Self and Mixed Supervision to Improve Training Labels for Multi-Class Medical Image Segmentation.

Accurate training labels are a key component for multi-class medical image segmentation. Their annotation is costly and time-consuming because it requires domain expertise. In our previous work, a dual-branch network was developed to segment single-class edematous adipose tissue. Its inputs include a few strong labels from manual annotation and many inaccurate weak labels from existing segmentation methods. The dual-branch network consists of a shared encoder and two decoders to process weak and strong labels. Self-supervision iteratively updates weak labels during the training process. This work aims to follow this strategy and automatically improve training labels for multi-class image segmentation. Instead of using weak and strong labels to only train the network once in the previous work, transfer learning is used to train the network and improve weak labels sequentially. The dual-branch network is first trained by weak labels alone to initialize model parameters. After the network is stabilized, the shared encoder is frozen, and strong and weak decoders are fine-tuned by strong and weak labels together. The accuracy of weak labels is iteratively improved in the fine-tuning process. The proposed method was applied to a three-class segmentation of muscle, subcutaneous and visceral adipose tissue on abdominal CT scans. Validation results on 11 patients showed that the accuracy of training labels was statistically significantly improved, with the Dice similarity coefficient of muscle, subcutaneous and visceral adipose tissue increased from 74.2% to 91.5%, 91.2% to 95.6%, and 77.6% to 88.5%, respectively (p<0.05). In comparison with our earlier method, the label accuracy was also significantly improved (p<0.05). These experimental results suggested that the combination of the dual-branch network and transfer learning is an efficient means to improve training labels for multi-class segmentation.

Enhanced muscle and fat segmentation for CT-based body composition analysis: a comparative study.

PURPOSE: Body composition measurements from routine abdominal CT can yield personalized risk assessments for asymptomatic and diseased patients. In particular, attenuation and volume measures of muscle and fat are associated with important clinical outcomes, such as cardiovascular events, fractures, and death. This study evaluates the reliability of an Internal tool for the segmentation of muscle and fat (subcutaneous and visceral) as compared to the well-established public TotalSegmentator tool. METHODS: We assessed the tools across 900 CT series from the publicly available SAROS dataset, focusing on muscle, subcutaneous fat, and visceral fat. The Dice score was employed to assess accuracy in subcutaneous fat and muscle segmentation. Due to the lack of ground truth segmentations for visceral fat, Cohen's Kappa was utilized to assess segmentation agreement between the tools. RESULTS: Our Internal tool achieved a 3% higher Dice (83.8 vs. 80.8) for subcutaneous fat and a 5% improvement (87.6 vs. 83.2) for muscle segmentation, respectively. A Wilcoxon signed-rank test revealed that our results were statistically different with p < 0.01. For visceral fat, the Cohen's Kappa score of 0.856 indicated near-perfect agreement between the two tools. Our internal tool also showed very strong correlations for muscle volume (R 2 =0.99), muscle attenuation (R 2 =0.93), and subcutaneous fat volume (R 2 =0.99) with a moderate correlation for subcutaneous fat attenuation (R 2 =0.45). CONCLUSION: Our findings indicated that our Internal tool outperformed TotalSegmentator in measuring subcutaneous fat and muscle. The high Cohen's Kappa score for visceral fat suggests a reliable level of agreement between the two tools. These results demonstrate the potential of our tool in advancing the accuracy of body composition analysis.

Weakly Supervised Detection of Pheochromocytomas and Paragangliomas in CT.

Pheochromocytomas and Paragangliomas (PPGLs) are rare adrenal and extra-adrenal tumors which have the potential to metastasize. For the management of patients with PPGLs, CT is the preferred modality of choice for precise localization and estimation of their progression. However, due to the myriad variations in size, morphology, and appearance of the tumors in different anatomical regions, radiologists are posed with the challenge of accurate detection of PPGLs. Since clinicians also need to routinely measure their size and track their changes over time across patient visits, manual demarcation of PPGLs is quite a time-consuming and cumbersome process. To ameliorate the manual effort spent for this task, we propose an automated method to detect PPGLs in CT studies via a proxy segmentation task. As only weak annotations for PPGLs in the form of prospectively marked 2D bounding boxes on an axial slice were available, we extended these 2D boxes into weak 3D annotations and trained a 3D full-resolution nnUNet model to directly segment PPGLs. We evaluated our approach on a dataset consisting of chest-abdomen-pelvis CTs of 255 patients with confirmed PPGLs. We obtained a precision of 70% and sensitivity of 64.1% with our proposed approach when tested on 53 CT studies. Our findings highlight the promising nature of detecting PPGLs via segmentation, and furthers the state-of-the-art in this exciting yet challenging area of rare cancer management.

Automated Plaque Detection and Agatston Score Estimation on Non-Contrast CT Scans: A Multicenter Study.

Coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular disease (CVD). However, manual assessment of CAC often requires radiological expertise, time, and invasive imaging techniques. The purpose of this multicenter study is to validate an automated cardiac plaque detection model using a 3D multiclass nnU-Net for gated and non-gated non-contrast chest CT volumes. CT scans were performed at three tertiary care hospitals and collected as three datasets, respectively. Heart, aorta, and lung segmentations were determined using TotalSegmentator, while plaques in the coronary arteries and heart valves were manually labeled for 801 volumes. In this work we demonstrate how the nnU-Net semantic segmentation pipeline may be adapted to detect plaques in the coronary arteries and valves. With a linear correction, nnU-Net deep learning methods may also accurately estimate Agatston scores on chest non-contrast CT scans. Compared to manual Agatson scoring, automated Agatston scoring indicated a slope of the linear regression of 0.841 with an intercept of +16 HU (R2 = 0.97). These results are an improvement over previous work assessing automated Agatston score computation in non-gated CT scans.

Automated Classification of Body MRI Sequence Type Using Convolutional Neural Networks.

Multi-parametric MRI of the body is routinely acquired for the identification of abnormalities and diagnosis of diseases. However, a standard naming convention for the MRI protocols and associated sequences does not exist due to wide variations in imaging practice at institutions and myriad MRI scanners from various manufacturers being used for imaging. The intensity distributions of MRI sequences differ widely as a result, and there also exists information conflicts related to the sequence type in the DICOM headers. At present, clinician oversight is necessary to ensure that the correct sequence is being read and used for diagnosis. This poses a challenge when specific series need to be considered for building a cohort for a large clinical study or for developing AI algorithms. In order to reduce clinician oversight and ensure the validity of the DICOM headers, we propose an automated method to classify the 3D MRI sequence acquired at the levels of the chest, abdomen, and pelvis. In our pilot work, our 3D DenseNet-121 model achieved an F1 score of 99.5% at differentiating 5 common MRI sequences obtained by three Siemens scanners (Aera, Verio, Biograph mMR). To the best of our knowledge, we are the first to develop an automated method for the 3D classification of MRI sequences in the chest, abdomen, and pelvis, and our work has outperformed the previous state-of-the-art MRI series classifiers.

Enhanced Muscle and Fat Segmentation for CT-Based Body Composition Analysis: A Comparative Study.

Purpose: Body composition measurements from routine abdominal CT can yield personalized risk assessments for asymptomatic and diseased patients. In particular, attenuation and volume measures of muscle and fat are associated with important clinical outcomes, such as cardiovascular events, fractures, and death. This study evaluates the reliability of an Internal tool for the segmentation of muscle and fat (subcutaneous and visceral) as compared to the well-established public TotalSegmentator tool. Methods: We assessed the tools across 900 CT series from the publicly available SAROS dataset, focusing on muscle, subcutaneous fat, and visceral fat. The Dice score was employed to assess accuracy in subcutaneous fat and muscle segmentation. Due to the lack of ground truth segmentations for visceral fat, Cohen's Kappa was utilized to assess segmentation agreement between the tools. Results: Our Internal tool achieved a 3% higher Dice (83.8 vs. 80.8) for subcutaneous fat and a 5% improvement (87.6 vs. 83.2) for muscle segmentation respectively. A Wilcoxon signed-rank test revealed that our results were statistically different with p < 0.01. For visceral fat, the Cohen's kappa score of 0.856 indicated near-perfect agreement between the two tools. Our internal tool also showed very strong correlations for muscle volume (R2=0.99), muscle attenuation (R2=0.93), and subcutaneous fat volume (R2=0.99) with a moderate correlation for subcutaneous fat attenuation (R2=0.45). Conclusion: Our findings indicated that our Internal tool outperformed TotalSegmentator in measuring subcutaneous fat and muscle. The high Cohen's Kappa score for visceral fat suggests a reliable level of agreement between the two tools. These results demonstrate the potential of our tool in advancing the accuracy of body composition analysis.

Improved subcutaneous edema segmentation on abdominal CT using a generated adipose tissue density prior.

PURPOSE: Edema, or swelling, is a common symptom of kidney, heart, and liver disease. Volumetric edema measurement is potentially clinically useful. Edema can occur in various tissues. This work focuses on segmentation and volume measurement of one common site, subcutaneous adipose tissue. METHODS: The density distributions of edema and subcutaneous adipose tissue are represented as a two-class Gaussian mixture model (GMM). In previous work, edema regions were segmented by selecting voxels with density values within the edema density distribution. This work improves upon the prior work by generating an adipose tissue mask without edema through a conditional generative adversarial network. The density distribution of the generated mask was imported into a Chan-Vese level set framework. Edema and subcutaneous adipose tissue are separated by iteratively updating their respective density distributions. RESULTS: Validation results on 25 patients with edema showed that the segmentation accuracy significantly improved. Compared to GMM, the average Dice Similarity Coefficient increased from 56.0 to 61.7% ([Formula: see text]) and the relative volume difference decreased from 36.5 to 30.2% ([Formula: see text]). CONCLUSION: The generated adipose tissue density prior improved edema segmentation accuracy. Accurate edema volume measurement may prove clinically useful.

ONOO- Activatable Fluorescent Sulfur Dioxide Donor for a More Accurate Assessment of Cell Ferroptosis.

Ferroptosis is critical in the treatment of tumor therapies. Thus, monitoring reactive oxygen species (ROS) is of great significance for accurate assessment in ferroptosis without any interference. However, current probes for monitoring ROS during ferroptosis suffer from a drawback in that the probes consume ROS during detection, which inhibits the ferroptosis process and thus affects the accuracy and effectiveness of monitoring the process of ferroptosis. Herein, a new fluorescent donor probe, TFMU-SO2D, with the combination of the moiety of the SO2 donor is designed and synthesized by introducing the aryl boronate moieties that could give it the ability to effectively recognize ONOO-. The released SO2 could consume excess glutathione and regulate oxidative stress by elevating ROS levels, which would offset the ROS depletion by TFMU-SO2D and ensure accuracy in monitoring the ferroptosis process. The experimental results demonstrated that TFMU-SO2D possessed satisfactory performance for monitoring ONOO- as well as simultaneously releasing SO2 in oxidative stress stimulated by monensin and ferroptosis stimulated by erastin and RSL3. Additionally, the capability of SO2 synergized with ferroptosis to inhibit the viability of cancer cells was demonstrated by the CCK8 assay, which may be due to the fact that SO2 can potentiate ferroptosis cell death by increasing the ROS level. Overall, these combined results indicated that TFMU-SO2D possesses the excellent ability to precisely monitor ONOO- during ferroptosis without interference, which is significant for accurately accessing ferroptosis, cancer treatment, and drug development.

Birefringence characterization in a dual-hole microstructured optical fiber using an OFDR method.

The birefringence in a dual-hole microstructured optical fiber is numerically calculated and characterized with an optical frequency domain reflectometry (OFDR) method. Due to the asymmetric dual air holes in the cross-section, the polarized L P01x and L P01y modes propagate with different group velocities and time delays. Through a polarized coherent OFDR system in experiment, the Fresnel reflection peaks for each mode are separated in the frequency domain with their corresponding beat frequency. Thus, the group birefringence -9.68×10-4 is calculated with a beat frequency difference of 50.03 Hz between the L P01x and L P01y modes at a 6.2 m fiber end, which is in good agreement with that of -9.54×10-4 from the theoretical simulation. Our demonstration provides an accurate and flexible method for group birefringence characterization in microstructured optical fibers with complex cross-sectional structures.

Evaluation of a novel lysis-based sample processing method to optimize Vibrio vulnificus detecting by loop-mediated isothermal amplification assay.

BACKGROUND: Vibrio vulnificus exists as one of the most serious foodborne pathogens for humans, and rapid and sensitive detection methods are needed to control its infections. As an emerging method, The Loop-Mediated Isothermal Amplification (LAMP) assay has been applied to the early detection of various foodborne pathogens due to its high efficiency, but sample preprocessing still prolongs the complete detection. To optimize the detection process, our study established a novel sample preprocessing method that was more efficient compared to common methods. RESULT: Using V. vulnificus as the detecting pathogen, the water-lysis-based detecting LAMP method shortened the preprocessing time to ≤ 1 min with 100% LAMP specificity; the detection limits of the LAMP assay were decreased to 1.20 × 102 CFU/mL and 1.47 × 103 CFU/g in pure culture and in oyster, respectively. Furthermore, the 100% LAMP specificity and high sensitivity of the water-lysis method were also obtained on detecting V. parahaemolyticus, V. alginolyticus, and P. mirabilis, revealing its excellent LAMP adaption with improvement in sensitivity and efficiency. CONCLUSION: Our study provided a novel LAMP preprocessing method that was more efficient compared to common methods and possessed the practical potential for LAMP application in the future.

Fully Reversible and Super-Fast Photo-Induced Morphological Transformation of Nanofilms for High-Performance UV Detection and Light-Driven Actuators.

Flexible and highly ultraviolet (UV) sensitive materials garner considerable attention in wearable devices, adaptive sensors, and light-driven actuators. Herein, a type of nanofilms with unprecedented fully reversible UV responsiveness are successfully constructed. Building upon this discovery, a new system for ultra-fast, sensitive, and reliable UV detection is developed. The system operates by monitoring the displacement of photoinduced macroscopic motions of the nanofilms based composite membranes. The system exhibits exceptional responsiveness to UV light at 375 nm, achieving remarkable response and recovery times of < 0.3 s. Furthermore, it boasts a wide detection range from 2.85 µW cm-2 to 8.30 mW cm-2, along with robust durability. Qualitative UV sensing is accomplished by observing the shape changes of the composite membranes. Moreover, the composite membrane can serve as sunlight-responsive actuators for artificial flowers and smart switches in practical scenarios. The photo-induced motion is ascribed to the cis-trans isomerization of the acylhydrazone bonds, and the rapid and fully reversible shape transformation is supposed to be a synergistic result of the instability of the cis-isomers acylhydrazone bonds and the rebounding property of the networked nanofilms. These findings present a novel strategy for both quantitative and qualitative UV detection.

Separation of polysaccharides from Lycium barbarum L. by high-speed countercurrent chromatography with aqueous two-phase system.

The traditional method for isolation and purification of polysaccharides is time-consuming. It often involves toxic solvents that destroy the function and structure of the polysaccharides, thus limiting in-depth research on the essential active ingredient of Lycium barbarum L. Therefore, in this study, high-speed countercurrent chromatography (HSCCC) and aqueous two-phase system (ATPS) were combined for the separation of crude polysaccharides of Lycium barbarum L. (LBPs). Under the optimized HSCCC conditions of PEG1000-K2HPO4-KH2PO4-H2O (12:10:10:68, w/w), 1.0 g of LBPs-ILs was successfully divided into three fractions (126.0 mg of LBPs-ILs-1, 109.9 mg of LBPs-ILs-2, and 65.4 mg of LBPs-ILs-3). Moreover, ATPS was confirmed as an efficient alternative method of pigment removal for LBPs purification, with significantly better decolorization (97.1 %) than the traditional H2O2 method (88.5 %). Then, the different partitioning behavior of LBPs-ILs in the two-phase system of HSCCC was preliminarily explored, which may be related to the difference in monosaccharide composition of polysaccharides. LBPs-ILs-1 exhibited better hypoglycemic activities than LBPs-ILs-2 and LBPs-ILs-3 in vitro. Therefore, HSCCC, combined with aqueous two-phase system, was an efficient separation and purification method with great potential for separating and purifying active polysaccharides in biological samples.

Larger deep white matter hyperintensity volume correlates with more severe social behavioral changes in patients with subacute ischemic stroke.

Background: Changes in social behavior can occur after ischemic stroke. We aimed to investigate the potential correlations between neuroimaging variables and changes in social behavior in patients who experienced subacute ischemic stroke. Methods: We prospectively screened patients with first-ever ischemic stroke. Three months after the index stroke, changes in patients' social behavior were investigated by the Frontal Behavioral Inventory (FBI), which consists of both deficit and positive groups of behaviors. The protocol of brain magnetic resonance imaging (MRI) including the baseline MRI at the acute stage and additional MRI with three-dimensional T1-weighted imaging on follow-up. Using these MRI scans, we assessed the acute infarction and the volumes of various brain structures by an automatic volumetry tool. Results: Eighty patients were enrolled. In univariate analyses, patients with deficit behavioral changes had more left cortical infarction (r = 0.271, p = 0.015), Cholinergic Pathways Hyperintensities Scale scores (r = 0.227, p = 0.042), DWMH volumes (r = 0.349, p = 0.001), and modified Rankin Scale (mRS) scores (r = 0.392, p < 0.001). Patients with positive behavioral changes had more frequency of men (r = 0.229, p = 0.041) and a history of hypertension (r = 0.245, p = 0.028). In multiple stepwise linear regression models, after adjusting for age, deep WMH volumes (ß = 0.849, 95% confidence interval = 0.352-1.346, p = 0.001) and mRS scores on follow-up (ß = 1.821, 95% confidence interval = 0.881-2.76, p < 0.001) were significantly correlated with deficit behavioral changes (R2 = 0.245). Conclusion: Larger deep WMH volumes and poorer mRS scores on follow-up were significantly correlated with deficit behavioral changes in patients with subacute ischemic stroke.

Non-destructive detection of protein content in mulberry leaves by using hyperspectral imaging.

Protein content is one of the most important indicators for assessing the quality of mulberry leaves. This work is carried out for the rapid and non-destructive detection of protein content of mulberry leaves using hyperspectral imaging (HSI) (Specim FX10 and FX17, Spectral Imaging Ltd., Oulu, Finland). The spectral range of the HSI acquisition system and data processing methods (pretreatment, feature extraction, and modeling) is compared. Hyperspectral images of three spectral ranges in 400-1,000 nm (Spectral Range I), 900-1,700 nm (Spectral Range II), and 400-1,700 nm (Spectral Range III) were considered. With standard normal variate (SNV), Savitzky-Golay first-order derivation, and multiplicative scatter correction used to preprocess the spectral data, and successive projections algorithm (SPA), competitive adaptive reweighted sampling, and random frog used to extract the characteristic wavelengths, regression models are constructed by using partial least square and least squares-support vector machine (LS-SVM). The protein content distribution of mulberry leaves is visualized based on the best model. The results show that the best results are obtained with the application of the model constructed by combining SNV with SPA and LS-SVM, showing an R 2 of up to 0.93, an RMSE of just 0.71 g/100 g, and an RPD of up to 3.83 based on the HSI acquisition system of 900-1700 nm. The protein content distribution map of mulberry leaves shows that the protein of healthy mulberry leaves distributes evenly among the mesophyll, with less protein content in the vein of the leaves. The above results show that rapid, non-destructive, and high-precision detection of protein content of mulberry leaves can be achieved by applying the SWIR HSI acquisition system combined with the SNV-SPA-LS-SVM algorithm.

Discovery of all-inorganic lead-free perovskites with high photovoltaic performance via ensemble machine learning.

Growing evidence shows that all-inorganic lead-free perovskites hold promise for solving stability and toxicity problems in perovskite solar cells. However, the power conversion efficiency of all-inorganic perovskites cannot match that of hybrid organic-inorganic perovskites. To face the challenges of efficiency, stability and toxicity simultaneously for application in perovskite solar cells, this study conducts a high-throughput materials search via ensemble machine learning for nearly 12 million all-inorganic perovskites to obtain candidates with non-toxicity and excellent photovoltaic performance. Based on experimental data, models for structure identification and band gap classification are established for , and a physics-inspired multi-component neural network is proposed as part of the exploration of the model's logical structure. It is found that extracting key features for input into the model and treating non-key features as supplements make model learning easier and are more effective in reducing the model parameters. Then, based on established ensemble models as well as the new criteria of ion radius difference and the optimization rules of toxicity and cost, over 80 000 candidates are screened. Among the 34 lead-free identified with suitable band gaps and negative formation energies through first principles calculations, 17 candidates have theoretical power conversion efficiencies over 20%. The Debye temperature of 10 lead-free , basically Bi-based compounds, is greater than 350 K, which is advantageous for suppressing nonradiative recombination and thermally induced degradation.

The effects of polyethylene microplastics on the growth, reproduction, metabolic enzymes, and metabolomics of earthworms Eisenia fetida.

The existing data regarding the effects of polyethylene (PE) microplastics (MPs) smaller than 5 mm in size on earthworms are insufficient to fully comprehend their toxicity. In this study, earthworms Eisenia fetida were exposed to artificially added PE at a concentration ranging from 0.05 to 20 g/kg soil (0.005%-2%) for 60 days to determine the concentration range causing negative effects on earthworms and to uncover the potential toxic mechanisms. The individual growth, reproduction, and metabolic enzyme activities, including phase I enzymes (cytochrome P450 [CYP] 1A2, 2B6, 2C9, and 3A4), and phase II metabolic enzymes (superoxide dismutase (SOD), catalase (CAT), and glutathione sulfotransferase (GST)), and metabolomics were measured. The observed variations in responses of multiple cross-scale endpoints indicated that individual indices are less responsive to PE MPs than metabolic enzymes or metabolomics. Despite the absence of significant alterations in growth inhibition based on body weight, PE MPs at concentrations equal to or exceeding 2.5 g/kg were found to exert a toxic effect on earthworms, which was evidenced by significant changes in metabolic enzyme activities (CYP1A2, 2B6, 2C9, and 3A4, SOD, CAT, and GST) and important small molecule metabolites screened based on metabolomics, likely due to the bioaccumulation of PE. The toxicity of PE MPs to earthworms is inferred to be associated with neurotoxicity, oxidative damage, decreased detoxification capacity, energy metabolism imbalance, and impaired amino acid and purine metabolism due to bioaccumulation. The findings of this study will enhance our understanding of the molecular toxicity mechanisms of PE MPs and contribute to a more accurate assessment of the ecological risks posed by PE MPs in soil.

Towards a scalable and controllable preparation of highly-uniform surface-enhanced Raman scattering substrates: Defect-free nanofilms as templates.

The uniformity and reproducibility of substrates highly determine the applicability of surface-enhanced Raman scattering (SERS). Production of them, however, remains a challenge. Herein, we report a template-based strategy for the strictly controllable and handily scalable preparation of a very uniform SERS substrate, Ag nanoparticles (AgNPs)/nanofilm, where the template used is a flexible, transparent, self-standing, defect-free and robust nanofilm. Importantly, the obtained AgNPs/nanofilm is self-adhesive to surfaces of different properties and morphologies, ensuring in-situ and at real-time SERS detection. The enhancement factor (EF) of the substrate for rhodamine 6G (R6G) could reach 5.8 × 1010 with a detection limit (DL) of 1.0 × 10-15 mol L-1. Moreover, 500 bending tests and one-month storage showed no observable performance degradation, and up to 50.0 cm2 scaled-up preparation depicted negligible effect upon the structure and the sensing performance. The real-life applicability of AgNPs/nanofilm was demonstrated by the sensitive detection of tetramethylthiuram disulfide on cherry tomato and fentanyl in methanol with a routine handheld Raman spectrometer. This work thus provides a reliable strategy for large area wet-chemical preparation of high-quality SERS substrates.

Prediction of liver cancer prognosis based on immune cell marker genes.

Introduction: Monitoring the response after treatment of liver cancer and timely adjusting the treatment strategy are crucial to improve the survival rate of liver cancer. At present, the clinical monitoring of liver cancer after treatment is mainly based on serum markers and imaging. Morphological evaluation has limitations, such as the inability to measure small tumors and the poor repeatability of measurement, which is not applicable to cancer evaluation after immunotherapy or targeted treatment. The determination of serum markers is greatly affected by the environment and cannot accurately evaluate the prognosis. With the development of single cell sequencing technology, a large number of immune cell-specific genes have been identified. Immune cells and microenvironment play an important role in the process of prognosis. We speculate that the expression changes of immune cell-specific genes can indicate the process of prognosis. Method: Therefore, this paper first screened out the immune cell-specific genes related to liver cancer, and then built a deep learning model based on the expression of these genes to predict metastasis and the survival time of liver cancer patients. We verified and compared the model on the data set of 372 patients with liver cancer. Result: The experiments found that our model is significantly superior to other methods, and can accurately identify whether liver cancer patients have metastasis and predict the survival time of liver cancer patients according to the expression of immune cell-specific genes. Discussion: We found these immune cell-specific genes participant multiple cancer-related pathways. We fully explored the function of these genes, which would support the development of immunotherapy for liver cancer.

Non-destructive prediction and visualization of anthocyanin content in mulberry fruits using hyperspectral imaging.

Being rich in anthocyanin is one of the most important physiological traits of mulberry fruits. Efficient and non-destructive detection of anthocyanin content and distribution in fruits is important for the breeding, cultivation, harvesting and selling of them. This study aims at building a fast, non-destructive, and high-precision method for detecting and visualizing anthocyanin content of mulberry fruit by using hyperspectral imaging. Visible near-infrared hyperspectral images of the fruits of two varieties at three maturity stages are collected. Successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS) and stacked auto-encoder (SAE) are used to reduce the dimension of high-dimensional hyperspectral data. The least squares-support vector machine and extreme learning machine (ELM) are used to build models for predicting the anthocyanin content of mulberry fruit. And genetic algorithm (GA) is used to optimize the major parameters of models. The results show that the higher the anthocyanin content is, the lower the spectral reflectance is. 15, 7 and 13 characteristic variables are extracted by applying CARS, SPA and SAE respectively. The model based on SAE-GA-ELM achieved the best performance with R2 of 0.97 and the RMSE of 0.22 mg/g in both the training set and testing set, and it is applied to retrieve the distribution of anthocyanin content in mulberry fruits. By applying SAE-GA-ELM model to each pixel of the mulberry fruit images, distribution maps are created to visualize the changes in anthocyanin content of mulberry fruits at three maturity stages. The overall results indicate that hyperspectral imaging, in combination with SAE-GA-ELM, can help achieve rapid, non-destructive and high-precision detection and visualization of anthocyanin content in mulberry fruits.

Imine Bond-Based Fluorescent Nanofilms toward High-Performance Detection and Efficient Removal of HCl and NH3.

A new kind of imine bond-based fluorescent nanofilm was developed as multifunctional materials for high-performance detection and efficient removal of hydrogen chloride (HCl) and ammonia (NH3). The flexible, uniform, and photochemically stable nanofilms as prepared showed fast (<1 and <0.5 s), sensitive (<150 ppb and <1.5 ppm), and selective response to HCl and NH3, respectively, and the removal efficiencies to HCl and NH3 are 187.5 and 37.5% (w/w), respectively. A reversible earthy-red to green fluorescence color change upon adsorption of NH3 or HCl enabled visualized monitoring of the two gases in the air. Mechanism studies revealed that the adsorption of HCl is a result of hydrogen bond formation between the analyte and the imine groups. Adsorption of NH3, however, is a result of chemical reaction with the pre-adsorbed HCl. The applicability of the detection and removal strategies as developed was further verified by conducting the tests on real-life or simulated scenarios.