•A deep learning approach to quantify discriminatory leaf is proposed.•Shape is not a dominant feature for leaf but rather the different orders of venation.•Deep learning reveals transformation of ...leaf features from general to specific types.•Findings archived fit with the hierarchical botanical definitions of leaf characters.•Features learned using deep learning can improve plant recognition performance.
Plant identification systems developed by computer vision researchers have helped botanists to recognize and identify unknown plant species more rapidly. Hitherto, numerous studies have focused on procedures or algorithms that maximize the use of leaf databases for plant predictive modeling, but this results in leaf features which are liable to change with different leaf data and feature extraction techniques. In this paper, we learn useful leaf features directly from the raw representations of input data using Convolutional Neural Networks (CNN), and gain intuition of the chosen features based on a Deconvolutional Network (DN) approach. We report somewhat unexpected results: (1) different orders of venation are the best representative features compared to those of outline shape, and (2) we observe multi-level representation in leaf data, demonstrating the hierarchical transformation of features from lower-level to higher-level abstraction, corresponding to species classes. We show that these findings fit with the hierarchical botanical definitions of leaf characters. Through these findings, we gained insights into the design of new hybrid feature extraction models which are able to further improve the discriminative power of plant classification systems. The source code and models are available at: https://github.com/cs-chan/Deep-Plant.
Patients infected with SARS-CoV-2 may deteriorate rapidly and therefore continuous monitoring is necessary. We conducted an observational study involving patients with mild COVID-19 to explore the ...potentials of wearable biosensors and machine learning-based analysis of physiology parameters to detect clinical deterioration. Thirty-four patients (median age: 32 years; male: 52.9%) with mild COVID-19 from Queen Mary Hospital were recruited. The mean National Early Warning Score 2 (NEWS2) were 0.59 ± 0.7. 1231 manual measurement of physiology parameters were performed during hospital stay (median 15 days). Physiology parameters obtained from wearable biosensors correlated well with manual measurement including pulse rate (r = 0.96, p < 0.0001) and oxygen saturation (r = 0.87, p < 0.0001). A machine learning-derived index reflecting overall health status, Biovitals Index (BI), was generated by autonomous analysis of physiology parameters, symptoms, and other medical data. Daily BI was linearly associated with respiratory tract viral load (p < 0.0001) and NEWS2 (r = 0.75, p < 0.001). BI was superior to NEWS2 in predicting clinical worsening events (sensitivity 94.1% and specificity 88.9%) and prolonged hospitalization (sensitivity 66.7% and specificity 72.7%). Wearable biosensors coupled with machine learning-derived health index allowed automated detection of clinical deterioration.
Classification of plants based on a multi-organ approach is very challenging. Although additional data provide more information that might help to disambiguate between species, the variability in ...shape and appearance in plant organs also raises the degree of complexity of the problem. Despite promising solutions built using deep learning enable representative features to be learned for plant images, the existing approaches focus mainly on generic features for species classification, disregarding the features representing plant organs. In fact, plants are complex living organisms sustained by a number of organ systems. In our approach, we introduce a hybrid generic-organ convolutional neural network (HGO-CNN), which takes into account both organ and generic information, combining them using a new feature fusion scheme for species classification. Next, instead of using a CNN-based method to operate on one image with a single organ, we extend our approach. We propose a new framework for plant structural learning using the recurrent neural network-based method. This novel approach supports classification based on a varying number of plant views, capturing one or more organs of a plant, by optimizing the contextual dependencies between them. We also present the qualitative results of our proposed models based on feature visualization techniques and show that the outcomes of visualizations depict our hypothesis and expectation. Finally, we show that by leveraging and combining the aforementioned techniques, our best network outperforms the state of the art on the PlantClef2015 benchmark. The source code and models are available at https://github.com/cs-chan/Deep-Plant.
Mammalian genomes are viewed as functional organizations that orchestrate spatial and temporal gene regulation. CTCF, the most characterized insulator-binding protein, has been implicated as a key ...genome organizer. However, little is known about CTCF-associated higher-order chromatin structures at a global scale. Here we applied chromatin interaction analysis by paired-end tag (ChIA-PET) sequencing to elucidate the CTCF-chromatin interactome in pluripotent cells. From this analysis, we identified 1,480 cis- and 336 trans-interacting loci with high reproducibility and precision. Associating these chromatin interaction loci with their underlying epigenetic states, promoter activities, enhancer binding and nuclear lamina occupancy, we uncovered five distinct chromatin domains that suggest potential new models of CTCF function in chromatin organization and transcriptional control. Specifically, CTCF interactions demarcate chromatin-nuclear membrane attachments and influence proper gene expression through extensive cross-talk between promoters and regulatory elements. This highly complex nuclear organization offers insights toward the unifying principles that govern genome plasticity and function.
This paper studies convolutional neural networks (CNN) to learn unsupervised feature representations for 44 different plant species, collected at the Royal Botanic Gardens, Kew, England. To gain ...intuition on the chosen features from the CNN model (opposed to a `black box' solution), a visualisation technique based on the deconvolutional networks (DN) is utilized. It is found that venations of different order have been chosen to uniquely represent each of the plant species. Experimental results using these CNN features with different classifiers show consistency and superiority compared to the state-of-the art solutions which rely on hand-crafted features.
Apical-basal cell polarity must be tightly controlled for epithelial cyst and tubule formation, and these are important functional units in various epithelial organs. Polarization is achieved through ...the coordination of several molecules that divide cells into an apical domain and a basolateral domain, which are separated from tight and adherens junctions. Cdc42 regulates cytoskeletal organization and the tight junction protein ZO-1 at the apical margin of epithelial cell junctions. MST kinases control organ size through the regulation of cell proliferation and cell polarity. For example, MST1 relays the Rap1 signal to induce cell polarity and adhesion of lymphocytes. Our previous study showed that MST3 was involved in E-cadherin regulation and migration in MCF7 cells. In vivo, MST3 knockout mice exhibited higher ENaC expression at the apical site of renal tubules, resulting in hypertension. However, it was not clear whether MST3 was involved in cell polarity. Here, control MDCK cells, HA-MST3 and HA-MST3 kinase-dead (HA-MST3-KD) overexpressing MDCK cells were cultured in collagen or Matrigel. We found that the cysts of HA-MST3 cells were fewer and smaller than those of control MDCK cells; ZO-1 was delayed to the apical site of cysts and in cell-cell contact in the Ca2+ switch assay. However, HA-MST3-KD cells exhibited multilumen cysts. Intensive F-actin stress fibers were observed in HA-MST3 cells with higher Cdc42 activity; in contrast, HA-MST3-KD cells had lower Cdc42 activity and weaker F-actin staining. In this study, we identified a new MST3 function in the establishment of cell polarity through Cdc42 regulation.
Many of today's publish/subscribe (pub/sub) systems have been designed to cope with a large
volume
of subscriptions and high event arrival rate (
velocity
). However, in many novel applications (such ...as e-commerce), there is an increasing
variety
of items, each with different attributes. This leads to a very high-dimensional and sparse database that existing pub/sub systems can no longer support effectively. In this paper, we propose an efficient in-memory index that is scalable to the volume and update of subscriptions, the arrival rate of events and the variety of subscribable attributes. The index is also extensible to support complex scenarios such as prefix/suffix filtering and regular expression matching. We conduct extensive experiments on synthetic datasets and two real datasets (AOL query log and Ebay products). The results demonstrate the superiority of our index over state-of-the-art methods: our index incurs orders of magnitude less index construction time, consumes a small amount of memory and performs event matching efficiently.
Recent studies found white coats to be reservoirs for bacteria and medical students did not conform to proper hygiene measures when using these white coats. We investigated the knowledge, attitude, ...and practice (KAP) of medical students toward white coat use in clinical settings (LAUNDERKAP).
A validated, online-based survey was disseminated to 670 students from four Malaysian medical schools via random sampling. Scores were classified into good, moderate, or poor knowledge and practice, and positive, neutral, or negative attitude. Mann-Whitney U and Kruskal-Wallis tests were used to analyze the relationship between demographic variables and knowledge, attitude, and practice scores.
A total of 492/670 students responded (response rate: 73.4%). A majority showed negative attitudes (n = 246, 50%), poor knowledge (n = 294, 59.8%), and moderate practice (n = 239, 48.6%). Senior and clinical year students had more negative attitudes. Male students had higher knowledge, while students from private medical schools and preclinical years had better practice. There was a significant relationship between attitude and practice (r = 0.224, P < .01), as well as knowledge and practice (r = 0.111, P < .05).
The results demonstrate the need for more education to improve medical students' infection control practices. Our results can also guide decision-making among administrators on the role of white coats as part of medical student attire.
Background: The aim of current study was to (1) construct and validate a novel hepatocellular carcinoma (HCC)-specific inflammatory index; (2) compare the performances of the Integrated Liver ...Inflammatory Score (ILIS) to existing 4 inflammatory indices in HCC; (3) explore the association between the inflammatory indices and systemic/intratumoral inflammatory markers. Methods: Two cohorts from Hong Kong (HK; n = 1,315) and Newcastle (n = 574) were studied. A novel index was constructed from the HK training set (n = 627). The index was constructed from the training set by combing independent prognostic circulating parameters, followed by validating in the validation set of HK cohort (n = 688) and the Newcastle cohort. Its prognostic performance was compared to 4 inflammatory indices, namely, the neutrophil to lymphocyte ratio, platelet-to-lymphocyte ratio, prognostic nutrition index, and systemic immune-inflammation index, were compared in the HK cohort. Circulating cytokines and intratumoral gene expression were analyzed in a subset of patients with available samples and correlated with the inflammatory indices. Results: In the training set of the HK cohort, the ILIS, was generated: –0.057 × albumin (g/L) + 0.978 × log (Bilirubin, µmol/L) + 1.341 × log (alkaline phosphatase, IU/L) + 0.086 × Neutrophil (10 9 /L) + 0.301 × log (alpha-fetoprotein, µg/L). With cutoff of 2.60 and 3.87, the ILIS could categorize patients into 3 risk groups in the both validation cohorts. ILIS outperforms other inflammatory indices and remains an independent prognosticator for overall survival after adjustment with Barcelona Clinic Liver Cancer (hazard ratio 31.90, p < 0.001). The ILIS had the best prognostic performances as compared to other inflammatory indices. In exploratory analyses, the ILIS correlated with circulating inflammatory cytokines (e.g., IL-8) but not with any intratumoral inflammatory gene expression. Conclusions: ILIS is an HCC-specific prognostic index built on 5 readily available blood parameters. Its versatility is validated both Eastern and Western population of HCC. The score is correlated with levels of circulating cytokines.
Background
Timely and relevant information helps parents to cope when a child is diagnosed with cancer. However, obtaining and understanding information is not a straightforward process for parents.
...Objectives
This article aims to explain paediatric cancer parents' information behaviour related to the care of their child.
Methods
Qualitative in‐depth interviews were conducted with fourteen Malaysian paediatric cancer parents and eight healthcare professionals who worked with paediatric cancer patients. Reflexivity and inductive approaches were used to interpret the data to identify meaningful themes and subthemes.
Results
Three themes about how paediatric cancer parents interact with information emerged: Acquiring information, internalising information, and using information. Information may be actively sought or passively acquired. Cognitive and affective aspects influence how information is internalised into meaningful knowledge. Knowledge then leads to further action including further information gathering.
Conclusion
Paediatric cancer parents need health literacy support to meet their information needs. They require guidance in identifying and appraising suitable information resources. Development of suitable supporting materials is needed to facilitate parents' ability to comprehend information related to their child's cancer. Understanding parents' information behaviour could assist healthcare professionals in providing information support in the context of paediatric cancer.