Intelligent classification of cardiotocography based on a support vector machine and convolutional neural network: Multiscene research.

OBJECTIVE: To propose a computerized system utilizing multiscene analysis based on a support vector machine (SVM) and convolutional neural network (CNN) to assess cardiotocography (CTG) intelligently. METHODS: We retrospectively collected 2542 CTG records of singleton pregnancies delivered at the maternity ward of the First Affiliated Hospital of Xi'an Jiaotong University from October 10, 2020, to August 7, 2021. CTG records were divided into five categories (baseline, variability, acceleration, deceleration, and normality). Apart from the category of normality, the other four different categories of abnormal data correspond to four scenes. Each scene was divided into training and testing sets at 9:1 or 7:3. We used three computer algorithms (dynamic threshold, SVM, and CNN) to learn and optimize the system. Accuracy, sensitivity, and specificity were performed to evaluate performance. RESULTS: The global accuracy, sensitivity, and specificity of the system were 93.88%, 93.06%, and 94.33%, respectively. In acceleration and deceleration scenes, when the convolution kernel was 3, the test data set reached the highest performance. CONCLUSION: The multiscene research model using SVM and CNN is a potential effective tool to assist obstetricians in classifying CTG intelligently.

Clinically Applicable Pathological Diagnosis System for Cell Clumps in Endometrial Cancer Screening via Deep Convolutional Neural Networks.

OBJECTIVES: The soaring demand for endometrial cancer screening has exposed a huge shortage of cytopathologists worldwide. To address this problem, our study set out to establish an artificial intelligence system that automatically recognizes and diagnoses pathological images of endometrial cell clumps (ECCs). METHODS: We used Li Brush to acquire endometrial cells from patients. Liquid-based cytology technology was used to provide slides. The slides were scanned and divided into malignant and benign groups. We proposed two (a U-net segmentation and a DenseNet classification) networks to identify images. Another four classification networks were used for comparison tests. RESULTS: A total of 113 (42 malignant and 71 benign) endometrial samples were collected, and a dataset containing 15,913 images was constructed. A total of 39,000 ECCs patches were obtained by the segmentation network. Then, 26,880 and 11,520 patches were used for training and testing, respectively. On the premise that the training set reached 100%, the testing set gained 93.5% accuracy, 92.2% specificity, and 92.0% sensitivity. The remaining 600 malignant patches were used for verification. CONCLUSIONS: An artificial intelligence system was successfully built to classify malignant and benign ECCs.

Combining Radiology and Pathology for Automatic Glioma Classification.

Subtype classification is critical in the treatment of gliomas because different subtypes lead to different treatment options and postoperative care. Although many radiological- or histological-based glioma classification algorithms have been developed, most of them focus on single-modality data. In this paper, we propose an innovative two-stage model to classify gliomas into three subtypes (i.e., glioblastoma, oligodendroglioma, and astrocytoma) based on radiology and histology data. In the first stage, our model classifies each image as having glioblastoma or not. Based on the obtained non-glioblastoma images, the second stage aims to accurately distinguish astrocytoma and oligodendroglioma. The radiological images and histological images pass through the two-stage design with 3D and 2D models, respectively. Then, an ensemble classification network is designed to automatically integrate the features of the two modalities. We have verified our method by participating in the MICCAI 2020 CPM-RadPath Challenge and won 1st place. Our proposed model achieves high performance on the validation set with a balanced accuracy of 0.889, Cohen's Kappa of 0.903, and an F1-score of 0.943. Our model could advance multimodal-based glioma research and provide assistance to pathologists and neurologists in diagnosing glioma subtypes. The code has been publicly available online at https://github.com/Xiyue-Wang/1st-in-MICCAI2020-CPM.

A Computer-Aided Diagnosis System of Fetal Nucleated Red Blood Cells With Convolutional Neural Network.

CONTEXT.­: The rapid recognition of fetal nucleated red blood cells (fNRBCs) presents considerable challenges. OBJECTIVE.­: To establish a computer-aided diagnosis system for rapid recognition of fNRBCs by convolutional neural network. DESIGN.­: We adopted density gradient centrifugation and magnetic-activated cell sorting to extract fNRBCs from umbilical cord blood samples. The cell-block method was used to embed fNRBCs for routine formalin-fixed paraffin sectioning and hematoxylin-eosin staining. Then, we proposed a convolutional neural network-based, computer-aided diagnosis system to automatically discriminate features and recognize fNRBCs. Extracting methods of interested region were used to automatically segment individual cells in cell slices. The discriminant information from cellular-level regions of interest was encoded into a feature vector. Pathologic diagnoses were also provided by the network. RESULTS.­: In total, 4760 pictures of fNRBCs from 260 cell-slides of 4 umbilical cord blood samples were collected. On the premise of 100% accuracy in the training set (3720 pictures), the sensitivity, specificity, and accuracy of cellular intelligent recognition were 96.5%, 100%, and 98.5%, respectively, in the test set (1040 pictures). CONCLUSIONS.­: We established a computer-aided diagnosis system for effective and accurate fNRBC recognition based on a convolutional neural network.

Towards open-set touchless palmprint recognition via weight-based meta metric learning.

Touchless biometrics has become significant in the wake of novel coronavirus 2019 (COVID-19). Due to the convenience, user-friendly, and high-accuracy, touchless palmprint recognition shows great potential when the hygiene issues are considered during COVID-19. However, previous palmprint recognition methods are mainly focused on close-set scenario. In this paper, a novel Weight-based Meta Metric Learning (W2ML) method is proposed for accurate open-set touchless palmprint recognition, where only a part of categories is seen during training. Deep metric learning-based feature extractor is learned in a meta way to improve the generalization ability. Multiple sets are sampled randomly to define support and query sets, which are further combined into meta sets to constrain the set-based distances. Particularly, hard sample mining and weighting are adopted to select informative meta sets to improve the efficiency. Finally, embeddings with obvious inter-class and intra-class differences are obtained as features for palmprint identification and verification. Experiments are conducted on four palmprint benchmarks including fourteen constrained and unconstrained palmprint datasets. The results show that our W2ML method is more robust and efficient in dealing with open-set palmprint recognition issue as compared to the state-of-the-arts, where the accuracy is increased by up to 9.11% and the Equal Error Rate (EER) is decreased by up to 2.97%.

3D Dense Volumetric Network for Accurate Automated Pancreas Segmentation.

Pancreatic cancer poses a great threat to our health with an overall five-year survival rate of 8%. Automatic and accurate segmentation of pancreas plays an important and prerequisite role in computer-assisted diagnosis and treatment. Due to the ambiguous pancreas borders and intertwined surrounding tissues, it is a challenging task. In this paper, we propose a novel 3D Dense Volumetric Network (3D2VNet) to improve the segmentation accuracy of pancreas organ. Firstly, 3D fully convolutional architecture is applied to effectively incorporate the 3D pancreas and geometric cues for volume-to-volume segmentation. Then, dense connectivity is introduced to preserve the maximum information flow between layers and reduce the overfitting on limited training data. In addition, a auxiliary side path is constructed to help the gradient propagation to stabilize the training process. Adequate experiments are conducted on a challenging pancreas dataset in Medical Segmentation Decathlon challenge. The results demonstrate our method can outperform other comparison methods on the task of automated pancreas segmentation using limited data.Clinical relevance-This paper proposes an accurate automated pancreas segmentation method, which can provide assistance to clinicians in the diagnosis and treatment of pancreatic cancer.

Towards Cross-Dataset Palmprint Recognition Via Joint Pixel and Feature Alignment.

Deep learning-based palmprint recognition algorithms have shown great potential. Most of them are mainly focused on identifying samples from the same dataset. However, they may be not suitable for a more convenient case that the images for training and test are from different datasets, such as collected by embedded terminals and smartphones. Therefore, we propose a novel Joint Pixel and Feature Alignment (JPFA) framework for such cross-dataset palmprint recognition scenarios. Two-stage alignment is applied to obtain adaptive features in source and target datasets. 1) Deep style transfer model is adopted to convert source images into fake images to reduce the dataset gaps and perform data augmentation on pixel level. 2) A new deep domain adaptation model is proposed to extract adaptive features by aligning the dataset-specific distributions of target-source and target-fake pairs on feature level. Adequate experiments are conducted on several benchmarks including constrained and unconstrained palmprint databases. The results demonstrate that our JPFA outperforms other models to achieve the state-of-the-arts. Compared with baseline, the accuracy of cross-dataset identification is improved by up to 28.10% and the Equal Error Rate (EER) of cross-dataset verification is reduced by up to 4.69%. To make our results reproducible, the codes are publicly available at http://gr.xjtu.edu.cn/web/bell/resource.

A computational method for prediction of matrix proteins in endogenous retroviruses.

Human endogenous retroviruses (HERVs) encode active retroviral proteins, which may be involved in the progression of cancer and other diseases. Matrix protein (MA), in group-specific antigen genes (gag) of retroviruses, is associated with the virus envelope glycoproteins in most mammalian retroviruses and may be involved in virus particle assembly, transport and budding. However, the amount of annotated MAs in ERVs is still at a low level so far. No computational method to predict the exact start and end coordinates of MAs in gags has been proposed yet. In this paper, a computational method to identify MAs in ERVs is proposed. A divide and conquer technique was designed and applied to the conventional prediction model to acquire better results when dealing with gene sequences with various lengths. Initiation sites and termination sites were predicted separately and then combined according to their intervals. Three different algorithms were applied and compared: weighted support vector machine (WSVM), weighted extreme learning machine (WELM) and random forest (RF). G - mean (geometric mean of sensitivity and specificity) values of initiation sites and termination sites under 5-fold cross validation generated by random forest models are 0.9869 and 0.9755 respectively, highest among the algorithms applied. Our prediction models combine RF & WSVM algorithms to achieve the best prediction results. 98.4% of all the collected ERV sequences with complete MAs (125 in total) could be predicted exactly correct by the models. 94,671 HERV sequences from 118 families were scanned by the model, 104 new putative MAs were predicted in human chromosomes. Distributions of the putative MAs and optimizations of model parameters were also analyzed. The usage of our predicting method was also expanded to other retroviruses and satisfying results were acquired.

A computational model for predicting integrase catalytic domain of retrovirus.

Integrase catalytic domain (ICD) is an essential part in the retrovirus for integration reaction, which enables its newly synthesized DNA to be incorporated into the DNA of infected cells. Owing to the crucial role of ICD for the retroviral replication and the absence of an equivalent of integrase in host cells, it is comprehensible that ICD is a promising drug target for therapeutic intervention. However, annotated ICDs in UniProtKB database have still been insufficient for a good understanding of their statistical characteristics so far. Accordingly, it is of great importance to put forward a computational ICD model in this work to annotate these domains in the retroviruses. The proposed model then discovered 11,660 new putative ICDs after scanning sequences without ICD annotations. Subsequently in order to provide much confidence in ICD prediction, it was tested under different cross-validation methods, compared with other database search tools, and verified on independent datasets. Furthermore, an evolutionary analysis performed on the annotated ICDs of retroviruses revealed a tight connection between ICD and retroviral classification. All the datasets involved in this paper and the application software tool of this model can be available for free download at https://sourceforge.net/projects/icdtool/files/?source=navbar.

A novel method for in silico identification of regulatory SNPs in human genome.

Regulatory single nucleotide polymorphisms (rSNPs), kind of functional noncoding genetic variants, can affect gene expression in a regulatory way, and they are thought to be associated with increased susceptibilities to complex diseases. Here a novel computational approach to identify potential rSNPs is presented. Different from most other rSNPs finding methods which based on hypothesis that SNPs causing large allele-specific changes in transcription factor binding affinities are more likely to play regulatory functions, we use a set of documented experimentally verified rSNPs and nonfunctional background SNPs to train classifiers, so the discriminating features are found. To characterize variants, an extensive range of characteristics, such as sequence context, DNA structure and evolutionary conservation etc. are analyzed. Support vector machine is adopted to build the classifier model together with an ensemble method to deal with unbalanced data. 10-fold cross-validation result shows that our method can achieve accuracy with sensitivity of ~78% and specificity of ~82%. Furthermore, our method performances better than some other algorithms based on aforementioned hypothesis in handling false positives. The original data and the source matlab codes involved are available at https://sourceforge.net/projects/rsnppredict/.

A Bevel Gear Quality Inspection System Based on Multi-Camera Vision Technology.

Surface defect detection and dimension measurement of automotive bevel gears by manual inspection are costly, inefficient, low speed and low accuracy. In order to solve these problems, a synthetic bevel gear quality inspection system based on multi-camera vision technology is developed. The system can detect surface defects and measure gear dimensions simultaneously. Three efficient algorithms named Neighborhood Average Difference (NAD), Circle Approximation Method (CAM) and Fast Rotation-Position (FRP) are proposed. The system can detect knock damage, cracks, scratches, dents, gibbosity or repeated cutting of the spline, etc. The smallest detectable defect is 0.4 mm × 0.4 mm and the precision of dimension measurement is about 40-50 µm. One inspection process takes no more than 1.3 s. Both precision and speed meet the requirements of real-time online inspection in bevel gear production.

CarSPred: a computational tool for predicting carbonylation sites of human proteins.

Protein carbonylation is one of the most pervasive oxidative stress-induced post-translational modifications (PTMs), which plays a significant role in the etiology and progression of several human diseases. It has been regarded as a biomarker of oxidative stress due to its relatively early formation and stability compared with other oxidative PTMs. Only a subset of proteins is prone to carbonylation and most carbonyl groups are formed from lysine (K), arginine (R), threonine (T) and proline (P) residues. Recent advancements in analysis of the PTM by mass spectrometry provided new insights into the mechanisms of protein carbonylation, such as protein susceptibility and exact modification sites. However, the experimental approaches to identifying carbonylation sites are costly, time-consuming and capable of processing a limited number of proteins, and there is no bioinformatics method or tool devoted to predicting carbonylation sites of human proteins so far. In the paper, a computational method is proposed to identify carbonylation sites of human proteins. The method extracted four kinds of features and combined the minimum Redundancy Maximum Relevance (mRMR) feature selection criterion with weighted support vector machine (WSVM) to achieve total accuracies of 85.72%, 85.95%, 83.92% and 85.72% for K, R, T and P carbonylation site predictions respectively using 10-fold cross-validation. The final optimal feature sets were analysed, the position-specific composition and hydrophobicity environment of flanking residues of modification sites were discussed. In addition, a software tool named CarSPred has been developed to facilitate the application of the method. Datasets and the software involved in the paper are available at https://sourceforge.net/projects/hqlstudio/files/CarSPred-1.0/.

A practical application combining wireless sensor networks and Internet of Things: Safety Management System for Tower Crane Groups.

The so-called Internet of Things (IoT) has attracted increasing attention in the field of computer and information science. In this paper, a specific application of IoT, named Safety Management System for Tower Crane Groups (SMS-TC), is proposed for use in the construction industry field. The operating status of each tower crane was detected by a set of customized sensors, including horizontal and vertical position sensors for the trolley, angle sensors for the jib and load, tilt and wind speed sensors for the tower body. The sensor data is collected and processed by the Tower Crane Safety Terminal Equipment (TC-STE) installed in the driver's operating room. Wireless communication between each TC-STE and the Local Monitoring Terminal (LMT) at the ground worksite were fulfilled through a Zigbee wireless network. LMT can share the status information of the whole group with each TC-STE, while the LMT records the real-time data and reports it to the Remote Supervision Platform (RSP) through General Packet Radio Service (GPRS). Based on the global status data of the whole group, an anti-collision algorithm was executed in each TC-STE to ensure the safety of each tower crane during construction. Remote supervision can be fulfilled using our client software installed on a personal computer (PC) or smartphone. SMS-TC could be considered as a promising practical application that combines a Wireless Sensor Network with the Internet of Things.

Analysis of interleukin-8 gene variants reveals their relative importance as genetic susceptibility factors for chronic periodontitis in the Han population.

Interleukin (IL)-8, an important chemokine that regulates the inflammatory response, plays an important role in periodontitis. Previous studies indicate that certain IL-8 gene polymorphisms are associated with periodontitis susceptibility in some populations. However, the literature is somewhat contradictory, and not all IL-8 polymorphisms have been examined, particularly in Han Chinese individuals. The aim of this study was to investigate the association of every IL-8 SNP with chronic periodontitis in Han Chinese individuals. We analyzed 23 SNPs with minor allele frequency (MAF)≥0.01, which were selected from 219 SNPs in the NCBI dbSNP and preliminary HapMap data analyses from a cohort of 400 cases and 750 controls from genetically independent Han Chinese individuals. Single SNP, haplotype and gender-specific associations were performed. We found that rs4073 and rs2227307 were significantly associated with chronic periodontitis. Further haplotype analysis indicated that a haplotype block (rs4073-rs2227307-rs2227306) that spans the promoter and exon1 of IL-8 was highly associated with chronic periodontitis. Additionally, the ATC haplotype in this block was increased 1.5-fold in these cases. However, when analyzing the samples by gender, no significant gender-specific associations in IL-8 were observed, similar to the results of haplotype association analyses in female and male subgroups. Our results provide further evidence that IL-8 is associated with chronic periodontitis in Han Chinese individuals. Furthermore, our results confirm previous reports suggesting the intriguing possibilities that IL-8 plays a role in the pathogenesis of chronic periodontitis and that this gene may be involved in the etiology of this condition.

Genome-wide identification and predictive modeling of lincRNAs polyadenylation in cancer genome.

Long noncoding RNAs (lncRNAs) play essential regulatory roles in the human cancer genome. Many identified lncRNAs are transcribed by RNA polymerase II in which they are polyadenylated, whereby the long intervening noncoding RNAs (lincRNAs) have been widely used for the researches of lncRNAs. To date, the mechanism of lincRNAs polyadenylation related to cancer is rarely fully understood yet. In this paper, first we reported a comprehensive map of global lincRNAs polyadenylation sites (PASs) in five human cancer genomes; second we proposed a grouping method based on the pattern of genes expression and the manner of alternative polyadenylation (APA); third we investigated the distribution of motifs surrounding PASs. Our analysis reveals that about 70% of PASs are located in the sense strand of lincRNAs. Also more than 90% PASs in the antisense strand of lincRNAs are located in the intron regions. In addition, around 40% of lincRNA genes with PASs has APA sites. Four obvious motifs i.e., AATAAA, TTTTTTTT, CCAGSCTGG, and RGYRYRGTGG were detected in the sequences surrounding PASs in the normal and cancer tissues. Furthermore, a novel algorithm was proposed to recognize the lincRNAs PASs of tumor tissues based on support vector machine (SVM). The algorithm can achieve the accuracies up to 96.55% and 89.48% for identification the tumor lincRNAs PASs from the non-polyadenylation sites and the non-lincRNA PASs, respectively.

ISDTool 2.0: a computational model for predicting immunosuppressive domain of retroviruses.

Immunosuppressive domain (ISD) is a conserved region of transmembrane proteins (TM) in envelope gene (env) of retroviruses. in vitro and vivo, a synthetic peptide (CKS-17) that shows homology to ISD inhibits immune function. Evidence has shown that ISD suppresses lymphocyte proliferation and allows escape from immune effectors of the innate and adaptive arms in mouse immune system. Previously, we have developed a tool ISDTool 1.0 to identify ISD of human endogenous retrovirus (HERV). However, several other important retroviruses exist and no method is devoted to ISD prediction of them so far. In the paper, a computational model is proposed to identify ISD of six typical retroviruses from three species. The model combines the minimum Redundancy Maximum Relevance (mRMR) feature selection criterion with weighted extreme learning machine (WELM) to achieve high identification accuracies of 98.95%, 96.34% and 96.87% using self-consistency, 5-fold and 10-fold cross-validation, respectively. A software tool named ISDTool 2.0 has been developed to facilitate the application of the model and a large number of new putative ISDs of the six retroviruses were predicted. In addition, motifs of ISD in these retroviruses were analyzed and the evolutionary relationship was discussed. Datasets and the software involved in the paper are available at http://sourceforge.net/projects/isdtool/files/ISDTool-2.0/.

ISDTool: a computational model for predicting immunosuppressive domain of HERVs.

Human endogenous retroviruses (HERVs) have been found to act as etiological cofactors in several chronic diseases, including cancer, autoimmunity and neurological dysfunction. Immunosuppressive domain (ISD) is a conserved region of transmembrane protein (TM) in envelope gene (env) of retroviruses. In vitro and vivo, evidence has shown that retroviral TM is highly immunosuppressive and a synthetic peptide (CKS-17) that shows homology to ISD inhibits immune function. ISD is probably a potential pathogenic element in HERVs. However, only less than one hundred ISDs of HERVs have been annotated by researchers so far, and universal software for domain prediction could not achieve sufficient accuracy for specific ISD. In this paper, a computational model is proposed to identify ISD in HERVs based on genome sequences only. It has a classification accuracy of 97.9% using Jack-knife test. 117 HERVs families were scanned with the model, 1002 new putative ISDs have been predicted and annotated in the human chromosomes. This model is also applicable to search for ISDs in human T-lymphotropic virus (HTLV), simian T-lymphotropic virus (STLV) and murine leukemia virus (MLV) because of the evolutionary relationship between endogenous and exogenous retroviruses. Furthermore, software named ISDTool has been developed to facilitate the application of the model. Datasets and the software involved in the paper are all available at https://sourceforge.net/projects/isdtool/files/ISDTool-1.0.

Analysis of selective constraints on mitochondrial DNA, flight ability and physiological index on avian.

For most of the birds in the word, they can be divided into two main groups, i.e. resident birds and migratory ones. Most of the energy required for long-distance migration is supplied by mitochondria via oxidative phosphorylation. Therefore, the evolutionary constraints acted on the mitochondria DNA (mtDNA) are considered to vary with the locomotive abilities and flight speed. The flight speed is assumed to increase with mass and wing loading according to the fundamental aerodynamic theories, which is common between aves and aircrafts. We compared 148 avian mitochondrial genomes and main physiological parameters. More nonsynonymous nucleotide substitutions than synonymous ones are accumulated in low-speed and flightless birds rather than high-speed flying birds. No matter how the speed is obtained, directly measured or estimated through physiological index. Our results demonstrated that, besides artificial and environmental factors, selective constraints relevant to flight ability play an essential role in the evolution of mtDNA, even it might cause the extinction of avian species.

A hybrid model for the prediction of mRNA polyadenylation signals.

The mRNA polyadenylation is the cellular process that adds adenosine tails to mature mRNAs. Malfunction of polyadenylation has been implicated in several human diseases. In this paper, we proposed a novel feature extraction approach which employs the K-gram nucleotide acid pattern, the position weight matrix (PWM) and the increment of diversity (ID) to represent the original features. Then Principle Component Analysis (PCA) was applied to transform the original features into a new feature space where the low-dimensional features were used to train the real-coded genetic neural network model. In the experiments, our proposed algorithm (GA-BP) can achieve the accuracy about 82.98%, specificity 82.95% and sensitivity 83.01% in the specific dataset constructed by Kalkatawi. The results demonstrate that GA-BP is a promising algorithm for the prediction of mRNA polyadenylation signals.

Fingerprint identification using SIFT-based minutia descriptors and improved all descriptor-pair matching.

The performance of conventional minutiae-based fingerprint authentication algorithms degrades significantly when dealing with low quality fingerprints with lots of cuts or scratches. A similar degradation of the minutiae-based algorithms is observed when small overlapping areas appear because of the quite narrow width of the sensors. Based on the detection of minutiae, Scale Invariant Feature Transformation (SIFT) descriptors are employed to fulfill verification tasks in the above difficult scenarios. However, the original SIFT algorithm is not suitable for fingerprint because of: (1) the similar patterns of parallel ridges; and (2) high computational resource consumption. To enhance the efficiency and effectiveness of the algorithm for fingerprint verification, we propose a SIFT-based Minutia Descriptor (SMD) to improve the SIFT algorithm through image processing, descriptor extraction and matcher. A two-step fast matcher, named improved All Descriptor-Pair Matching (iADM), is also proposed to implement the 1:N verifications in real-time. Fingerprint Identification using SMD and iADM (FISiA) achieved a significant improvement with respect to accuracy in representative databases compared with the conventional minutiae-based method. The speed of FISiA also can meet real-time requirements.