Single Segment Research Articles

Diagnosis of Heart Failure Complicated with Sleep Apnea Syndrome by Thoracic Computerized Tomography under Artificial Intelligence Algorithm.

The aim of this study was to explore the application effect of thoracic computerized tomography (CT) under single threshold segmentation algorithm in the diagnosis of heart failure (HF) complicated with sleep apnea syndrome. 30 patients diagnosed with HF complicated with sleep apnea syndrome were chosen for the research. Another 30 patients without sleep apnea syndrome were selected as the control group, whose age, height, and weight were similar to those of the experimental group. Then, a model for thoracic CT image segmentation was proposed under the single threshold segmentation algorithm, and the faster region convolutional neural network (Faster RCNN) was applied to label the thoracic respiratory lesions. All the patients underwent thoracic CT examination, and the obtained images were processed using the algorithm model above. After that, the morphology of the patient's respiratory tract after treatment was observed. The results suggested that the improved single threshold segmentation algorithm was effective for the image segmentation of patient lesions, and the Faster RCNN could effectively finish the labeling of the lesion area in the CT image. The classification accuracy of the Faster RCNN was about 0.966, and the loss value was about 0.092. With CT scanning under the algorithm, it was found that the airway collapse of the posterior palatal area, retrolingual area, and laryngopharyngeal area of the sleep apnea syndrome patients was significantly greater than that of the control group (P < 0.05). But there was no significant difference of the collapse of the nasopharyngeal area between the two groups (P > 0.05). The single threshold segmentation algorithm had a better segmentation accuracy for thoracic CT images in patients with HF and sleep apnea syndrome, so it had a highly promising application prospect in the diagnosis of the disease.

Female Genital Variation Far Exceeds that of Male Genitalia: A Review of Comparative Anatomy of Clitoris and the Female Lower Reproductive Tract in Theria.

SynopsisA review of the literature on the anatomy of the lower female genital tract in therian mammals reveals, contrary to the general perception, a large amount of inter-specific variation. Variation in females is anatomically more radical than that in the male genitalia. It includes the absence of whole anatomical units, like the cervix in many Xenarthra, or the absence of the urogenital sinus (UGS), as well as the complete spatial separation of the external clitoral parts from the genital canal (either vagina or UGS). A preliminary phylogenetic analysis shows two patterns. Some morphs are unique to early branching clades, like the absence of the cervix, while others arose multiple times independently, like the flattening out or loss of the UGS, or the extreme elongation of the clitoris. Based on available information, the ancestral eutherian configuration of the external female genitalia included a cervix, a single vaginal segment, a tubular UGS, and an unperforated clitoris close to the entrance of the genital canal. The evidence for either bilobed or unitary glandes clitorides is ambivalent. Despite the wealth of information available, many gaps in knowledge remain and will require a community-wide effort to come to a more robust model of female genital evolutionary patterns.

Individual differences in simultaneous perceptual compensation for coarticulatory and lexical cues

Abstract Idiosyncratic perceptual compensation behaviors are considered to have a bearing on the perceptual foundation of sound change. We investigate how compensation processes driven by lexical and coarticulatory contexts simultaneously affect listeners’ perception of a single segment and the individual differences in the compensation patterns. Sibilants on an /s-ʃ/ continuum were embedded into four lexical frames that differed in whether the lexical context favored /s/ or /ʃ/ perceptually and whether the vocalic context favored /s/ or not. Forty-two participants took a lexical decision task to decide whether each stimulus was a word or not. They also completed the autism-spectrum quotient questionnaire. The aggregate results of the lexical decision task show coexistence of lexically induced and coarticulatorily induced perceptual shifts in parallel. A negative correlation was found between the two kinds of perceptual shifts for individual listeners in lexical decisions, lending support to a potential trade-off between compensation magnitudes on different levels of cue integration.

A single smartwatch-based segmentation approach in human activity recognition

The development of smart wearable devices has driven the rapid progress of activity recognition. However, existing activity recognition methods are still struggling to recognize single arm swings due to coarse-grained sensor data segmentation. Refined arm-swing-wise data segmentation is vital in some specific cases, such as the rehabilitation of disabled patients. In this paper, we propose a smartwatch-based arm-swing-wise data segmentation approach for human activity recognition, which converts original sensor signals into square-wave signals to detect the cut-off points of each arm swing. Particularly, our method can adaptively adjust the window size and step size of a sliding window without considering the change of swing speed. Empirical evaluation on two datasets, a self-collected dataset and a publicly-available benchmark dataset, shows superior performance of our approach over other methods under different settings, such as classifiers, features, and wearing positions.

A Performance Improvement Strategy for Concrete Damage Detection Using Stacking Ensemble Learning of Multiple Semantic Segmentation Networks.

Semantic segmentation network-based methods can detect concrete damage at the pixel level. However, the performance of a single semantic segmentation network is often limited. To improve the concrete damage detection performance of a semantic segmentation network, a stacking ensemble learning-based concrete crack detection method using multiple semantic segmentation networks is proposed. To realize this method, a database including 500 images and their labels with concrete crack and spalling is built and divided into training and testing sets. At first, the training and prediction of five semantic segmentation networks (FCN-8s, SegNet, U-Net, PSPNet and DeepLabv3+) are respectively implemented on the built training set according to a five-fold cross-validation principle, where 80% of the training images are used in the training process, and 20% training images are reserved. Then, in predicting the results of reserved training images from trained semantic segmentation networks, the class labels of all pixels are collected, and then four softmax regression-based ensemble learning models are trained using the collected class labels and their true classification labels. The trained ensemble learning models are applied to regressed testing results of semantic segmentation network models. Compared with the best single semantic segmentation network, the best ensemble learning model provides performance improvement of 0.21% PA, 0.54% MPA, 3.66% MIoU, and 0.12% FWIoU, respectively. The study results show that the stacking ensemble learning strategy can indeed improve concrete damage detection performance through ensemble learning of multiple semantic segmentation networks.

FAS-A Fully Actuated Segment for Tendon-Driven Continuum Robots.

We propose a segment design that combines two distinct characteristics of tendon-driven continuum robots, i.e. variable length and non-straight tendon routing, into a single segment by enabling rotation of its backbone. As a result, this segment can vary its helical tendon routing and has four degrees-of-freedom, while maintaining a small-scale design with an overall outer diameter of 7 mm thanks to an extrinsic actuation principle. In simulation and on prototypes, we observe improved motion capabilities, as evidenced by position redundancy and follow-the-leader deployment along spatially tortuous paths. To demonstrate the latter on a physical prototype, a simple, yet effective area-based error measure for follow-the-leader deployment is proposed to evaluate the performance. Furthermore, we derive a static model which is used to underpin the observed motion capabilities. In summary, our segment design extends previous designs with minimal hardware overhead, while either archiving similar accuracy in position errors and planar follow-the-leader deployment, or exhibiting superior motion capabilities due to position redundancy and spatial follow-the-leader deployment.

The Proposal of an Expert System Consisting of Image Categorization Using Deep Learning and Application to Medical Diagnosis

Classification is one well-known type of supervised machine learning and has been developed and applied in the medical, and industrial fields. Currently, single machine learning models, such as support vector machine (SVM) and decision tree are widely implemented, but the difficulty of embedding human knowledge in application with image datasets impedes application extension. To address this problem, we propose a category classification expert system (CCES), which consists of a single semantic segmentation network model, deep learning network model, and classification machine learning model. Unlike a single machine learning model with limited functionality, CCES can embed human expert knowledge into the system, increasing model accuracy, sensitivity, and adaptability of the input with image datasets in the category classification field. We describe a medical category classification application using CCES in detail and describe the evaluation results.

A Novel Image Watermarking Method Against Crop Attack Using Two-Step Sudoku Puzzle

Digital image watermarking is used to secure the digital images. There are several methods for securing the images. But there is probability to destroy the information by an attacker. Attacker can damage even a single segment of watermark image. There are many techniques to overcome from several attacks through which the cropped section of an image can be recover and there is no need to detect watermark. A robust image watermarking method against various cropping attack by the use of Sudoku puzzle is suggested in this paper. This method is build upon the attributes of permutation of Sudoku matrix and it gives Sudoku table has 9x9 formats, i.e. uniformly divided into multiple sample of images in the sections of the original image. Justified Sudoku result is explained for the embedded and extraction of the watermark image. The standard format of Sudoku having 9x9 matrix is used and the method expressed the hardiness up to great extent against crop attack.

One-stage freehand minimally invasive pedicle screw fixation combined with mini-access surgery through OLIF approach for the treatment of lumbar tuberculosis

ObjectiveTo compare one-stage freehand minimally invasive pedicle screw fixation (freehand MIPS) combined with mini-access surgery through OLIF approach with posterior approach for treatment of lumbar tuberculosis (TB), and evaluate its feasibility, efficacy and safety in debridement, bone graft fusion and internal fixation.Methods48 patients with single segment lumbar TB from June 2014 to June 2017 were included. Among them, 22 patients underwent one-stage freehand MIPS combined with mini-access surgery through OLIF approach (group 1), 26 patients were treated with posterior open surgery (group 2). Duration of operation, blood loss, and stay time in hospital were compared. Pre- and postoperative visual analog scale (VAS) pain scores, Oswestry disability index (ODI), erythrocyte sedimentation rate, complications and images were also recorded.ResultsPatients in group 1 showed significantly less blood loss (165 ± 73 ml vs 873 ± 318 ml, P < 0.001), shorter stay time in hospital (6/4–8 days vs 12/8–15 days, P < 0.001), while longer duration of operation (185 ± 14 min vs 171 ± 12 min, P < 0.001) than group 2 did. VAS scores significantly decreased after surgery in both groups, however, VAS scores of group 1 were significantly lower than that of group 2 immediately after surgery and during follow-ups (P < 0.001). ODI of group 1 was also significantly lower than that of group 2 at 12-month after surgery (P < 0.001).ConclusionOne-stage freehand MIPS combined with mini-access surgery through OLIF approach is a feasible, efficient and safe method in treating single segment lumbar TB. It shows advantages of less surgical trauma and faster postoperative recovery.

Ab initio development of generalized Lennard-Jones (Mie) force fields for predictions of thermodynamic properties in advanced molecular-based SAFT equations of state.

A methodology for obtaining molecular parameters of a modified statistical associating fluid theory for variable-range interactions of Mie form (SAFT-VR Mie) equation of state (EoS) from ab initio calculations is proposed for non-associative species that can be modeled as single spherical segments. The methodology provides a strategy to map interatomic or intermolecular potentials obtained from ab initio quantum-chemistry calculations to the corresponding Mie potentials that can be used within the SAFT-VR Mie EoS. The inclusion of corrections for quantum and many-body effects allows for an excellent, fully predictive description of the vapor-liquid envelope and other bulk thermodynamic properties of noble gases; this description is of similar or superior quality to that obtained using SAFT-VR Mie with parameters regressed in the traditional way using experimental thermodynamic-property data. The methodology is extended to an anisotropic species, methane, where similar levels of accuracy are obtained. The efficacy of using less-accurate quantum-chemistry methods in this methodology is explored, showing that these methods do not provide satisfactory results, although we note that the description is nevertheless substantially better than those obtained using the conductor-like screening model for describing real solvents (COSMO-RS), the only other fully predictive ab initio method currently available. Overall, the reliance on thermophysical data is completely dispensed with, providing the first extensible, wholly predictive SAFT-type EoSs.

An integrated biological system for air pollution control in WtE plants and interaction between NO reduction and toluene oxidation

The abatement of NO and VOCs in the flue gas from WtE plants is of great significance for improving the atmospheric environmental quality at present. In this study, a device of absorption-bioreactor coupling biotrickling-filter (ABR-BTF) was built to realize the simultaneous removal of NO and VOCs, in which the chemical absorption-bioreactor (ABR) was used for reducing NO and the biotrickling-filter (BTF) was employed for eliminating toluene. When the simulated flue gas containing 400 mg m−3 NO and 150 mg m−3 toluene passed through the system for 30 s, the removal efficiency of NO and toluene reached 85% and 90%, respectively. In contrast with the single ABR segment, the loss rate of NO complexing absorber was reduced by 85% in ABR-BTF. Meanwhile, a variety of novel bacterial genera in the field of biological denitrification and VOCs elimination were discovered within the integrated system biome. Thereinto, Candidatus_Cloacamonas and Syntrophomonas produced the hydrogen, which could as electron donors be consumed by the dissolved oxygen species during the process of VOCs degradation, promoting the biological reduction and reducing the loss rate of complexing absorbent in the ABR portion. Meanwhile, Tisierella and Desulfitobacterium could reduce sulfite to S2−, so that part of the complexing absorbent was transformed into FeS and re-entered into the circulation system through the redox reaction with Fe(III). The integrated biological purification system can efficiently remove NO and VOCs simultaneously, and overcome the problems of insufficient microbial reduction rate for poor hydrophobic VOCs, which will provide a fundamental for the optimization and industrial application of the biological technology in WtE plants flue gas treatment.

An Intelligent Analysis Method for 3D Wheat Grain and Ventral Sulcus Traits Based on Structured Light Imaging.

The wheat grain three-dimensional (3D) phenotypic characters are of great significance for final yield and variety breeding, and the ventral sulcus traits are the important factors to the wheat flour yield. The wheat grain trait measurements are necessary; however, the traditional measurement method is still manual, which is inefficient, subjective, and labor intensive; moreover, the ventral sulcus traits can only be obtained by destructive measurement. In this paper, an intelligent analysis method based on the structured light imaging has been proposed to extract the 3D wheat grain phenotypes and ventral sulcus traits. First, the 3D point cloud data of wheat grain were obtained by the structured light scanner, and then, the specified point cloud processing algorithms including single grain segmentation and ventral sulcus location have been designed; finally, 28 wheat grain 3D phenotypic characters and 4 ventral sulcus traits have been extracted. To evaluate the best experimental conditions, three-level orthogonal experiments, which include rotation angle, scanning angle, and stage color factors, were carried out on 125 grains of 5 wheat varieties, and the results demonstrated that optimum conditions of rotation angle, scanning angle, and stage color were 30°, 37°, black color individually. Additionally, the results also proved that the mean absolute percentage errors (MAPEs) of wheat grain length, width, thickness, and ventral sulcus depth were 1.83, 1.86, 2.19, and 4.81%. Moreover, the 500 wheat grains of five varieties were used to construct and validate the wheat grain weight model by 32 phenotypic traits, and the cross-validation results showed that the R2 of the models ranged from 0.77 to 0.83. Finally, the wheat grain phenotype extraction and grain weight prediction were integrated into the specialized software. Therefore, this method was demonstrated to be an efficient and effective way for wheat breeding research.

Analysis of torsionally loaded non-uniform circular piles in multi-layered non-homogeneous elastic soils

A new method for the torsional analysis of non-uniform circular piles partially or fully embedded in multi-layered elastic soils is developed. The mechanical response of non-uniform piles such as those with a linear variation in cross-section (i.e., tapered piles) or discontinuous variations (i.e., stepped piles), and reacting against a non-homogeneous elastic soil can be easily investigated with the proposed formulation. The non-homogeneity of the soil is incorporated by assuming a shear modulus distribution that fits a quadratic equation (i.e., G(z)=Go+sz+tz2). The governing differential equation (GDE) of a single non-uniform circular pile segment is derived and solved using the differential transformation method (DTM); then, the stiffness matrix of the segment is found by applying equilibrium and compatibility conditions at the ends of the element. The analysis of non-uniform piles in multi-layered soils is conducted by dividing the pile into multiple segments (i.e., each segment representing a change in soil properties or pile geometry) and then assembling them using classic matrix methods. The proposed matrix formulation is simple to implement, easy to incorporate into already available structural matrix analysis codes and provides accurate results when compared with more cumbersome analytical and numerical solutions. The simplicity, practicality and accuracy of the method is validated with five illustrative examples.

PECULIARITIES OF THE PORTA-CAVAL FIBROUS UNION EXISTENCE IN A SEPARATE SEGMENT OF HUMAN LIVER

undamental work relies on studying 40 normal human livers. Macro-microscopic morphologic methods have been used to reveal presence of porta-caval fibrotic connections and its characteristics in single hepatic segment. In hepatic segments major branches of portal complexes and hepatic veins in the area of intersection touch each other and give rise to porta-caval fibrotic connections. It has been demonstrated in all livers. In a single organ, number of porta-caval fibrotic connections ranged from 1 to 9, which depended on a density of portal and caval venous branching. Left lobular segments are remarkable for the constant presence of porta-caval fibrotic connections, where there is an abundance of fan-shaped (I segment) and overlying (II and III segments) connection types. In terms of porta-caval fibrotic connections, bile ducts are in contact with wall of hepatic veins and inferior vena cava, which determines high likelihood of extension of inflammatory process of biliary pathways to the caval veins.

The Mismatch Between Bony Endplates and Grafted Bone Increases Screw Loosening Risk for OLIF Patients With ALSR Fixation Biomechanically.

The mismatch between bony endplates (BEPs) and grafted bone (GB) triggers several complications biomechanically. However, no published study has identified whether this factor increases the risk of screw loosening by deteriorating the local stress levels. This study aimed to illustrate the biomechanical effects of the mismatch between BEP and GB and the related risk of screw loosening. In this study, radiographic and demographic data of 56 patients treated by single segment oblique lumbar interbody fusion (OLIF) with anterior lateral single rod (ALSR) fixation were collected retrospectively, and the match sufficiency between BEP and GB was measured and presented as the grafted bony occupancy rate (GBOR). Data in patients with and without screw loosening were compared; regression analyses identified independent risk factors. OLIF with different GBORs was simulated in a previously constructed and validated lumbosacral model, and biomechanical indicators related to screw loosening were computed in surgical models. The radiographic review and numerical simulations showed that the coronal plane’s GBOR was significantly lower in screw loosening patients both in the cranial and caudal vertebral bodies; the decrease in the coronal plane’s GBOR has been proven to be an independent risk factor for screw loosening. In addition, numerical mechanical simulations showed that the poor match between BEP and GB will lead to stress concentration on both screws and bone-screw interfaces. Therefore, we can conclude that the mismatch between the BEP and GB will increase the risk of screw loosening by deteriorating local stress levels, and the increase in the GBOR by modifying the OLIF cage’s design may be an effective method to optimize the patient’s prognosis.

A numerical model for geometrically nonlinear analysis of a pipe-lay on a rough seafloor

Despite a detailed assessment of a potential route for offshore oil and gas transport pipelines, the pipelines are still often being subjected to a pipe-lay on a rough seafloor, which can substantially increase the internal forces within the pipeline.To ensure pipeline integrity during the installation, it is essential to obtain internal force envelope diagrams, which provide the historical maximum and minimum force bounds at every location along the pipeline throughout the entire pipe-lay proceeding.This paper provides a simple numerical technique for calculating the internal force envelope diagrams. The entire pipeline is modeled as a single continuous segment considering geometrical nonlinearity induced by large deformations. The solution technique is based on consistent minimization of the total potential energy of the system discretized as a Riemann sum and the solution of the subsequent algebraic system of nonlinear finite difference equations with a Newton-Raphson technique.The feasibility of the proposed technique is demonstrated through several scenarios of a pipe-lay across the basic types of seafloor irregularity. The results have revealed that, in general, any seafloor irregularity leads to an increase in maximum internal force values at certain locations.The proposed technique provides a time-saving alternative to commercial special-purpose finite element software.

Variational Inference for Quantifying Inter-observer Variability in Segmentation of Anatomical Structures.

Lesions or organ boundaries visible through medical imaging data are often ambiguous, thus resulting in significant variations in multi-reader delineations, i.e., the source of aleatoric uncertainty. In particular, quantifying the inter-observer variability of manual annotations with Magnetic Resonance (MR) Imaging data plays a crucial role in establishing a reference standard for various diagnosis and treatment tasks. Most segmentation methods, however, simply model a mapping from an image to its single segmentation map and do not take the disagreement of annotators into consideration. In order to account for inter-observer variability, without sacrificing accuracy, we propose a novel variational inference framework to model the distribution of plausible segmentation maps, given a specific MR image, which explicitly represents the multi-reader variability. Specifically, we resort to a latent vector to encode the multi-reader variability and counteract the inherent information loss in the imaging data. Then, we apply a variational autoencoder network and optimize its evidence lower bound (ELBO) to efficiently approximate the distribution of the segmentation map, given an MR image. Experimental results, carried out with the QUBIQ brain growth MRI segmentation datasets with seven annotators, demonstrate the effectiveness of our approach.

An Integration of MicroRNA and Transcriptome Sequencing Analysis Reveal Regulatory Roles of miRNAs in Response to Chilling Stress in Wild Rice.

A chromosome single segment substitution line (CSSL) DC90, which was generated by introgressing CTS-12, a locus derived from common wild rice (Oryza rufipogon Griff.), into the 9311 (Oryza sativa L. ssp. indica) background, exhibits a chilling tolerance phenotype under chilling stress. Here, an integration of microRNA (miRNA) deep sequencing and transcriptomic sequencing analysis was performed to explore the expression profiles of miRNAs and their target genes mediated by CTS-12 under chilling stress, and to reveal the possible regulatory mechanisms of miRNAs that are involved in chilling tolerance. Integration analysis revealed that a number of differentially expressed miRNAs (DEMs) and putative target genes with different expression patterns and levels were identified in 9311 and DC90 under chilling stress. KEGG enrichment analysis revealed that the target genes that are regulated by chilling-induced miRNAs are involved in the regulation of various biological processes/pathways, including protein biosynthesis, redox process, photosynthetic process, and chloroplast development in two genotypes. CRISPR/Cas9 editing of the target genes of the key DEMs in a chilling tolerant rice variety Zhonghua 11 (ZH11) found that LOC_Os11g48020 (OsGL1-11), one of the putative target genes of osa-miR1846a/b-5p and encoding a wax synthesis protein, is correlated with a chilling stress tolerance phenotype, implying osa-miR1846a/b-5p/OsGL1-11 plays an important role in CTS-12-mediated chilling stress tolerance regulatory pathway(s). Therefore, we speculate that the CTS-12 may regulate the key miRNA target genes in response to chilling stress by differential regulation of miRNAs in wild rice, thereby resulting in the variation of chilling tolerance phenotype between 9311 and DC90.

Premature Beats Rejection Strategy on Paroxysmal Atrial Fibrillation Detection.

Paroxysmal atrial fibrillation (PAF) may related to the risk of thromboembolism and is the most common cardiac risk factor of cryptogenic stroke (CS). Due to its paroxysmal characteristics, it is usually diagnosed by continuous long-term ECG. Patients with paroxysmal atrial fibrillation usually have premature beats at the same time which is easy to be confused with the rhythm of atrial fibrillation. Therefore, in this article, we designed a screening algorithm for single premature beat, multi premature beats, bigeminy and trigeminy premature beats, according to their rhythm characteristics to reduce false detection caused by premature beats during the PAF detection process. The proposed elimination method was verified on ECG segments with different types of premature beats, and tested on long-term ECG data of PAF patients. ECG segments of different kinds of premature beats were selected from MIT Atrial Fibrillation database (MIT-AFDB), MIT-BIH Arrhythmia database (MIT-AR) and wearable ECG data from the China Physiological Signal Challenge 2021 (CPSC 2021). The proposed method can effectively eliminate single premature beat segments with 99.5% accuracy, and it also can eliminate more than 95% of ECG segments with other types of premature beats. We designed PAF-score as a new index to evaluate the accuracy of detection, and we also calculate the misjudged and missed segments to comprehensively evaluate the PAF detection algorithm. The proposed method get a PAF-score of 0.912 on MIT-AFDB. The proposed method also has the potential to implant low computing power wearable devices for real-time analysis.

Nucleus segmentation: towards automated solutions.

Single nucleus segmentation is a frequent challenge of microscopy image processing, since it is the first step of many quantitative data analysis pipelines. The quality of tracking single cells, extracting features or classifying cellular phenotypes strongly depends on segmentation accuracy. Worldwide competitions have been held, aiming to improve segmentation, and recent years have definitely brought significant improvements: large annotated datasets are now freely available, several 2D segmentation strategies have been extended to 3D, and deep learning approaches have increased accuracy. However, even today, no generally accepted solution and benchmarking platform exist. We review the most recent single-cell segmentation tools, and provide an interactive method browser to select the most appropriate solution.