Recognition Of Structures Research Articles

MolNexTR: a generalized deep learning model for molecular image recognition

In the field of chemical structure recognition, the task of converting molecular images into machine-readable data formats such as SMILES string stands as a significant challenge, primarily due to the varied drawing styles and conventions prevalent in chemical literature. To bridge this gap, we proposed MolNexTR, a novel image-to-graph deep learning model that collaborates to fuse the strengths of ConvNext, a powerful Convolutional Neural Network variant, and Vision-TRansformer. This integration facilitates a more detailed extraction of both local and global features from molecular images. MolNexTR can predict atoms and bonds simultaneously and understand their layout rules. It also excels at flexibly integrating symbolic chemistry principles to discern chirality and decipher abbreviated structures. We further incorporate a series of advanced algorithms, including an improved data augmentation module, an image contamination module, and a post-processing module for getting the final SMILES output. These modules cooperate to enhance the model’s robustness to diverse styles of molecular images found in real literature. In our test sets, MolNexTR has demonstrated superior performance, achieving an accuracy rate of 81–97%, marking a significant advancement in the domain of molecular structure recognition.Scientific contributionMolNexTR is a novel image-to-graph model that incorporates a unique dual-stream encoder to extract complex molecular image features, and combines chemical rules to predict atoms and bonds while understanding atom and bond layout rules. In addition, it employs a series of novel augmentation algorithms to significantly enhance the robustness and performance of the model.

Illustration as a Teaching-Learning Tool in Histology Practical in Undergraduate Medical Education of Bangladesh: Teacher & Student Perspective

Objectives: This study was aimed to find out the perception of students and teachers regarding illustration as a teaching-learning tool in pistology practical class in undergraduate medical education of Bangladesh. Methods: The present study was a cross sectional descriptive one involving quantitative and qualitative methods. Data was collected from 10 medical colleges. 824 1st year MBBS students were enrolled in the survey. A semi-structured questionnaire having multiple response answers was used for obtaining information from the students and in-depth interviews were carried out with 21 teachers of Anatomy. Results: Students mentioned that use of illustration is interesting and helpful for proper understanding of histological structure. A majority of the respondents (66%) mentioned “schematic diagram as their choice of form of illustrations. The interviewee teachers agreed that illustration is very much useful for histology practical session. Conclusions: Illustration aids in better recognition of histological structure. Bangladesh Journal of Anatomy July 2021, Vol. 19, No. 1, pp. 3-7

Development of time-series point cloud data changes and automatic structure recognition system using Unreal Engine

Development of time-series point cloud data changes and automatic structure recognition system using Unreal Engine

Are spinal cord and medulla samples from embalmed donors suitable for histological examination? A pilot study.

A general belief exists that tissue from anatomical donors, especially from the central nervous system (CNS), may not be suitable for histological investigation. This is based on the idea that fixation routinely used in embalming whilst optimal for enabling dissection, insufficiently preserves tissue architecture at the cellular level. However, anatomical donors represent a precious resource for microscopical investigation, provided that preservation is sufficient to enable recognition of structures at the histological level. This could considerably extend the biomedical knowledge currently gained from donations. In this study, we addressed this question and examined histologically, samples of medulla and spinal cord from donors from the Anatomical Gift Programme of RCSI in Dublin. Samples of medulla and spinal cord in the cervical, thoracic and lumbar regions were obtained with appropriate permissions from four different donors that had been previously embalmed for routine anatomical examination. The tissue obtained was processed for paraffin embedding and routine histology. Analysis revealed that several features were identifiable with good histological detail. A scoring system was applied to evaluate the level of histological preservation in the various samples by assessing the following parameters: tissue integrity, presence of leptomeninges along the entire section surface, distinction/adherence grey/white matter, identification of neurons, other cell nuclei, neuropil pattern, capillaries and other intraneural vessels. Lumbar spinal cord and to a lesser extent medulla and cervical spinal cord showed on average good quality of preservation. Conversely, thoracic spinal cord tended, in general, to be less well preserved. We can conclude that spinal cord and medulla samples from embalmed donors can be suitable for histological examination. These findings open new avenues of study of spinal cord and brain stem anatomy on cadaveric tissue from donors already existing in anatomy donation programmes. These results also pave the way for the potential development of new human models of study useful to spinal cord and brain stem researchers. Finally, this expands considerably the impact of the generosity of anatomical donors for the advancement of biomedical knowledge.

T-SRE: Transformer-based semantic Relation extraction for contextual paraphrased plagiarism detection

Plagiarism has become a pervasive issue in academics and professionals to safeguard academic integrity and intellectual property rights. The escalating sophistication of plagiarized content through semantic manipulation and structural reorganization poses significant challenges to existing detection systems that rely primarily on lexical similarity measures. The proposed T-SRE (Transformer-based Semantic Relation Extraction), a novel framework addresses the limitations of traditional n-gram and string-matching approaches by leveraging deep semantic analysis. The proposed framework combines Dependency Parsing (DP) for syntactic relationship mapping and Named Entity Recognition (NER) for contextual entity identification, augmented by a transformer-based neural network that captures long-range contextual dependencies. This learning methodology incorporates three key components: a position-aware word reordering algorithm, Levenshtein distance metric for structural similarity, and contextual word embeddings for semantic preservation detection. The proposed T-SRE enhances text structure recognition by combining position-aware reordering with semantic preservation through ensemble learning. The system implements a hierarchical classification scheme that quantifies plagiarism severity through a four-tier taxonomy: heavy, low, non-plagiarized and verbatim copy. The Udacity benchmark dataset showcases the model’s superior detection capabilities, achieving 92% precision, 89% recall, and an F1-score of 90.5%, particularly in lightweight textual modifications.The framework achieves a granularity score of 1.28, outperforming existing approaches.

Comparison of NeedleTrainer™ and ultrasound tissue simulator in a simulated environment among novice regional anaesthesia practitioners

BackgroundUtilising ultrasound technology has resulted in higher success and lower complication rates during regional anaesthesia (RA) procedures. Proper training is necessary to accurately identify structures, optimise images, and improve hand–eye coordination. Simulation training using immersive virtual environments and simulation models has enabled this competency training to be conducted safely before performing on patients. We conducted a study to compare the simulator performance and users’ feedback on a Blue Phantom Regional Anaesthesia Ultrasound Training Block and NeedleTrainer™.MethodsForty-seven participants were recruited via convenient sampling during a RA workshop for novice practitioners. They were divided into the N or B group and then crossover to experience using both Blue Phantom and NeedleTrainer model. Time-to-reach-target, first-pass success rate, and complication rate were assessed, while the learning and confidence scores were rated using six-item and three-item questionnaires, respectively, via a 5-point Likert scale.ResultsBlue Phantom model has a longer time-to-target as compared to the NeedleTrainer model (16 ± 8 vs 8 ± 3 s, p < 0.001), higher first- pass success rate (100% vs 80.9%), and lower complication rate (0% vs 19.1%). Higher overall learning satisfaction scores (28 ± 4 vs 25 ± 4, p = 0.003) and confidence scores after training (13 ± 2 vs 12 ± 2, p < 0.001) were recorded for the Blue Phantom model.ConclusionsWe postulated that the artificial intelligence structure recognition software enables NeedleTrainer users to attain shorter time-to-target. That being said, Blue Phantom provides better operator learning satisfaction, improved confidence, higher success and lower complication rates among novice RA practitioners, possibly due to greater tactile feedback during the simulated training.

Diagnostic electron microscopy in human infectious diseases - Methods and applications.

Diagnostic electron microscopy (EM) is indispensable in all cases of infectious diseases which deserve or profit from the detection of the entire pathogen (i.e. the infectious unit). The focus of its application has shifted during the last decades from routine diagnostics to diagnostics of special cases, emergencies and the investigation of disease pathogenesis. While the focus of application has changed, the methods remain more or less the same. However, since the number of cases for diagnostic EM has declined as the number of laboratories that are able to perform such investigations, the preservation of the present knowledge is important. The aim of this article is to provide a review of the methods and strategies which are useful for diagnostic EM related to infectious diseases in our days. It also addresses weaknesses as well as useful variants or extensions of established methods. The main techniques, negative staining and thin section EM, are described in detail with links to suitable protocols and more recent improvements, such as thin section EM of small volume suspensions. Sample collection, transport and conservation/inactivation are discussed. Strategies of sample examination and requirements for a proper recognition of structures are outlined. Finally, some examples for the actual application of diagnostic EM related to infectious diseases are presented. The outlook section will discuss recent trends in microscopy, such as automated object recognition by machine learning, regarding their potential in supporting diagnostic EM.

Multimodal Strain Sensing System for Shape Recognition of Tensegrity Structures by Combining Traditional Regression and Deep Learning Approaches

Multimodal Strain Sensing System for Shape Recognition of Tensegrity Structures by Combining Traditional Regression and Deep Learning Approaches

Trichoscopic Evaluation of Focal Non-Cicatricial Alopecia in Egyptian Children.

Dermoscopy is a noninvasive diagnostic tool that allows the recognition of morphologic structures not visible to the naked eye. Trichoscopy is useful for the diagnosis and follow-up of hair and scalp disorders. The aim of the present study was to evaluate the causes of focal non-cicatricial alopecia in Egyptian children and to assess the importance of the trichoscope in the diagnosis of each disease. This study was done with 200 Egyptian pediatric patients aged from 2 to 18 years who suffered from focal non-cicatricial alopecia. Clinical and dermoscopic evaluations were performed on all patients, and informed consent was obtained from their parents. The most prevalent diagnoses were alopecia areata (42%) and tinea capitis (40.5%), followed by trichotillomania (8%) and tractional alopecia (7%). Congenital triangular alopecia (1.5%) and patchy androgenetic alopecia (1%) were less common. Trichoscopy revealed distinct features in alopecia areata cases, such as short vellus hair, exclamation mark hair, black dots, broken hair, pigtail hair, and upright regrowing hair. The most common trichoscopic features of tinea capitis were comma hair, corkscrew hair, broken hair, bent hair, zigzag hair, morse code hair, perifollicular scaling, and diffuse scaling. These findings contribute to understanding the etiology and clinical presentation of childhood alopecia, facilitating accurate diagnosis and appropriate management. The routine use of trichoscopy in the clinical evaluation of scalp and hair disorders enhances diagnostic capabilities beyond simple clinical inspection. Trichoscopy reveals disease features that contribute to accurate diagnosis and improved management.

TSRDet: A Table Structure Recognition Method Based on Row-Column Detection

As one of the most commonly used and important data carriers, tables have the advantages of high structuring, strong readability and strong flexibility. However, in reality, tables usually present various forms, such as Excel, images, etc. Among them, the information in the table image cannot be read directly, let alone further applied. Therefore, the research related to image-based table recognition is crucial. It contains the table structure recognition and the table content recognition. Among them, table structure recognition is the most important and difficult task because the table structure is abstract and changeable. In order to address this problem, we propose an innovative table structure recognition method, named TSRDet (Table Structure Recognition based on object Detection). It includes a row-column detection method, named SACNet (StripAttention-CenterNet) and the corresponding post-processing. SACNet is an improved version of the original CenterNet. The specific improvements include the following: firstly, we introduce the Swin Transformer as the encoder to obtain the global feature map of the image. Then, we propose a plug-and-play row-column attention module, including a channel attention module and a row-column spatial attention module. It improves the detection accuracy of rows and columns by capturing long-range row-column feature maps in the image. After completing the row-column detection, this paper also designs a simple and fast post-processing to generate the table structure based on the row-column detection results. Experimental results show that for row-column detection, SACNet has high detection accuracy, even at a high IoU threshold. Specifically, when the threshold is 0.75, its mAP of row detection and column detection still exceeds 90%, which is 91.40% and 92.73% respectively. In addition, in the comparative experiment with the existing object detection methods, SACNet’s performance was significantly better than that of all others. For table structure recognition, the TEDS-Struct score of TSRDet is 95.7%, which shows competitive performance in table structure recognition, and verifies the rationality and superiority of the proposed method.

Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)

Graph convolutional networks (GCNs) are an effective skeleton-based human action recognition (HAR) technique. GCNs enable the specification of CNNs to a non-Euclidean frame that is more flexible. The previous GCN-based models still have a lot of issues: (I) The graph structure is the same for all model layers and input data. GCN model's hierarchical structure and human action recognition input diversity make this a problematic approach; (II) Bone length and orientation are understudied due to their significance and variance in HAR. For this purpose, we introduce an Extended Multi-stream Temporal-attention Adaptive GCN (EMS-TAGCN). By training the network topology of the proposed model either consistently or independently according to the input data, this data-based technique makes graphs more flexible and faster to adapt to a new dataset. A spatial, temporal, and channel attention module helps the adaptive graph convolutional layer focus on joints, frames, and features. Hence, a multi-stream framework representing bones, joints, and their motion enhances recognition accuracy. Our proposed model outperforms the NTU RGBD for CS and CV by 0.6% and 1.4%, respectively, while Kinetics-skeleton Top-1 and Top-5 are 1.4% improved, UCF-101 has improved 2.34% accuracy and HMDB-51 dataset has significantly improved 1.8% accuracy. According to the results, our model has performed better than the other models. Our model consistently outperformed other models, and the results were statistically significant that demonstrating the superiority of our model for the task of HAR and its ability to provide the most reliable and accurate results.

TableExtractNet: A Model of Automatic Detection and Recognition of Table Structures from Unstructured Documents

This paper presents TableExtractNet, a model that automatically finds and understands tables from scanned documents, tasks that are essential for quick use of information in many fields. This is driven by the growing need for efficient and accurate table interpretation in business documents where tables enhance data communication and aid decision-making. The model uses a mix of two advanced techniques, CornerNet and Faster R-CNN, to accurately locate tables and understand their layout. Tests on standard datasets, IIIT-AR-13K, STDW, SciTSR, and PubTabNet, show that this model performs better than previous ones, making it very good at dealing with tables that have complicated designs or are in documents with a lot of detail. The success of this model marks a step forward in making document analysis more automated. It makes it easier to turn complex scanned documents containing tables into data that are more manipulable by computers.

The crystal structure of Nictaba reveals its carbohydrate-binding properties and a new lectin dimerization mode.

Nictaba is a (GlcNAc)n-binding, stress-inducible lectin from Nicotiana tabacum that serves as a representative for the Nictaba-related lectins, a group of proteins that play pivotal roles in plant defense mechanisms and stress response pathways. Despite extensive research into biological activities and physiological role(s) of the lectin, the three-dimensional structure of Nictaba remained largely unknown. Here, we report crystal structures for Nictaba in the apo form and bound to chitotriose. The structures reveal that the Nictaba protomer has a jelly-roll fold, similar to the cucumber lectin Cus17, but exhibit a unique and previously unseen mode of dimerization. The chitotriose binding mode, similar to Cus17, centers around the central GlcNAc residue, providing insights into the determinants of specificity of Nictaba towards carbohydrate structures. By integrating these structural insights with inputs from glycan arrays, molecular docking, and molecular dynamics simulations, we propose that Nictaba employs a single carbohydrate-recognition domain within each of the two subunits in the dimer to display pronounced specificity towards GlcNAc-containing carbohydrates. Furthermore, we identified amino acid residues involved in the extended binding site capable of accommodating structurally diverse high-mannose and complex N-glycans. Glycan array and in silico analyses revealed interactions centered around the conserved Man3GlcNAc2 core, explaining the broad recognition of N-glycan structures. Collectively, the structural and biochemical insights presented here fill a void into the atlas of lectin structure-function relationships and pave the way for future developments in plant stress biology and lectin-based applications.

Priority Organic Pollutant Monitoring Inventory and Relative Risk Reduction Potential for Solid Waste Incineration.

Incineration is a promising sustainable treatment method for solid waste. However, the ongoing revelation of new toxic pollutants in this process has become a controversial issue impeding its development. Thus, identifying and regulating high-risk pollutants emerge as pivotal strides toward reconciling this debate. In this study, we proposed a workflow aimed at establishing priority monitoring inventories for organic compounds emitted by industries involving full-component structural recognition, environmental behavior prediction, and emission risk assessment, specifically focusing on solid waste incineration (SWI). A total of 174 stack gas samples from 29 incinerators were first collected. Nontarget full organic recognition technology was then deployed to analyze these samples, and 646 organic compounds were identified. The characteristics, i.e., toxicity effects, toxicity concentrations, persistence, and bioaccumulation potential, of these compounds were assessed and ranked based on the TOXCAST database from the US Environmental Protection Agency and structural effect models. Combined with consideration of changes in seasons and waste types, a priority control inventory consisting of 28 organic pollutants was finally proposed. The risks associated with SWI across different regions in China and various countries were assessed, and results pinpointed that by controlling the priority pollutants, the average global emission risk attributed to SWI was anticipated to be reduced by 71.4%. These findings offer significant guidance for decision-making in industrial pollutant management, emphasizing the importance of targeted regulation and monitoring to enhance the sustainability and safety of incineration processes.

Enhancing abstractive summarization of scientific papers using structure information

Abstractive summarization of scientific papers has always been a research focus, yet existing methods face two main challenges. First, most summarization models rely on Encoder-Decoder architectures that treat papers as sequences of words, thus fail to fully capture the structured information inherent in scientific papers. Second, existing research often use keyword mapping or feature engineering to identify the structural information, but these methods struggle with the structural flexibility of scientific papers and lack robustness across different disciplines. To address these challenges, we propose a two-stage abstractive summarization framework that leverages automatic recognition of structural functions within scientific papers. In the first stage, we standardize chapter titles from numerous scientific papers and construct a large-scale dataset for structural function recognition. A classifier is then trained to automatically identify the key structural components (e.g., Background, Methods, Results, Discussion), which provides a foundation for generating more balanced summaries. In the second stage, we employ Longformer to capture rich contextual relationships across sections and generating context-aware summaries. Experiments conducted on two domain-specific scientific paper summarization datasets demonstrate that our method outperforms advanced baselines, and generates more comprehensive summaries. The code and dataset can be accessed at https://github.com/tongbao96/code-for-SFR-AS.

Rational design based on multi-monomer simultaneous docking for epitope imprinting of SARS-CoV-2 spike protein

Among biomimetic strategies shaping engineering designs, molecularly imprinted polymer (MIP) technology stands out, involving chemically synthesised receptors emulating natural antigen-antibody interactions. These versatile ‘designer polymers’ with remarkable stability and low cost, are pivotal for in vitro diagnostics. Amid the recent global health crisis, we probed MIPs’ potential to capture SARS-CoV-2 virions. Large biotemplates complicate MIP design, influencing generated binding site specificity. To precisely structure recognition sites within polymers, we innovated an epitope imprinting method supplemented by in silico polymerization component screening. A viral surface Spike protein informed epitope selection was targeted for MIP development. A novel multi-monomer docking approach (MMSD) was employed to simulate classical receptor-ligand interactions, mimicking binding reinforcement across multiple amino acids. Around 40 monomer combinations were docked to the epitope sequence and top performers experimentally validated via rapid fluorescence binding assays. Notably, high imprinting factor polymers correlated with MMSD predictions, promising rational MIP design applicable to diverse viral pathologies.

Study on in-situ measurement and analysis method of rock pores based on borehole camera technology

In-situ measurement and analysis of pores are helpful to understand the properties of rocks. However, continuous quantitative analysis of pores in whole borehole is still difficult. Borehole camera technology can capture the borehole wall image of the whole well section by going deep into the borehole, which provides technical conditions for the measurement and analysis of pores. In this paper, a continuous measurement method of rock pores based on borehole camera technology is introduced. According to the characteristics of the optical image of borehole wall, a method of pore recognition and analysis is proposed. Specifically, the influence of redundant information on pore recognition is eliminated, and then the pores are accurately recognized by binarization and morphological operation. Based on the results of pore recognition and the coordinate information provided by borehole wall image, the calculation methods of surface porosity and line porosity are proposed, and the statistical analysis of pore distribution is realized according to the calculation results. In addition, the morphological characteristics of pores are also discussed. This method realizes the accurate recognition and quantitative calculation of pore structure based on borehole wall image, and provides a new method for continuous analysis of pore structure in the whole well.

Three-dimensional modeling of 500 kV transmission lines by airborne LiDAR

This study aims to enhance the accuracy of three-dimensional (3D) modeling in the planning, design, operation management, and risk assessment of 500 kV transmission lines. Addressing the limitations of traditional two-dimensional (2D) or low-precision 3D models, a new method based on airborne Light Detection and Ranging (LiDAR) technology is proposed. Initially, high-density, high-precision 3D point cloud data are collected using airborne LiDAR technology. This data is then processed using specialized software for noise removal, terrain classification extraction, and Geographic Information System (GIS) data integration. Subsequently, a Convolutional Neural Network (CNN) is employed to classify the 3D point cloud data to enhance the accuracy of complex structure recognition. Lastly, the point cloud data are converted into linear and planar entities using Computer-Aided Design (CAD) technology, achieving high-precision 3D reconstruction of the 500 kV transmission lines and their complex terrain environment. Experimental results show that the spatial resolution of the constructed model reaches 0.1 m per pixel, with overall geometric accuracy within ±5 cm. Compared to traditional aerial imagery and ground survey methods, the model based on airborne LiDAR technology achieves improvements of 30 % in detail richness and 35 % in terrain adaptability, with a 45 % increase in decision-making efficiency. These improvements significantly enhance the accuracy of line operations, safety assessments, and environmental impact analyses, providing solid data support for the modernization and intelligent development of the power industry.

A Deep Learning Application of Capsule Endoscopic Gastric Structure Recognition Based on a Transformer Model.

Gastric structure recognition systems have become increasingly necessary for the accurate diagnosis of gastric lesions in capsule endoscopy. Deep learning, especially using transformer models, has shown great potential in the recognition of gastrointestinal (GI) images according to self-attention. This study aims to establish an identification model of capsule endoscopy gastric structures to improve the clinical applicability of deep learning to endoscopic image recognition. A total of 3343 wireless capsule endoscopy videos collected at Nanfang Hospital between 2011 and 2021 were used for unsupervised pretraining, while 2433 were for training and 118 were for validation. Fifteen upper GI structures were selected for quantifying the examination quality. We also conducted a comparison of the classification performance between the artificial intelligence model and endoscopists by the accuracy, sensitivity, specificity, and positive and negative predictive values. The transformer-based AI model reached a relatively high level of diagnostic accuracy in gastric structure recognition. Regarding the performance of identifying 15 upper GI structures, the AI model achieved a macroaverage accuracy of 99.6% (95% CI: 99.5-99.7), a macroaverage sensitivity of 96.4% (95% CI: 95.3-97.5), and a macroaverage specificity of 99.8% (95% CI: 99.7-99.9) and achieved a high level of interobserver agreement with endoscopists. The transformer-based AI model can accurately evaluate the gastric structure information of capsule endoscopy with the same performance as that of endoscopists, which will provide tremendous help for doctors in making a diagnosis from a large number of images and improve the efficiency of examination.

Real-time segmentation of biliary structure in pure laparoscopic donor hepatectomy

Pure laparoscopic donor hepatectomy (PLDH) has become a standard practice for living donor liver transplantation in expert centers. Accurate understanding of biliary structures is crucial during PLDH to minimize the risk of complications. This study aims to develop a deep learning-based segmentation model for real-time identification of biliary structures, assisting surgeons in determining the optimal transection site during PLDH. A single-institution retrospective feasibility analysis was conducted on 30 intraoperative videos of PLDH. All videos were selected for their use of the indocyanine green near-infrared fluorescence technique to identify biliary structure. From the analysis, 10 representative frames were extracted from each video specifically during the bile duct division phase, resulting in 300 frames. These frames underwent pixel-wise annotation to identify biliary structures and the transection site. A segmentation task was then performed using a DeepLabV3+ algorithm, equipped with a ResNet50 encoder, focusing on the bile duct (BD) and anterior wall (AW) for transection. The model’s performance was evaluated using the dice similarity coefficient (DSC). The model predicted biliary structures with a mean DSC of 0.728 ± 0.01 for BD and 0.429 ± 0.06 for AW. Inference was performed at a speed of 15.3 frames per second, demonstrating the feasibility of real-time recognition of anatomical structures during surgery. The deep learning-based semantic segmentation model exhibited promising performance in identifying biliary structures during PLDH. Future studies should focus on validating the clinical utility and generalizability of the model and comparing its efficacy with current gold standard practices to better evaluate its potential clinical applications.