Modeling global oceanic nitrogen deposition from food systems and its mitigation potential by reducing overuse of fertilizers.

Growing population and consumption pose unprecedented demands on food production. However, ammonia emissions mainly from food systems increase oceanic nitrogen deposition contributing to eutrophication. Here, we developed a long-term oceanic nitrogen deposition dataset (1970 to 2018) with updated ammonia emissions from food systems, evaluated the impact of ammonia emissions on oceanic nitrogen deposition patterns, and discussed the potential impact of nitrogen fertilizer overuse. Based on the chemical transport modeling approach, oceanic ammonia-related nitrogen deposition increased by 89% globally between 1970 and 2018, and now, it exceeds oxidized nitrogen deposition by over 20% in coastal regions including China Sea, India Coastal, and Northeastern Atlantic Shelves. Approximately 38% of agricultural nitrogen fertilizer was excessive, which corresponds to 15% of global oceanic ammonia-related nitrogen deposition. Policymakers and water quality managers need to pay increasingly more attention to ammonia associated with food production if the goal of reducing coastal nitrogen pollution is to be achieved for Sustainable Development Goals.

Exploring global changes in agricultural ammonia emissions and their contribution to nitrogen deposition since 1980.

SignificanceAgricultural systems are already major forces of ammonia pollution and environmental degradation. How agricultural ammonia emissions affect the spatio-temporal patterns of nitrogen deposition and where to target future mitigation efforts, remains poorly understood. We develop a substantially complete and coherent agricultural ammonia emissions dataset in nearly recent four decades, and evaluate the relative role of reduced nitrogen in total nitrogen deposition in a spatially explicit way. Global reduced nitrogen deposition has grown rapidly, and will occupy a greater dominant position in total nitrogen deposition without future ammonia regulations. Recognition of agricultural ammonia emissions on nitrogen deposition is critical to formulate effective policies to address ammonia related environmental challenges and protect ecosystems from excessive nitrogen inputs.

Attention-aware contrastive learning for predicting T cell receptor-antigen binding specificity.

MOTIVATION: It has been proven that only a small fraction of the neoantigens presented by major histocompatibility complex (MHC) class I molecules on the cell surface can elicit T cells. This restriction can be attributed to the binding specificity of T cell receptor (TCR) and peptide-MHC complex (pMHC). Computational prediction of T cells binding to neoantigens is a challenging and unresolved task. RESULTS: In this paper, we proposed an attention-aware contrastive learning model, ATMTCR, to infer the TCR-pMHC binding specificity. For each TCR sequence, we used a transformer encoder to transform it to latent representation, and then masked a percentage of amino acids guided by attention weights to generate its contrastive view. Compared to fully-supervised baseline model, we verified that contrastive learning-based pretraining on large-scale TCR sequences significantly improved the prediction performance of downstream tasks. Interestingly, masking a percentage of amino acids with low attention weights yielded best performance compared to other masking strategies. Comparison experiments on two independent datasets demonstrated our method achieved better performance than other existing algorithms. Moreover, we identified important amino acids and their positional preference through attention weights, which indicated the potential interpretability of our proposed model.

Attention-wise masked graph contrastive learning for predicting molecular property.

MOTIVATION: Accurate and efficient prediction of the molecular property is one of the fundamental problems in drug research and development. Recent advancements in representation learning have been shown to greatly improve the performance of molecular property prediction. However, due to limited labeled data, supervised learning-based molecular representation algorithms can only search limited chemical space and suffer from poor generalizability. RESULTS: In this work, we proposed a self-supervised learning method, ATMOL, for molecular representation learning and properties prediction. We developed a novel molecular graph augmentation strategy, referred to as attention-wise graph masking, to generate challenging positive samples for contrastive learning. We adopted the graph attention network as the molecular graph encoder, and leveraged the learned attention weights as masking guidance to generate molecular augmentation graphs. By minimization of the contrastive loss between original graph and augmented graph, our model can capture important molecular structure and higher order semantic information. Extensive experiments showed that our attention-wise graph mask contrastive learning exhibited state-of-the-art performance in a couple of downstream molecular property prediction tasks. We also verified that our model pretrained on larger scale of unlabeled data improved the generalization of learned molecular representation. Moreover, visualization of the attention heatmaps showed meaningful patterns indicative of atoms and atomic groups important to specific molecular property.

DeepDDS: deep graph neural network with attention mechanism to predict synergistic drug combinations.

MOTIVATION: Drug combination therapy has become an increasingly promising method in the treatment of cancer. However, the number of possible drug combinations is so huge that it is hard to screen synergistic drug combinations through wet-lab experiments. Therefore, computational screening has become an important way to prioritize drug combinations. Graph neural network has recently shown remarkable performance in the prediction of compound-protein interactions, but it has not been applied to the screening of drug combinations. RESULTS: In this paper, we proposed a deep learning model based on graph neural network and attention mechanism to identify drug combinations that can effectively inhibit the viability of specific cancer cells. The feature embeddings of drug molecule structure and gene expression profiles were taken as input to multilayer feedforward neural network to identify the synergistic drug combinations. We compared DeepDDS (Deep Learning for Drug-Drug Synergy prediction) with classical machine learning methods and other deep learning-based methods on benchmark data set, and the leave-one-out experimental results showed that DeepDDS achieved better performance than competitive methods. Also, on an independent test set released by well-known pharmaceutical enterprise AstraZeneca, DeepDDS was superior to competitive methods by more than 16% predictive precision. Furthermore, we explored the interpretability of the graph attention network and found the correlation matrix of atomic features revealed important chemical substructures of drugs. We believed that DeepDDS is an effective tool that prioritized synergistic drug combinations for further wet-lab experiment validation. AVAILABILITY AND IMPLEMENTATION: Source code and data are available at https://github.com/Sinwang404/DeepDDS/tree/master.

Contrastive learning-based computational histopathology predict differential expression of cancer driver genes.

MOTIVATION: Digital pathological analysis is run as the main examination used for cancer diagnosis. Recently, deep learning-driven feature extraction from pathology images is able to detect genetic variations and tumor environment, but few studies focus on differential gene expression in tumor cells. RESULTS: In this paper, we propose a self-supervised contrastive learning framework, HistCode, to infer differential gene expression from whole slide images (WSIs). We leveraged contrastive learning on large-scale unannotated WSIs to derive slide-level histopathological features in latent space, and then transfer it to tumor diagnosis and prediction of differentially expressed cancer driver genes. Our experiments showed that our method outperformed other state-of-the-art models in tumor diagnosis tasks, and also effectively predicted differential gene expression. Interestingly, we found the genes with higher fold change can be more precisely predicted. To intuitively illustrate the ability to extract informative features from pathological images, we spatially visualized the WSIs colored by the attention scores of image tiles. We found that the tumor and necrosis areas were highly consistent with the annotations of experienced pathologists. Moreover, the spatial heatmap generated by lymphocyte-specific gene expression patterns was also consistent with the manually labeled WSIs.

Risk of Venous Thromboembolism by Cancer Type: A Network Meta-Analysis.

Patients with cancer have an increased risk of venous thromboembolism (VTE). Comparing tumor-specific VTE risk is complicated by factors such as surgery, disease stage, and chemotherapy. Network meta-analysis (NMA) using cancer types as network nodes enabled us to estimate VTE rates by leveraging comparisons across cancer types while adjusting for baseline VTE risk in individual studies. This study was conducted to estimate the risk of VTE by cancer type and factors influencing VTE risk. The Embase, MEDLINE, and Cochrane Library repositories were systematically searched to identify clinical trials and observational studies published from 2005 to 2022 that assessed the risk of primary cancer-related VTE among two or more distinct cancer types. Studies with similar cancer populations and study methods reporting VTE occurring within 1 year of diagnosis were included in the NMA. Relative VTE rates across cancer types were estimated with random-effects Bayesian NMAs. Absolute VTE rates were calculated from these estimates using the average VTE incidence in lung cancer (the most frequently reported type) as the "anchor." From 2,603 records reviewed, 30 studies were included in this NMA. The general network described 3,948,752 patients and 18 cancer types: 3.1% experienced VTE within 1 year of diagnosis, with cancer-specific rates ranging from 0.7 to 7.4%. Consistent with existing VTE risk prediction tools, pancreatic cancer was associated with higher-than-average VTE risk. Other cancer types with high VTE risk were brain and ovarian cancers. The relative rankings of VTE risk for certain cancers changed based on disease stage and/or receipt of chemotherapy or surgery.

Setting goals for agricultural nitrogen emission reduction to ensure safe air and groundwater quality: A case study of Quzhou, the North China Plain.

Setting nitrogen (N) emission targets for agricultural systems is crucial to prevent to air and groundwater pollution, yet such targets are rarely defined at the county level. In this study, we employed a forecasting-and-back casting approach to establish human health-based nitrogen targets for air and groundwater quality in Quzhou county, located in the North China Plain. By adopting the World Health Organization (WHO) phase I standard for PM2.5 concentration (35 µg m-3) and a standard of 11.3 mg NO3--N L-1 for nitrate in drinking water, we found that ammonia (NH3) emissions from the entire county must be reduced by at least 3.2 kilotons year-1 in 2050 to meet the WHO's PM2.5 phase I standard. Additionally, controlling other pollutants such as sulfur dioxide (SO2) and nitrogen oxides (NOx) is necessary, with required reductions ranging from 16% to 64% during 2017-2050. Furthermore, to meet the groundwater quality standard, nitrate nitrogen (NO3--N) leaching to groundwater should not exceed 0.8 kilotons year-1 by 2050. Achieving this target would require a 50% reduction in NH3 emissions and a 21% reduction in NO3--N leaching from agriculture in Quzhou in 2050 compared to their respective levels in 2017 (5.0 and 2.1 kilotons, respectively). Our developed method and the resulting N emission targets can support the development of environmentally-friendly agriculture by facilitating the design of control strategies to minimize agricultural N losses.

Quantitative Cerebral Blood Volume Image Synthesis from Standard MRI Using Image-to-Image Translation for Brain Tumors.

Background Cerebral blood volume (CBV) maps derived from dynamic susceptibility contrast-enhanced (DSC) MRI are useful but not commonly available in clinical scenarios. Purpose To test image-to-image translation techniques for generating CBV maps from standard MRI sequences of brain tumors using the bookend technique DSC MRI as ground-truth references. Materials and Methods A total of 756 MRI examinations, including quantitative CBV maps produced from bookend DSC MRI, were included in this retrospective study. Two algorithms, the feature-consistency generative adversarial network (GAN) and three-dimensional encoder-decoder network with only mean absolute error loss, were trained to synthesize CBV maps. The performance of the two algorithms was evaluated quantitatively using the structural similarity index (SSIM) and qualitatively by two neuroradiologists using a four-point Likert scale. The clinical value of combining synthetic CBV maps and standard MRI scans of brain tumors was assessed in several clinical scenarios (tumor grading, prognosis prediction, differential diagnosis) using multicenter data sets (four external and one internal). Differences in diagnostic and predictive accuracy were tested using the z test. Results The three-dimensional encoder-decoder network with T1-weighted images, contrast-enhanced T1-weighted images, and apparent diffusion coefficient maps as the input achieved the highest synthetic performance (SSIM, 86.29% ± 4.30). The mean qualitative score of the synthesized CBV maps by neuroradiologists was 2.63. Combining synthetic CBV with standard MRI improved the accuracy of grading gliomas (standard MRI scans area under the receiver operating characteristic curve [AUC], 0.707; standard MRI scans with CBV maps AUC, 0.857; z = 15.17; P < .001), prediction of prognosis in gliomas (standard MRI scans AUC, 0.654; standard MRI scans with CBV maps AUC, 0.793; z = 9.62; P < .001), and differential diagnosis between tumor recurrence and treatment response in gliomas (standard MRI scans AUC, 0.778; standard MRI scans with CBV maps AUC, 0.853; z = 4.86; P < .001) and brain metastases (standard MRI scans AUC, 0.749; standard MRI scans with CBV maps AUC, 0.857; z = 6.13; P < .001). Conclusion GAN image-to-image translation techniques produced accurate synthetic CBV maps from standard MRI scans, which could be used for improving the clinical evaluation of brain tumors. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Branstetter in this issue.

Graph2MDA: a multi-modal variational graph embedding model for predicting microbe-drug associations.

MOTIVATION: Accumulated clinical studies show that microbes living in humans interact closely with human hosts, and get involved in modulating drug efficacy and drug toxicity. Microbes have become novel targets for the development of antibacterial agents. Therefore, screening of microbe-drug associations can benefit greatly drug research and development. With the increase of microbial genomic and pharmacological datasets, we are greatly motivated to develop an effective computational method to identify new microbe-drug associations. RESULTS: In this article, we proposed a novel method, Graph2MDA, to predict microbe-drug associations by using variational graph autoencoder (VGAE). We constructed multi-modal attributed graphs based on multiple features of microbes and drugs, such as molecular structures, microbe genetic sequences and function annotations. Taking as input the multi-modal attribute graphs, VGAE was trained to learn the informative and interpretable latent representations of each node and the whole graph, and then a deep neural network classifier was used to predict microbe-drug associations. The hyperparameter analysis and model ablation studies showed the sensitivity and robustness of our model. We evaluated our method on three independent datasets and the experimental results showed that our proposed method outperformed six existing state-of-the-art methods. We also explored the meaning of the learned latent representations of drugs and found that the drugs show obvious clustering patterns that are significantly consistent with drug ATC classification. Moreover, we conducted case studies on two microbes and two drugs and found 75-95% predicted associations have been reported in PubMed literature. Our extensive performance evaluations validated the effectiveness of our proposed method. AVAILABILITY AND IMPLEMENTATION: Source codes and preprocessed data are available at https://github.com/moen-hyb/Graph2MDA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Interfacial Engineering of Ni/Ni0.2Mo0.8N Heterostructured Nanorods Realizes Efficient 5-Hydroxymethylfurfural Electrooxidation and Hydrogen Evolution.

Simultaneously achieving electrochemical conversion of biomass-derived molecules into value-added products and energy-efficient hydrogen production is a highly attractive strategy but challenging. Herein, we reported a heterostructured Ni/Ni0.2Mo0.8N nanorod array electrocatalyst deposited on nickel foam (Ni/Ni0.2Mo0.8N/NF), which exhibited excellent electrocatalytic activity toward 5-hydroxymethylfurfural (HMF) oxidation, and nearly 100% conversion of HMF and 98.5% yield of 2,5-furandicarboxylic acid (FDCA) products can be achieved. The post-reaction characterizations unveil that Ni species in Ni/Ni0.2Mo0.8N/NF would be readily converted to NiOOH as the real active sites. Furthermore, a two-electrode electrolyzer was assembled with Ni/Ni0.2Mo0.8N/NF utilized as a bifunctional electrocatalyst for both the cathode and anode, giving rise to a low voltage of 1.51 V to concurrently produce FDCA and H2 at 50 mA cm-2. This work enlightens the significance of regulating redox activities of transition metals via interfacial engineering and constructing heterostructured electrocatalysts toward more efficient energy utilization.

Primary bone tumor detection and classification in full-field bone radiographs via YOLO deep learning model.

OBJECTIVES: Automatic bone lesions detection and classifications present a critical challenge and are essential to support radiologists in making an accurate diagnosis of bone lesions. In this paper, we aimed to develop a novel deep learning model called You Only Look Once (YOLO) to handle detecting and classifying bone lesions on full-field radiographs with limited manual intervention. METHODS: In this retrospective study, we used 1085 bone tumor radiographs and 345 normal bone radiographs from two centers between January 2009 and December 2020 to train and test our YOLO deep learning (DL) model. The trained model detected bone lesions and then classified these radiographs into normal, benign, intermediate, or malignant types. The intersection over union (IoU) was used to assess the model's performance in the detection task. Confusion matrices and Cohen's kappa scores were used for evaluating classification performance. Two radiologists compared diagnostic performance with the trained model using the external validation set. RESULTS: In the detection task, the model achieved accuracies of 86.36% and 85.37% in the internal and external validation sets, respectively. In the DL model, radiologist 1 and radiologist 2 achieved Cohen's kappa scores of 0.8187, 0.7927, and 0.9077 for four-way classification in the external validation set, respectively. The YOLO DL model illustrated a significantly higher accuracy for intermediate bone tumor classification than radiologist 1 (95.73% vs 88.08%, p = 0.004). CONCLUSIONS: The developed YOLO DL model could be used to assist radiologists at all stages of bone lesion detection and classification in full-field bone radiographs. KEY POINTS: • YOLO DL model can automatically detect bone neoplasms from full-field radiographs in one shot and then simultaneously classify radiographs into normal, benign, intermediate, or malignant. • The dataset used in this retrospective study includes normal bone radiographs. • YOLO can detect even some challenging cases with small volumes.

Source Apportionment of Atmospheric Ammonia at 16 Sites in China Using a Bayesian Isotope Mixing Model Based on δ15N-NHx Signatures.

Reducing atmospheric ammonia (NH3) emissions is critical to mitigating poor air quality. However, the contributions of major agricultural and non-agricultural source emissions to NH3 at receptor sites remain uncertain in many regions, hindering the assessment and implementation of effective NH3 reduction strategies. This study conducted simultaneous measurements of the monthly concentrations and stable nitrogen isotopes of NHx (gaseous NH3 plus particulate NH4+) at 16 sites across China. Ambient NHx concentrations averaged 21.7 ± 19.6 µg m-3 at rural sites, slightly higher than those at urban (19.2 ± 6.0 µg m-3) and three times of those at background (7.0 ± 6.9 µg m-3) sites. Based on revised δ15N values of the initial NH3, source apportionment results indicated that non-agricultural sources (traffic and waste) and agricultural sources (fertilizer and livestock) contributed 54 and 46% to NH3 at urban sites, 51 and 49% at rural sites, and 61 and 39% at background sites, respectively. Non-agricultural sources contributed more to NH3 at rural and background sites in cold than warm seasons, arising from traffic and waste, but were similar across seasons at urban sites. We concluded that non-agricultural sources need to be addressed when reducing ambient NH3 across China, even in rural regions.

Effectiveness and safety of blonanserin in young and middle-aged female patients with schizophrenia: data from a post-marketing surveillance.

BACKGROUND: A post-marketing surveillance of blonanserin has been ongoing since September 2018. The aim of this study was to assess the effectiveness and safety of oral blonanserin in Chinese young and middle-aged female patients with schizophrenia in real clinical settings, using the data from the post-marketing surveillance. METHODS: A 12-week, prospective, multi-center, open-label, post-marketing surveillance was conducted. Female patients aged 18-40 years were included in this analysis. The Brief Psychiatric Rating Scale (BPRS) was used to evaluate the effectiveness of blonanserin in improving psychiatric symptoms. The incidence of adverse drug reactions (ADRs) such as of extrapyramidal symptoms (EPS), prolactin elevation and the weight gain were used to evaluate the safety profile of blonanserin. RESULTS: A total of 392 patients were included both in the safety and full analysis sets, 311 patients completed the surveillance protocol. The BPRS total score was 48.8 ± 14.11 at the baseline, decreasing to 25.5 ± 7.56 at 12 weeks (P < 0.001, compared with baseline). EPS (20.2%) including akathisia, tremor, dystonia, and parkinsonism were found as the most frequent ADRs. The mean weight gain was 0.27 ± 2.5 kg at 12 weeks from the baseline. Four cases (1%) of prolactin elevation were observed during the period of surveillance. CONCLUSION: Blonanserin significantly improved the symptoms of schizophrenia in female patients aged 18-40 years; the drug was well tolerated and had a low tendency to cause metabolic side effects, including prolactin elevation in these patients. Blonanserin might be a reasonable drug for the treatment of schizophrenia in young and middle-aged female patients.

The application of machine learning to air pollution research: A bibliometric analysis.

Machine learning (ML) is an advanced computer algorithm that simulates the human learning process to solve problems. With an explosion of monitoring data and the increasing demand for fast and accurate prediction, ML models have been rapidly developed and applied in air pollution research. In order to explore the status of ML applications in air pollution research, a bibliometric analysis was made based on 2962 articles published from 1990 to 2021. The number of publications increased sharply after 2017, comprising approximately 75% of the total. Institutions in China and United States contributed half of all publications with most research being conducted by individual groups rather than global collaborations. Cluster analysis revealed four main research topics for the application of ML: chemical characterization of pollutants, short-term forecasting, detection improvement and optimizing emission control. The rapid development of ML algorithms has increased the capability to explore the chemical characteristics of multiple pollutants, analyze chemical reactions and their driving factors, and simulate scenarios. Combined with multi-field data, ML models are a powerful tool for analyzing atmospheric chemical processes and evaluating the management of air quality and deserve greater attention in future.

Safety and effectiveness of oral medium to high dose blonanserin in patients with schizophrenia: subgroup analysis from a prospective, multicenter, post-marketing surveillance study in mainland China.

BACKGROUND: Blonanserin (BNS) had been undergoing post-market surveillance (PMS) since September 2018. Using the surveillance data, we did this analysis to assess the safety and effectiveness of different doses of BNS to explore a sufficient dose range of BNS in Chinese patients with schizophrenia (SZ). METHODS: A 12-week, prospective, observational, single-arm, multicenter, open-label PMS was conducted. In this analysis, we divided the patients from PMS into low, medium to high, and high dose groups based on the dose of BNS they received, with medium to high dose group being the focus. The Brief Psychiatric Rating Scale (BPRS) scores at week 2 or 4, 6 or 8, and 12 were calculated to evaluate the effectiveness of BNS in improving psychiatric symptoms. The safety of BNS was reported as the incidence of adverse drug reactions. RESULTS: 364 patients were included in the medium to high dose group, of which 321 completed the surveillance, with a dropout rate of 11.8%. The mean daily dose was 15.1 ± 1.92 mg. The BPRS total score was 50.1 ± 11.95 at baseline and decreased to 26.6 ± 7.43 at 12 weeks (P < 0.001). When compared with other groups, the median to high dose group achieved significantly more reduction in BPRS score at week 12 (P = 0.004 versus low dose and P = 0.033 versus higher dose). Extrapyramidal symptoms [EPS (46.4%)] were the most common adverse reactions in the medium to high group. The average weight gain during the surveillance was 0.5 ± 2.56 kg and prolactin elevation occurred in 2.2% patients. Most adverse reactions were mild. CONCLUSIONS: BNS at medium to high doses (mean 15.1 mg/d) significantly improved symptoms of SZ and was well-tolerated. Most ADRs were mild, and the likelihood of causing metabolic side effects and prolactin elevations was low. Medium to high dose of BNS is a more potent treatment choice for SZ. TRIAL REGISTRATION NUMBER: ChiCTR2100048734. Date of registration: 2021/07/15 (retrospectively registered).

Crop-specific ammonia volatilization rates and key influencing factors in the upland of China - A data synthesis.

Ammonia (NH3) is an important alkaline reactive nitrogen (Nr) species which is involved in global nitrogen (N) biogeochemical cycling, but which has negative impacts on the environment and human health. In order to better understand and control the NH3 loss potential in soil-upland crop systems in China, an integrated data analysis including 1302 observations from 236 published articles between 1980 and 2021 was conducted. The typical NH3 volatilization rate (AVR) and the main factors influencing AVR in the major Chinese upland crops (maize, wheat, openfield vegetables and greenhouse vegetables and others) were estimated and analyzed. The mean AVR for maize, wheat, openfield vegetables and greenhouse vegetables were 7.8%, 5.3%, 8.4% and 1.8%. The most important influencing factors were fertilizer placement, meteorological conditions (especially temperature and rainfall) and soil properties (especially SOM). Subsurface N application produced a significantly lower AVR compared to surface application. High N recovery efficiency and N agronomic efficiency were generally associated with low AVRs. In conclusion, high N application rates, inefficient application methods and the use of loss-prone N fertilizer types are the main factors responsible for high AVRs in major Chinese croplands.

DeepMHADTA: Prediction of Drug-Target Binding Affinity Using Multi-Head Self-Attention and Convolutional Neural Network.

Drug-target interactions provide insight into the drug-side effects and drug repositioning. However, wet-lab biochemical experiments are time-consuming and labor-intensive, and are insufficient to meet the pressing demand for drug research and development. With the rapid advancement of deep learning, computational methods are increasingly applied to screen drug-target interactions. Many methods consider this problem as a binary classification task (binding or not), but ignore the quantitative binding affinity. In this paper, we propose a new end-to-end deep learning method called DeepMHADTA, which uses the multi-head self-attention mechanism in a deep residual network to predict drug-target binding affinity. On two benchmark datasets, our method outperformed several current state-of-the-art methods in terms of multiple performance measures, including mean square error (MSE), consistency index (CI), rm2, and PR curve area (AUPR). The results demonstrated that our method achieved better performance in predicting the drug-target binding affinity.

MRI comparative study of diffuse midline glioma, H3 K27-altered and glioma in the midline without H3 K27-altered.

PURPOSE: The MRI features of Diffuse midline glioma, H3 K27-altered and glioma in the midline without H3 K27-altered were compared and analyzed, and the changes in the apparent diffusion coefficient (ADC) of the two groups were quantitatively analyzed. METHODS: The MRI images of 35 patients with Diffuse midline gliomas, H3 K27-altered and gliomas in the midline without H3 K27-altered were analyzed retrospectively. The location, edge, signal, peritumoral edema and enhancement characteristics of the lesions were observed, and the changes in ADC values were analyzed. RESULTS: In the H3 K27-altered group, 85.7% (12/14) of the tumors were located in the thalamus and brainstem compared with 28.6% (6/21) in the no H3 K27-altered group. In the H3 K27-altered group, for tumors only located in the midline area, only 14.3% (1/7) had irregular shapes and unclear boundaries, while for tumors also invaded the extramidline tissues 85.7% (6/7) had irregular shapes and unclear boundaries.The"basilar artery wrapped sign" was found in 6 patients with tumors located in the pons in the H3 K27-altered group, but none in the no H3 K27-altered group had this sign. In the H3 K27-altered group, only 14.3% (1/7) of the tumors confined to the midline area had small cystic degeneration and necrosis, while for tumors also invaded the extramidline tissues, 100% (7/7) of the tumors had cystic degeneration and necrosis, and the cystic degeneration and necrosis only located in the extramidline region of the tumor in 6 cases.A total of 78.6% (11/14) of tumors in the H3 K27-altered group showed mild to moderate enhancement, while 47.6% (10/21) of tumors in the no H3 K27-altered group showed mild to moderate enhancement. The average peritumoral edema index was 1.13 in the H3 K27-altered group and 1.75 in the no H3 K27-altered group. The average ADC value of tumor in the H3 K27-altered group was 7.83 × 10- 4 mm2/s, and the ratio to normal brain tissue was 0.844, while the values in the no H3 K27-altered group were 13.5 × 10- 4 mm2/s and 1.75, respectively. CONCLUSION: Compared with gliomas in the midline without H3 K27-altered, The MRI findings and ADC value of Diffuse midline gliomas, H3K27-altered have some characteristics, which can help improve the diagnosis and differential diagnosis.

A PM2.5 concentration estimation method based on multi-feature combination of image patches.

An efficient, accurate and high-resolution PM2.5 monitoring approach is critical to pollution control and public health. Here we propose an image-based method for PM2.5 concentration estimation. The method combines the image features with other influence factors to inference PM2.5, and an improved patchwise strategy is used in the processes of regression and prediction. The experimental results of the Shanghai scene dataset show that our method achieved a higher estimation accuracy with 0.88 at R2 and 10.42 µg⋅m-3 at RMSE, compared to other methods; the addition of the influence factors, such as relative humidity and photographing month, improve the accuracy, while the improved patchwise strategy significantly enhanced the predictive performance. Moreover, the results of two datasets at different times and location further demonstrate the effectiveness and applicability of the proposed method.