term stability in wastewater. Monte Carlo simulation of the nitrification process predicted that real-time, and high accurate in situ monitoring of Pb(II) in wastewater and swift feedback control could save ∼53 % of energy consumption by alleviating the errors from pH and DO impacts in WWTPs.