Removing ring artifacts in CBCT images via Transformer with unidirectional vertical gradient loss.

BACKGROUND: Cone-beam computed tomography (CBCT), an important medical modality for disease detection and diagnosis, is currently widely used in clinical practice. However, due to the inconsistent response of CBCT detectors, the lack of proper calibration often leads to the occurrence of ring artifacts in CBCT-reconstructed images. These artifacts may affect physicians' assessment and diagnosis. Therefore, effective elimination of ring artifacts in CBCT images without degrading image quality is important. PURPOSE: Given the pros and cons of existing methods for removing ring artifacts in CBCT images, this paper is devoted to designing a specific Transformer for this task, leveraging the global and local modeling ability of Transformer. METHODS: We design a loss function with dual-domain information fusion for the vanilla Transformer to correct ring artifacts in CBCT images. The method operates in image domain to predict artifact-free outputs and preserve more image details. Meanwhile, we design a tailored loss function incorporating polar domain optimization to remove ring artifacts more effectively. Specifically, an unidirectional gradient loss that constrains vertical gradients in polar domain is imposed, based on the geometric prior that in polar coordinates, ring artifacts predominately affect horizontal gradients while minimally influencing vertical gradients. RESULTS: We conduct extensive ablative and comparative experiments on CBCT/CT image set to validate the performance of the proposed method. First, four ablation experiments demonstrate the feasibility of our approach. Then, we compare our method with several classical methods and the latest state-of-the-arts, and our method achieves the highest quality of corrected images as well as the best evaluation metrics. In these experiments, 5332 CT images were used for training, and 550 CT images, and 500 real CBCT images were used for testing. The source code is available at https://github.com/shasha521/CBCT. CONCLUSIONS: Experimental results demonstrate that our method can significantly improve the effectiveness of ring artifact correction. By capitalizing on dual-domain information fusion and a customized loss function, the improved Transformer can not only effectively remove ring artifacts in CBCT images, but also preserve the details of original images quite well.

Phylogenomics and biogeographical diversification of Collabieae (Orchidaceae) and its implication in the reconstruction of the dynamic history of Asian evergreen broadleaved forests.

The tribe Collabieae (Epidendroideae, Orchidaceae) comprises approximately 500 species. Generic delimitation within Collabieae are confusing and phylogenetic interrelationships within the Collabieae have not been well resolved. Plastid genomes and nuclear internal transcribed spacer (ITS) sequences were used to estimate the phylogenetic relationships, ancestral ranges, and diversification rates of Collabieae. The results showed that Collabieae was subdivided into nine clades with high support. We proposed to combine Ancistrochilus and Pachystoma into Spathoglottis, merge Collabium and Chrysoglossum into Diglyphosa, and separate Pilophyllum and Hancockia as distinctive genera. The diversification of the nine clades of Collabieae might be associated with the uplift of the Himalayas during the Late Oligocene/Early Miocene. The enhanced East Asian summer monsoon in the Late Miocene may have promoted the rapid diversification of Collabieae at a sustained high diversification rate. The increased size of terrestrial pseudobulbs may be one of the drivers of Collabieae diversification. Our results suggest that the establishment and development of evergreen broadleaved forests facilitated the diversification of Collabieae.

Characteristics of the Hantaan virus complicated with SARS-CoV2 infection: A case series report.

Background: Coinfection poses a persistent threat to global public health due to its severe effect on individual-level infection risk and disease outcome. Coinfection of SARS-CoV2 with one or more pathogens has been documented. Nevertheless, this virus co-infected with the Hantaan virus (HTNV) is rarely reported. Case summary: Here, we presented three cases of HTNV complicated with SARS-CoV2 infection. Not only the conditions including general clinical manifestations, immune and inflammation parameters fluctuation presented in the single infection of HTNV or SARS-CoV2 can be found, but also the unexpected manifestations have attracted our attention that presented as more symptoms of HTNV infection including exudative changes in both lungs and an amount of bilateral pleural effusion as well as bilateral kidney enlargement rather than typical viral pneumonia in SARS-CoV2 infection. Fortunately, the conditions of patients gradually return to normal which is beneficial from the antiviral treatment, hemodialysis, and various supportive therapies including anti-inflammation, liver and gastric mucosa protection. Conclusion: Unexpected manifestations of coinfection patients present herein may be associated with multiple factors including virus load, competition or antagonism among antigens, and the susceptibility of target cells to the various pathogens, even though the pathogenesis of HTNV and SARS-CoV2 remains to be elucidated. Given that these two viruses have posed a profound influence on the socioeconomic, healthcare system worldwide, and the threat of coinfection to public health, it is warranted for clinicians, public health authorities, and infectious disease researchers to have a high index of consideration for patients co-infected with HTNV and SARS-CoV2.

Lipid phosphorylation by a diacylglycerol kinase suppresses ABA biosynthesis to regulate plant stress responses.

Lipid phosphorylation by diacylglycerol kinase (DGK) that produces phosphatidic acid (PA) plays important roles in various biological processes, including stress responses, but the underlying mechanisms remain elusive. Here, we show that DGK5 and its lipid product PA suppress ABA biosynthesis by interacting with ABA-DEFICIENT 2 (ABA2), a key ABA biosynthesis enzyme, to negatively modulate plant response to abiotic stress tested in Arabidopsis thaliana. Loss of DGK5 function rendered plants less damaged, whereas overexpression (OE) of DGK5 enhanced plant damage to water and salt stress. The dgk5 mutant plants exhibited decreased total cellular and nuclear levels of PA with increased levels of diacylglycerol, whereas DGK5-OE plants displayed the opposite effect. Interestingly, we found that both DGK5 and PA bind to the ABA-synthesizing enzyme ABA2 and suppress its enzymatic activity. Consistently, the dgk5 mutant plants exhibited increased levels of ABA, while DGK5-OE plants showed reduced ABA levels. In addition, we showed that both DGK5 and ABA2 are detected in and outside the nuclei, and loss of DGK5 function decreased the nuclear association of ABA2. We found that both DGK5 activity and PA promote nuclear association of ABA2. Taken together, these results indicate that both DGK5 and PA interact with ABA2 to inhibit its enzymatic activity and promote its nuclear sequestration, thereby suppressing ABA production in response to abiotic stress. Our study reveals a sophisticated mechanism by which DGK5 and PA regulate plant stress responses.

Phosphatidic acid signaling and function in nuclei.

Membrane lipidomes are dynamic and their changes generate lipid mediators affecting various biological processes. Phosphatidic acid (PA) has emerged as an important class of lipid mediators involved in a wide range of cellular and physiological responses in plants, animals, and microbes. The regulatory functions of PA have been studied primarily outside the nuclei, but an increasing number of recent studies indicates that some of the PA effects result from its action in nuclei. PA levels in nuclei are dynamic in response to stimuli. Changes in nuclear PA levels can result from activities of enzymes associated with nuclei and/or from movements of PA generated extranuclearly. PA has also been found to interact with proteins involved in nuclear functions, such as transcription factors and proteins undergoing nuclear translocation in response to stimuli. The nuclear action of PA affects various aspects of plant growth, development, and response to stress and environmental changes.

Non-specific phospholipase C4 hydrolyzes phosphosphingolipids and phosphoglycerolipids and promotes rapeseed growth and yield.

Phosphorus is a major nutrient vital for plant growth and development, with a substantial amount of cellular phosphorus being used for the biosynthesis of membrane phospholipids. Here, we report that NON-SPECIFIC PHOSPHOLIPASE C4 (NPC4) in rapeseed (Brassica napus) releases phosphate from phospholipids to promote growth and seed yield, as plants with altered NPC4 levels showed significant changes in seed production under different phosphate conditions. Clustered regularly interspaced short palindromic repeat (CRISPR)/CRISPR-associated nuclease 9 (Cas9)-mediated knockout of BnaNPC4 led to elevated accumulation of phospholipids and decreased growth, whereas overexpression (OE) of BnaNPC4 resulted in lower phospholipid contents and increased plant growth and seed production. We demonstrate that BnaNPC4 hydrolyzes phosphosphingolipids and phosphoglycerolipids in vitro, and plants with altered BnaNPC4 function displayed changes in their sphingolipid and glycerolipid contents in roots, with a greater change in glycerolipids than sphingolipids in leaves, particularly under phosphate deficiency conditions. In addition, BnaNPC4-OE plants led to the upregulation of genes involved in lipid metabolism, phosphate release, and phosphate transport and an increase in free inorganic phosphate in leaves. These results indicate that BnaNPC4 hydrolyzes phosphosphingolipids and phosphoglycerolipids in rapeseed to enhance phosphate release from membrane phospholipids and promote growth and seed production.

The Sapria himalayana genome provides new insights into the lifestyle of endoparasitic plants.

BACKGROUND: Sapria himalayana (Rafflesiaceae) is an endoparasitic plant characterized by a greatly reduced vegetative body and giant flowers; however, the mechanisms underlying its special lifestyle and greatly altered plant form remain unknown. To illustrate the evolution and adaptation of S. himalayasna, we report its de novo assembled genome and key insights into the molecular basis of its floral development, flowering time, fatty acid biosynthesis, and defense responses. RESULTS: The genome of S. himalayana is ~ 1.92 Gb with 13,670 protein-coding genes, indicating remarkable gene loss (~ 54%), especially genes involved in photosynthesis, plant body, nutrients, and defense response. Genes specifying floral organ identity and controlling organ size were identified in S. himalayana and Rafflesia cantleyi, and showed analogous spatiotemporal expression patterns in both plant species. Although the plastid genome had been lost, plastids likely biosynthesize essential fatty acids and amino acids (aromatic amino acids and lysine). A set of credible and functional horizontal gene transfer (HGT) events (involving genes and mRNAs) were identified in the nuclear and mitochondrial genomes of S. himalayana, most of which were under purifying selection. Convergent HGTs in Cuscuta, Orobanchaceae, and S. himalayana were mainly expressed at the parasite-host interface. Together, these results suggest that HGTs act as a bridge between the parasite and host, assisting the parasite in acquiring nutrients from the host. CONCLUSIONS: Our results provide new insights into the flower development process and endoparasitic lifestyle of Rafflesiaceae plants. The amount of gene loss in S. himalayana is consistent with the degree of reduction in its body plan. HGT events are common among endoparasites and play an important role in their lifestyle adaptation.

Effects of Tea Plant Varieties with High- and Low-Nutrient Efficiency on Nutrients in Degraded Soil.

Tea plants are widely planted in tropical and subtropical regions globally, especially in southern China. The high leaching and strong soil acidity in these areas, in addition to human factors (e.g., tea picking and inappropriate fertilization methods) aggravate the lack of nutrients in tea garden soil. Therefore, improving degraded tea-growing soil is urgently required. Although the influence of biological factors (e.g., tea plant variety) on soil nutrients has been explored in the existing literature, there are few studies on the inhibition of soil nutrient degradation using different tea plant varieties. In this study, two tea plant varieties with different nutrient efficiencies (high-nutrient-efficiency variety: Longjing43 (LJ43); low-nutrient-efficiency variety: Liyou002 (LY002)) were studied. Under a one-side fertilization mode of two rows and two plants, the tea plant growth status, soil pH, and available nutrients in the soil profiles were analyzed, aiming to reveal the improvement of degraded soil using different tea varieties. The results showed that (1) differences in the phenotypic features of growth (such as dry tea yield, chlorophyll, leaf nitrogen (N), phosphorus (P), and potassium (K) content) between the fertilization belts in LJ43 (LJ43-near and LJ43-far) were lower than those in LY002. (2) RDA results showed that the crucial soil nutrient factors which determine the features of tea plants included available P, slowly available K, and available K. Moreover, acidification was more serious near the fertilization belt. The pH of the soil near LJ43 was higher than that near LY002, indicating an improvement in soil acidification. (3) Soil nutrient heterogeneity between fertilization belts in LJ43 (LJ43-near and LJ43-far) was lower than in LY002. In conclusion, the long-term one-side fertilization mode of two rows and two plants usually causes spatial heterogeneities in soil nutrients and aggravates soil acidification. However, LJ43 can reduce the nutrient heterogeneities and soil acidification, which is probably due to the preferential development of secondary roots. These results are helpful in understanding the influence of tea plant variety on improving soil nutrients and provide a relevant scientific reference for breeding high-quality tea varieties, improving the state of degraded soil and maintaining soil health.

Phosphate deficiency modifies lipid composition and seed oil production in camelina.

Camelina (Camelina sativa) is an emerging industrial oilseed crop because of its potential for double cropping, fallow year production, growth on marginal lands, and multiple uses of seed oils and meals. To realize the potential for sustainable production of camelina, a better understanding of how camelina seed oil production and composition respond to low input environments is desired. Phosphorus (P) is one of the least available essential macronutrients to plants with finite worldwide supply. This study investigated seed oil production and lipid composition of camelina in field settings and under greenhouse conditions in response to P deficiency. Lipidomic profiling reveals that P deficiency in field settings triggered extensive leaf lipid remodeling that decreased the ratio of phospholipids to non-P-containing galactolipids from 30% to 5% under P sufficient to deficient conditions. P deficiency increased seed oil content per seed weight by approximately 25% and 20% in field and greenhouse settings, respectively. In addition, P deficiency altered seed fatty acid composition, with increases in monounsaturated 18:1 and 20:1 and decreases in polyunsaturated 18:3. Total seed production was decreased by 10- to 15-fold under P deficiency and the decrease resulted from reduced seed numbers without affecting seed weight. The results from field and greenhouse conditions indicate that P deficiency increases seed oil content, alters fatty acid composition, and decreases greatly seed production, suggesting that achieving a high yield and quality of camelina seed oil is positively linked to P status of soil.

Volumetric memory network for interactive medical image segmentation.

Despite recent progress of automatic medical image segmentation techniques, fully automatic results usually fail to meet clinically acceptable accuracy, thus typically require further refinement. To this end, we propose a novel Volumetric Memory Network, dubbed as VMN, to enable segmentation of 3D medical images in an interactive manner. Provided by user hints on an arbitrary slice, a 2D interaction network is firstly employed to produce an initial 2D segmentation for the chosen slice. Then, the VMN propagates the initial segmentation mask bidirectionally to all slices of the entire volume. Subsequent refinement based on additional user guidance on other slices can be incorporated in the same manner. To facilitate smooth human-in-the-loop segmentation, a quality assessment module is introduced to suggest the next slice for interaction based on the segmentation quality of each slice produced in the previous round. Our VMN demonstrates two distinctive features: First, the memory-augmented network design offers our model the ability to quickly encode past segmentation information, which will be retrieved later for the segmentation of other slices; Second, the quality assessment module enables the model to directly estimate the quality of each segmentation prediction, which allows for an active learning paradigm where users preferentially label the lowest-quality slice for multi-round refinement. The proposed network leads to a robust interactive segmentation engine, which can generalize well to various types of user annotations (e.g., scribble, bounding box, extreme clicking). Extensive experiments have been conducted on three public medical image segmentation datasets (i.e., MSD, KiTS19, CVC-ClinicDB), and the results clearly confirm the superiority of our approach in comparison with state-of-the-art segmentation models. The code is made publicly available at https://github.com/0liliulei/Mem3D.

Modeling the impact of nickel recycling from batteries on nickel demand during vehicle electrification in China from 2010 to 2050.

China is promoting the production and use of electric vehicles (EVs) to achieve carbon neutrality. However, the shift will drive higher demand and tighter supply of nickel in China. We develop a stock-driven bottom-up dynamic substance flow analysis (SFA) model to simulate the demand trends of various EVs under 3 scenarios, the flow of nickel under 9 scenarios and the amount of recoverable nickel under 27 scenarios in China's EV industry from 2010 to 2050. The results indicate that China's current production capacity and primary reserves of nickel cannot meet the growing nickel demand, especially under the High EVs-LNCT scenarios, and closed-loop nickel recovery from EV batteries can effectively alleviate the demand-supply contradiction. In different scenarios, the annual recycling nickel could cover between 67.7 % and 96.6 % of the demand for EV batteries in 2050, and between 37.9 % and 58.1 % in terms of the cumulative quantity by 2050. When the low nickel battery technology is adopted and the recovery efficiency is rapidly improved, the recovered nickel would meet the demand for EV batteries to the highest degree. Therefore, sufficient attention should be paid to low-nickel battery technology and efficient recycling of spent EV batteries, which is of great significance to ensure the development of EV industry and the availability of nickel in China.

The extremely reduced, diverged and reconfigured plastomes of the largest mycoheterotrophic orchid lineage.

BACKGROUND: Plastomes of heterotrophic plants have been greatly altered in structure and gene content, owing to the relaxation of selection on photosynthesis-related genes. The orchid tribe Gastrodieae is the largest and probably the oldest mycoheterotrophic clade of the extant family Orchidaceae. To characterize plastome evolution across members of this key important mycoheterotrophic lineage, we sequenced and analyzed the plastomes of eleven Gastrodieae members, including representative species of two genera, as well as members of the sister group Nervilieae. RESULTS: The plastomes of Gastrodieae members contain 20 protein-coding, four rRNA and five tRNA genes. Evolutionary analysis indicated that all rrn genes were transferred laterally and together, forming an rrn block in the plastomes of Gastrodieae. The plastome GC content of Gastrodia species ranged from 23.10% (G. flexistyla) to 25.79% (G. javanica). The plastome of Didymoplexis pallens contains two copies each of ycf1 and ycf2. The synonymous and nonsynonymous substitution rates were very high in the plastomes of Gastrodieae among mycoheterotrophic species in Orchidaceae and varied between genes. CONCLUSIONS: The plastomes of Gastrodieae are greatly reduced and characterized by low GC content, rrn block formation, lineage-specific reconfiguration and gene content, which might be positively selected. Overall, the plastomes of Gastrodieae not only serve as an excellent model for illustrating the evolution of plastomes but also provide new insights into plastome evolution in parasitic plants.

Root Foraging Strategy Improves the Adaptability of Tea Plants (Camellia sinensis L.) to Soil Potassium Heterogeneity.

Root foraging enables plants to obtain more soil nutrients in a constantly changing nutrient environment. Little is known about the adaptation mechanism of adventitious roots of plants dominated by asexual reproduction (such as tea plants) to soil potassium heterogeneity. We investigated root foraging strategies for K by two tea plants (low-K tolerant genotype "1511" and low-K intolerant genotype "1601") using a multi-layer split-root system. Root exudates, root architecture and transcriptional responses to K heterogeneity were analyzed by HPLC, WinRHIZO and RNA-seq. With the higher leaf K concentrations and K biological utilization indexes, "1511" acclimated to K heterogeneity better than "1601". For "1511", maximum total root length and fine root length proportion appeared on the K-enriched side; the solubilization of soil K reached the maximum on the low-K side, which was consistent with the amount of organic acids released through root exudation. The cellulose decomposition genes that were abundant on the K-enriched side may have promoted root proliferation for "1511". This did not happen in "1601". The low-K tolerant tea genotype "1511" was better at acclimating to K heterogeneity, which was due to a smart root foraging strategy: more roots (especially fine roots) were developed in the K-enriched side; more organic acids were secreted in the low-K side to activate soil K and the root proliferation in the K-enriched side might be due to cellulose decomposition. The present research provides a practical basis for a better understanding of the adaptation strategies of clonal woody plants to soil nutrient availability.

The Epidemiological, Clinical Features and Outcomes of Imported Chinese COVID-19 Patients Following Inactivated Vaccines Injection.

Background: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccination had been demonstrated as an effective way to reduce the risk of coronavirus disease 2019 (COVID-19), and only a few vaccines suffered from SARS-CoV-2 infection. However, limited data concerning the clinical features of these vaccines infected with SARS-CoV-2 can be identified. Methods: We retrospectively collected and analyzed epidemiological and clinical characteristics data of the imported COVID-19 cases who received Chinese inactivated vaccines abroad. Data were extracted from electronic medical records from a designated hospital in the Shaanxi Province of China between March 22 and May 17, 2021. Results: Totally, 46 confirmed SARS-CoV-2 infection patients were enrolled. The mean age was 40.5 years (range 20-61), 41 (89.1%) are male. Eighteen (39.1%) patients were from Pakistan. Fourteen (30.4%) patients had at least one comorbidity. Forty (87.0%) and 6 cases were fully vaccinated and partly vaccinated. The time interval between vaccination and infection was 88 days (IQR, 33-123), 31 (67.4%) and 15 (32.6%) were asymptomatic and symptomatic cases, respectively. Fever (3/46, 6.5%) was the most common symptom; however, none had a body temperature higher than 38.0°C, and no severe case was observed. Notably, the rate of SARS-CoV-2 shedding discontinuation at 7 days after hospitalization in asymptomatic cases was higher than symptomatic one (93.5% vs 40%, P < 0.0001). Conclusion: Individuals who received Chinese inactivated vaccines abroad remain to have the probability of being infected with SARS-CoV-2, but all the vaccines infected with SARS-CoV-2 were asymptomatic or had mild symptoms with favorable clinical outcomes.

The Gastrodia menghaiensis (Orchidaceae) genome provides new insights of orchid mycorrhizal interactions.

BACKGROUND: To illustrate the molecular mechanism of mycoheterotrophic interactions between orchids and fungi, we assembled chromosome-level reference genome of Gastrodia menghaiensis (Orchidaceae) and analyzed the genomes of two species of Gastrodia. RESULTS: Our analyses indicated that the genomes of Gastrodia are globally diminished in comparison to autotrophic orchids, even compared to Cuscuta (a plant parasite). Genes involved in arbuscular mycorrhizae colonization were found in genomes of Gastrodia, and many of the genes involved biological interaction between Gatrodia and symbiotic microbionts are more numerous than in photosynthetic orchids. The highly expressed genes for fatty acid and ammonium root transporters suggest that fungi receive material from orchids, although most raw materials flow from the fungi. Many nuclear genes (e.g. biosynthesis of aromatic amino acid L-tryptophan) supporting plastid functions are expanded compared to photosynthetic orchids, an indication of the importance of plastids even in totally mycoheterotrophic species. CONCLUSION: Gastrodia menghaiensis has the smallest proteome thus far among angiosperms. Many of the genes involved biological interaction between Gatrodia and symbiotic microbionts are more numerous than in photosynthetic orchids.

Responses of tea plants (Camellia sinensis) with different low-nitrogen tolerances during recovery from nitrogen deficiency.

BACKGROUND: Tea plants have high nitrogen (N) consumptions, whereas molecular and physiological responses of tea plants to N recovery are still unclear. RESULTS: By using non-invasive micro-test technology (NMT), 15 N tracer technique, ultra-performance liquid chromatography (UPLC), and transcriptome sequencing technology, we investigated the N recovery-induced changes in N absorptions, N tissue distributions, contents of free amino acids (FAAs), and global transcription of the low-N tolerant and intolerant tea genotypes [i.e. Wuniuzao (W) and Longjing43 (L)]. The results showed that the phenotype of Wuniuzao was better than that of Longjing43 under low-N condition. The N absorption and utilization of Wuniuzao were superior to Longjing43 under N recovery. The γ-aminobutyric acid (GABA) ratio (N recovery/N deficiency) in the root of Wuniuzao was significantly higher than that of Longjing43, while the glutamic acid ratio in the root of Wuniuzao was significantly lower than that of Longjing43. This findings suggested that Wuniuzao tended to enhance the GABA synthesis, while Longjing43 tended to inhibit the GABA synthesis under N recovery. The key genes in response to N recovery in Wuniuzao included N transport (AMT and NRT), N transformation (NR, NirA, and GAD), and amino acid transport (GAT) genes. In addition, some ribosome and flavonoid biosynthesis genes might help to maintain proteome homeostasis. CONCLUSION: The N absorption and transport, and the conversion abilities of key amino acids (Glu and GABA) might improve the adaptability of tea plants to N recovery, which provided a basis for the breeding of N efficient tea varieties. © 2021 Society of Chemical Industry.

Group-Wise Learning for Weakly Supervised Semantic Segmentation.

Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due to the data-hungry nature of deep learning. This is exacerbated in some structured prediction tasks, such as semantic segmentation, which require pixel-level annotations. This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. To achieve this, we propose, for the first time, a novel group-wise learning framework for WSSS. The framework explicitly encodes semantic dependencies in a group of images to discover rich semantic context for estimating more reliable pseudo ground-truths, which are subsequently employed to train more effective segmentation models. In particular, we solve the group-wise learning within a graph neural network (GNN), wherein input images are represented as graph nodes, and the underlying relations between a pair of images are characterized by graph edges. We then formulate semantic mining as an iterative reasoning process which propagates the common semantics shared by a group of images to enrich node representations. Moreover, in order to prevent the model from paying excessive attention to common semantics, we further propose a graph dropout layer to encourage the graph model to capture more accurate and complete object responses. With the above efforts, our model lays the foundation for more sophisticated and flexible group-wise semantic mining. We conduct comprehensive experiments on the popular PASCAL VOC 2012 and COCO benchmarks, and our model yields state-of-the-art performance. In addition, our model shows promising performance in weakly supervised object localization (WSOL) on the CUB-200-2011 dataset, demonstrating strong generalizability. Our code is available at: https://github.com/Lixy1997/Group-WSSS.

pH-Responsive Multifunctional Theranostic Rapamycin-Loaded Nanoparticles for Imaging and Treatment of Acute Ischemic Stroke.

Stroke is the second leading cause of death globally and the most common cause of severe disability. Several barriers need to be addressed more effectively to treat stroke, including efficient delivery of therapeutic agents, rapid release at the infarct site, precise imaging of the infarct site, and drug distribution monitoring. The present study aimed to develop a bio-responsive theranostic nanoplatform with signal-amplifying capability to deliver rapamycin (RAPA) to ischemic brain tissues and visually monitor drug distribution. A pH-sensitive theranostic RAPA-loaded nanoparticle system was designed since ischemic tissues have a low-pH microenvironment compared with normal tissues. The nanoparticles demonstrated good stability and biocompatibility and could efficiently load rapamycin, followed by its rapid release in acidic environments, thereby improving therapeutic accuracy. The nano-drug-delivery system also exhibited acid-enhanced magnetic resonance imaging (MRI) and near-infrared fluorescence (NIRF) imaging signal properties, enabling accurate multimodal imaging with minimal background noise, thus improving drug tracing and diagnostic accuracy. Finally, in vivo experiments confirmed that the nanoparticles preferentially aggregated in the ischemic hemisphere and exerted a neuroprotective effect in rats with transient middle cerebral artery occlusion (tMCAO). These pH-sensitive multifunctional theranostic nanoparticles could serve as a potential nanoplatform for drug tracing as well as the treatment and even diagnosis of acute ischemic stroke. Moreover, they could be a universal solution to achieve accurate in vivo imaging and treatment of other diseases.

Taxonomy notes on Vandeae (Orchidaceae) from China: Five new species and two new records.

Five new species (Gastrochilus yei, Gastrochilus minimus, Luisia simaoensis, Taeniophyllum xizangense, Tuberolabium subulatum) and two newly recorded species (Cleisostoma tricornutum, Luisia inconspicua) of Vandeae (Orchidaceae) from China are described and illustrated. Gastrochilus yei is similar to G. affinis and G. nepalensis, but differs from them by having an epichile not lobed, the apex of the hypochile not bilobed, and a tine on the apex of the leaf. Gastrochilus minimus is similar to G. acinacifolius, but can be distinguished from the latter by having a flabellate epichile that is densely hirsute on the adaxial surface and an inconspicuous central cushion; in addition, the hypochile of G. minimus has a keel that extends to the apex of the epichile. Taeniophyllum xizangense is similar to T. stella and T. radiatum, but it is distinguished from them by having much bigger flowers, inflorescences densely covered with short-bristly hairs, papillae on the external surface of sepals, and bigger triangular-ovate viscidium. Luisia simaoensis is similar to L. magniflora and L. ramosii, but can be easily distinguished from them by having lateral sepals longer than dorsal sepals and petals, lip with irregular and waved margins, and lip with bilobed apex. Luisia inconspicua is moved from Gastrochilus to Luisia based on phylogenetic analyses of plastid matK sequence data. Tuberolabium subulatum is similar to T. carnosum, but it can be easily distinguished from the latter by having an inflorescence much shorter than the leaves, yellow sepals and petals, and many small papillae outside the lip lobes.

New taxa of tribe Gastrodieae (Epidendroideae, Orchidaceae) from Yunnan, China and its conservation implication.

Gastrodia longistyla, a new species of Orchidaceae from Yunnan Province, China, is described and illustrated. It is morphologically similar to Gastrodia peichatieniana, but can be easily distinguished from the latter by having a rhombic epichile, long column (6.0-7.5 mm long), and a needle-shaped appendage (1.8-3.2 mm in length) at the base of the stigma. Identification key and colour photographs are provided. A preliminary risk-of-extinction assessment, according to the IUCN Red List Categories and Criteria, is given for the new species. The plastome of G. longistyla is 30464 bp in length with GC content approximately 24.8%, and the plastome does not contain some housekeeping genes, such as matK, rpl16, or all photosynthesis genes. In addition, the G. longistyla plastome lacks an IR region. This indicates that the plastome is in the last stage of degradation.