Temporal fact extraction of fruit cultivation technologies based on deep learning.

There are great differences in fruit planting techniques due to different regional environments. Farmers can't use the same standard in growing fruit. Most of the information about fruit planting comes from the Internet, which is characterized by complexity and heterogeneous multi-source. How to deal with such information to form the convenient facts becomes an urgent problem. Information extraction could automatically extract fruit cultivation facts from unstructured text. Temporal information is especially crucial for fruit cultivation. Extracting temporal facts from the corpus of cultivation technologies for fruit is also vital to several downstream applications in fruit cultivation. However, the framework of ordinary triplets focuses on handling static facts and ignores the temporal information. Therefore, we propose Basic Fact Extraction and Multi-layer CRFs (BFE-MCRFs), an end-to-end neural network model for the joint extraction of temporal facts. BFE-MCRFs describes temporal knowledge using an improved schema that adds the time dimension. Firstly, the basic facts are extracted from the primary model. Then, multiple temporal relations are added between basic facts and time expressions. Finally, the multi-layer Conditional Random Field are used to detect the objects corresponding to the basic facts under the predefined temporal relationships. Experiments conducted on public and self-constructed datasets show that BFE-MCRFs achieves the best current performance and outperforms the baseline models by a significant margin.

A novel knowledge extraction method based on deep learning in fruit domain.

Knowledge extraction aims to identify entities and extract relations between them from unstructured text, which are in the form of triplets. Analysis of the fruit nutrition domain corpus revealed many overlapping triplets, that is, multiple correspondences between a subject and multiple objects or the same subject and object. The current relevant methods mainly target the extraction of ordinary triplets, which cannot accurately identify overlapping triplets. To solve this problem, a deep learning based model for overlapping triplet extraction is proposed in this study. The relation is modeled as a function that maps a subject to an object. The hybrid information of the subject is entered into the relation-object extraction model to detect the object and relation. The experimental results show this model outperforms existing extraction models and achieves state-of-the-art performance on the manually labeled fruit nutrition domain dataset. In terms of application value, the proposed work can obtain a high-quality and structured fruit nutrition knowledge base, which provides application fundamentals for downstream applications of nutrition matching.

Enhanced remediation of PAHs-contaminated site soil by bioaugmentation with graphene oxide immobilized bacterial pellets.

Bioaugmentation is considered as a promising technology for cleanup of polycyclic aromatic hydrocarbons (PAHs) from contaminated site soil, however, available high-efficiency microbial agents remain very limited. Herein, we explored graphene oxide (GO)-immobilized bacterial pellets (JGOLB) by embedding high-efficiency degrading bacteria Paracoccus aminovorans HPD-2 in alginate-GO-Luria-Bertani medium (LB) composites. Microcosm culture experiments were performed with contaminated site soil to assess the effect of JGOLB on the removal of PAHs. The results showed that JGOLB exhibited greatly improved mechanical strength, larger specific surface area and more enriched mesopores, compared with traditional immobilized bacterial pellets. They significantly increased the removal rate of PAHs by 18.51% compared with traditional bacterial pellets, reaching the removal rate at 62.86% over 35 days of incubation. Moreover, the increase mainly focused on high-molecular-weight PAHs. JGOLB not only greatly increased the abundance of embedded degrading bacteria in soil, but also significantly enhanced the enrichment of potential indigenous degrading bacteria (Pseudarthrobacter and Arthrobacter), the functional genes involved in PAHs degradation and a number of ATP transport genes in the soil. Overall, such nanocomposite bacterial pellets provide a novel microbial immobilization option for remediating organic pollutants in harsh soil environment.

Variations of quantitative perfusion measurement on dynamic contrast enhanced CT for colorectal cancer: implication of standardized image protocol.

Tumor angiogenesis is considered an important prognostic factor. With an increasing emphasis on imaging evaluation of the tumor microenvironment, dynamic contrast enhanced-computed tomography (DCE-CT) has evolved as an important functional technique in this setting. Yet many questions remain as to how and when these functional measurements should be performed for each agent and tumor type, and what quantitative models should be used in the fitting process. In this study, we evaluated the variations of perfusion measurement on DCE-CT for rectal cancer patients from (1) different tracer kinetic models, (2) different scan acquisition lengths, and (3) different scan intervals. A total of seven commonly used models were studied: the adiabatic approximation to the tissue homogeneity (AATH) model, adiabatic approximation to the homogeneity tissue with fixed transit time (AATHFT) model, the Tofts model (TM), the extended Tofts model (ETM), Patlak model, Logan model, and the model-free deconvolution method. Akaike's information criterion was used to identify the best fitting model. The interchangeability of different models was further evaluated using Bland-Altman analysis. All models gave comparable blood volume (BV) measurements except the Patlak method. While for the volume transfer constant (Ktrans) estimation, AATHFT, AATH, and ETM generated reasonable agreement among each other but not for the other models. Regarding the blood flow (BF) measurement, no two models were interchangeable. In addition, the perfusion parameters were compared with four acquisition times (45, 65, 85, and 105 s) and four temporal intervals (1, 2, 3, and 4 s). No significant difference was observed in the volume transfer constant (Ktrans), BV, and BF measurements when comparing data acquired over 65 s with data acquired over 105 s using any of the DCE models in this study. Yet increasing the temporal interval led to a significant overestimation of BF in the deconvolution method. In conclusion, the perfusion measurement is indeed model dependent and the image acquisition/processing technique is dependent. The radiation dose of DCE-CT was an average of 1.5-2 times an abdomen/pelvic CT, which is not insubstantial. To take the DCE-CT forward as a biomarker in oncology, prospective studies should be carefully designed with the optimal image acquisition and analysis technique.

Iterative CT shading correction with no prior information.

Shading artifacts in CT images are caused by scatter contamination, beam-hardening effect and other non-ideal imaging conditions. The purpose of this study is to propose a novel and general correction framework to eliminate low-frequency shading artifacts in CT images (e.g. cone-beam CT, low-kVp CT) without relying on prior information. The method is based on the general knowledge of the relatively uniform CT number distribution in one tissue component. The CT image is first segmented to construct a template image where each structure is filled with the same CT number of a specific tissue type. Then, by subtracting the ideal template from the CT image, the residual image from various error sources are generated. Since forward projection is an integration process, non-continuous shading artifacts in the image become continuous signals in a line integral. Thus, the residual image is forward projected and its line integral is low-pass filtered in order to estimate the error that causes shading artifacts. A compensation map is reconstructed from the filtered line integral error using a standard FDK algorithm and added back to the original image for shading correction. As the segmented image does not accurately depict a shaded CT image, the proposed scheme is iterated until the variation of the residual image is minimized. The proposed method is evaluated using cone-beam CT images of a Catphan©600 phantom and a pelvis patient, and low-kVp CT angiography images for carotid artery assessment. Compared with the CT image without correction, the proposed method reduces the overall CT number error from over 200 HU to be less than 30 HU and increases the spatial uniformity by a factor of 1.5. Low-contrast object is faithfully retained after the proposed correction. An effective iterative algorithm for shading correction in CT imaging is proposed that is only assisted by general anatomical information without relying on prior knowledge. The proposed method is thus practical and attractive as a general solution to CT shading correction.