Massey Research Online - Browsing by Author "Liu B"

Browsing by Author "Liu B"

Now showing 1 - 15 of 15

A multi-label classification model for full slice brain computerised tomography image
(BioMed Central Ltd, 2020-11-18) Li J; Fu G; Chen Y; Li P; Liu B; Pei Y; Feng H
BACKGROUND: Screening of the brain computerised tomography (CT) images is a primary method currently used for initial detection of patients with brain trauma or other conditions. In recent years, deep learning technique has shown remarkable advantages in the clinical practice. Researchers have attempted to use deep learning methods to detect brain diseases from CT images. Methods often used to detect diseases choose images with visible lesions from full-slice brain CT scans, which need to be labelled by doctors. This is an inaccurate method because doctors detect brain disease from a full sequence scan of CT images and one patient may have multiple concurrent conditions in practice. The method cannot take into account the dependencies between the slices and the causal relationships among various brain diseases. Moreover, labelling images slice by slice spends much time and expense. Detecting multiple diseases from full slice brain CT images is, therefore, an important research subject with practical implications. RESULTS: In this paper, we propose a model called the slice dependencies learning model (SDLM). It learns image features from a series of variable length brain CT images and slice dependencies between different slices in a set of images to predict abnormalities. The model is necessary to only label the disease reflected in the full-slice brain scan. We use the CQ500 dataset to evaluate our proposed model, which contains 1194 full sets of CT scans from a total of 491 subjects. Each set of data from one subject contains scans with one to eight different slice thicknesses and various diseases that are captured in a range of 30 to 396 slices in a set. The evaluation results present that the precision is 67.57%, the recall is 61.04%, the F1 score is 0.6412, and the areas under the receiver operating characteristic curves (AUCs) is 0.8934. CONCLUSION: The proposed model is a new architecture that uses a full-slice brain CT scan for multi-label classification, unlike the traditional methods which only classify the brain images at the slice level. It has great potential for application to multi-label detection problems, especially with regard to the brain CT images.
Achieving Carbon Neutrality – The Role of Heterogeneous Environmental Regulations on Urban Green Innovation
(Frontiers Media S.A., 2022-06-09) Liu B; Wang J; Li RYM; Peng L; Mi L; Kirikkaleli D
This article examines the impact of heterogeneous environmental regulations on urban green innovation using panel data from 285 prefecture-level cities in mainland China from 2008 to 2019. From the perspective of green patents, this article utilizes a two-way fixed-effect model and the mediation effect model to examine the mechanism of the impact of heterogeneous environmental regulations on urban green innovation in China. Results show that the urban green innovation development in China is relatively slow and can be easily influenced by national policies. More specifically, the relationship between the command-based environmental regulation and urban green innovation presents an inverted non-linear U-shaped model, whereas the relationship between the market-based and voluntary environmental regulation presents a positive U-shaped model. Further investigation of this mechanism concludes that the progression of regional green innovation is primarily accelerated by technological development, effective energy allocation, and industrial structural upgrading. However, the implementation of relevant environmental regulations varies, resulting in various green innovation progression rates. Therefore, in order to achieve the carbon neutrality goal that China proposes, the effectiveness of environmental regulation implementation should be improved. Moreover, the development of various environmental regulation tools should be better coordinated.
An Investigation about Gene Modules Associated with hDPSC Differentiation for Adolescents
(Hindawi Limited, 2019-04-04) Xu W; Li J; Li J; Yang J-J; Wang Q; Liu B; Qiu W; Ballini A
Dental pulp stem cells (DPSCs) have the property of self-renewal and multidirectional differentiation so that they have the potential for future regenerative therapy of various diseases. The latest breakthrough in the biology of stem cells and the development of regenerative biology provides an effective strategy for regenerative therapy. However, in the medium promoting differentiation during long-term passage, DPSCs would lose their differentiation capability. Some efforts have been made to find genes influencing human DPSC (hDPSC) differentiation based on hDPSCs isolated from adults. However, hDPSC differentiation is a very complex process, which involves multiple genes and multielement interactions. The purpose of this study is to detect sets of correlated genes (i.e., gene modules) that are associated to hDPSC differentiation at the crown-completed stage of the third molars, by using weighted gene coexpression network analysis (WGCNA). Based on the gene expression dataset GSE10444 from Gene Expression Omnibus (GEO), we identified two significant gene modules: yellow module (742 genes) and salmon module (9 genes). The WEB-based Gene SeT AnaLysis Toolkit showed that the 742 genes in the yellow module were enriched in 59 KEGG pathways (including Wnt signaling pathway), while the 9 genes in the salmon module were enriched in one KEGG pathway (neurotrophin signaling pathway). There were 660 (7) genes upregulated at P10 and 82 (2) genes downregulated at P10 in the yellow (salmon) module. Our results provide new insights into the differentiation capability of hDPSCs.
Cascaded Segmented Matting Network for Human Matting
(IEEE, 2021-11-04) Liu B; Jing H; Qu G; Guesgen HW; Raval MS
Human matting, high quality extraction of humans from natural images, is crucial for a wide variety of applications such as virtual reality, augmented reality, entertainment and so on. Since the matting problem is an ill-posed problem, most previous methods rely on extra user inputs such as trimap or scribbles as guidance to estimate alpha value for the pixels that are in the unknown region of the trimap. This phenomenon makes it difficult to be applied to large scale data. In order to solve these problems, we studied the unique role of semantics and details in image matting, and decomposed the matting task into two sub-tasks: trimap segmentation based on high-level semantic information and alpha regression based on low-level detailed information. Specifically, we proposed a novel Cascaded Segmented Matting Network (CSMNet), which uses a shared encoder and two separate decoders to learn these two tasks in a collaborative way to achieve the end-to-end human image matting. In addition, we established a large-scale dataset with 14,000 fine-labeled human matting images. A background dataset is also built to simulate real pictures. Comprehensive empirical studies on above datasets demonstrate that CSMNet could produce a stable and accurate alpha matte without the input of trimap and achieve an evaluation value that is comparable to the algorithm that requires trimap.
Comparison of algorithms for road surface temperature prediction
(Emerald Publishing Limited, 2018-12-13) Liu B; Shen L; You H; Dong Y; Li J; Li Y
Purpose: The influence of road surface temperature (RST) on vehicles is becoming more and more obvious. Accurate predication of RST is distinctly meaningful. At present, however, the prediction accuracy of RST is not satisfied with physical methods or statistical learning methods. To find an effective prediction method, this paper selects five representative algorithms to predict the road surface temperature separately. Design/methodology/approach: Multiple linear regressions, least absolute shrinkage and selection operator, random forest and gradient boosting regression tree (GBRT) and neural network are chosen to be representative predictors. Findings: The experimental results show that for temperature data set of this experiment, the prediction effect of GBRT in the ensemble algorithm is the best compared with the other four algorithms. Originality/value: This paper compares different kinds of machine learning algorithms, observes the road surface temperature data from different angles, and finds the most suitable prediction method.
DeepCAC: a deep learning approach on DNA transcription factors classification based on multi-head self-attention and concatenate convolutional neural network
(BioMed Central Ltd, 2023-09-18) Zhang J; Liu B; Wu J; Wang Z; Li J
Understanding gene expression processes necessitates the accurate classification and identification of transcription factors, which is supported by high-throughput sequencing technologies. However, these techniques suffer from inherent limitations such as time consumption and high costs. To address these challenges, the field of bioinformatics has increasingly turned to deep learning technologies for analyzing gene sequences. Nevertheless, the pursuit of improved experimental results has led to the inclusion of numerous complex analysis function modules, resulting in models with a growing number of parameters. To overcome these limitations, it is proposed a novel approach for analyzing DNA transcription factor sequences, which is named as DeepCAC. This method leverages deep convolutional neural networks with a multi-head self-attention mechanism. By employing convolutional neural networks, it can effectively capture local hidden features in the sequences. Simultaneously, the multi-head self-attention mechanism enhances the identification of hidden features with long-distant dependencies. This approach reduces the overall number of parameters in the model while harnessing the computational power of sequence data from multi-head self-attention. Through training with labeled data, experiments demonstrate that this approach significantly improves performance while requiring fewer parameters compared to existing methods. Additionally, the effectiveness of our approach is validated in accurately predicting DNA transcription factor sequences.
DeepPN: a deep parallel neural network based on convolutional neural network and graph convolutional network for predicting RNA-protein binding sites.
(29/06/2022) Zhang J; Liu B; Wang Z; Lehnert K; Gahegan M
BACKGROUND: Addressing the laborious nature of traditional biological experiments by using an efficient computational approach to analyze RNA-binding proteins (RBPs) binding sites has always been a challenging task. RBPs play a vital role in post-transcriptional control. Identification of RBPs binding sites is a key step for the anatomy of the essential mechanism of gene regulation by controlling splicing, stability, localization and translation. Traditional methods for detecting RBPs binding sites are time-consuming and computationally-intensive. Recently, the computational method has been incorporated in researches of RBPs. Nevertheless, lots of them not only rely on the sequence data of RNA but also need additional data, for example the secondary structural data of RNA, to improve the performance of prediction, which needs the pre-work to prepare the learnable representation of structural data. RESULTS: To reduce the dependency of those pre-work, in this paper, we introduce DeepPN, a deep parallel neural network that is constructed with a convolutional neural network (CNN) and graph convolutional network (GCN) for detecting RBPs binding sites. It includes a two-layer CNN and GCN in parallel to extract the hidden features, followed by a fully connected layer to make the prediction. DeepPN discriminates the RBP binding sites on learnable representation of RNA sequences, which only uses the sequence data without using other data, for example the secondary or tertiary structure data of RNA. DeepPN is evaluated on 24 datasets of RBPs binding sites with other state-of-the-art methods. The results show that the performance of DeepPN is comparable to the published methods. CONCLUSION: The experimental results show that DeepPN can effectively capture potential hidden features in RBPs and use these features for effective prediction of binding sites.
DeepSIM: a novel deep learning method for graph similarity computation
(Springer-Verlag GmbH, 2024-01) Liu B; Wang Z; Zhang J; Wu J; Qu G
Abstract: Graphs are widely used to model real-life information, where graph similarity computation is one of the most significant applications, such as inferring the properties of a compound based on similarity to a known group. Definition methods (e.g., graph edit distance and maximum common subgraph) have extremely high computational cost, and the existing efficient deep learning methods suffer from the problem of inadequate feature extraction which would have a bad effect on similarity computation. In this paper, a double-branch model called DeepSIM was raised to deeply mine graph-level and node-level features to address the above problems. On the graph-level branch, a novel embedding relational reasoning network was presented to obtain interaction between pairwise inputs. Meanwhile, a new local-to-global attention mechanism is designed to improve the capability of CNN-based node-level feature extraction module on another path. In DeepSIM, double-branch outputs will be concatenated as the final feature. The experimental results demonstrate that our methods perform well on several datasets compared to the state-of-the-art deep learning models in related fields.
DiffusionDCI: A Novel Diffusion-Based Unified Framework for Dynamic Full-Field OCT Image Generation and Segmentation
(IEEE Access, 2024) Yang B; Li J; Wang J; Li R; Gu K; Liu B; Militello C
Rapid and accurate identification of cancerous areas during surgery is crucial for guiding surgical procedures and reducing postoperative recurrence rates. Dynamic Cell Imaging (DCI) has emerged as a promising alternative to traditional frozen section pathology, offering high-resolution displays of tissue structures and cellular characteristics. However, challenges persist in segmenting DCI images using deep learning methods, such as color variation and artifacts between patches in whole slide DCI images, and the difficulty in obtaining precise annotated data. In this paper, we introduce a novel two-stage framework for DCI image generation and segmentation. Initially, the Dual Semantic Diffusion Model (DSDM) is specifically designed to generate high-quality and semantically relevant DCI images. These images not only serve as an effective means of data augmentation to assist downstream segmentation tasks but also help in reducing the reliance on expensive and hard-to-obtain large annotated medical image datasets. Furthermore, we reuse the pretrained DSDM to extract diffusion features, which are then infused into the segmentation network via a cross-attention alignment module. This approach enables our network to capture and utilize the characteristics of DCI images more effectively, thereby significantly enhancing segmentation results. Our method was validated on the DCI dataset and compared with other methods for image generation and segmentation. Experimental results demonstrate that our method achieves superior performance in both tasks, proving the effectiveness of the proposed model.
Discrete Random Renewable Replacements after the Expiration of Collaborative Preventive Maintenance Warranty
(MDPI (Basel, Switzerland), 2024-09-13) Chen H; Chen J; Lai Y; Yu X; Shang L; Peng R; Liu B; Ferreira MAM
With advanced digital technologies as the key support, many scholars and researchers have proposed various random warranty models by integrating mission cycles into the warranty stage. However, these existing warranty models are designed only from the manufacturer’s subjective perspective, ignoring certain consumer requirements. For instance, they overlook a wide range of warranty coverage, the pursuit of reliability improvement rather than mere minimal repair, and the need to limit the delay in repair. To address these consumer requirements, this paper proposes a novel random collaborative preventive maintenance warranty with repair-time threshold (RCPMW-RTT). This model incorporates terms that are jointly designed by manufacturers and consumers to meet specific consumer needs, thereby overcoming the limitations of existing warranty models. The introduction of a repair-time threshold aims to limit the time delay in repairing failures and to compensate for any losses incurred by consumers. Using probability theory, the RCPMW-RTT is evaluated in terms of cost and time, and relevant variants are derived by analyzing key parameters. As an exemplary representation of the RCPMW-RTT, two random replacement policies named the discrete random renewable back replacement (DRRBR) and the discrete random renewable front replacement (DRRFR) are proposed and modelled to ensure reliability after the expiration of the RCPMW-RTT. In both policies, product replacement is triggered either by the occurrence of the first extreme mission cycle or by reaching the limit on the number of non-extreme mission cycles, whichever comes first. Probability theory is used to present cost rates for both policies in order to determine optimal values for decision variables. Finally, numerical analysis is performed on the RCPMW-RTT to reveal hidden variation tendencies and mechanisms; numerical analysis is also performed on the DRRBR and the DRRFR. The numerical results show that the proposed random replacement policies are feasible and unique; the replacement time within the post-warranty coverage increases as the maintenance quality improves and the cost rate can be reduced by setting a smaller repair-time threshold.
DL-PPI: a method on prediction of sequenced protein-protein interaction based on deep learning
(BioMed Central Ltd, 2023-12) Wu J; Liu B; Zhang J; Wang Z; Li J
PURPOSE: Sequenced Protein-Protein Interaction (PPI) prediction represents a pivotal area of study in biology, playing a crucial role in elucidating the mechanistic underpinnings of diseases and facilitating the design of novel therapeutic interventions. Conventional methods for extracting features through experimental processes have proven to be both costly and exceedingly complex. In light of these challenges, the scientific community has turned to computational approaches, particularly those grounded in deep learning methodologies. Despite the progress achieved by current deep learning technologies, their effectiveness diminishes when applied to larger, unfamiliar datasets. RESULTS: In this study, the paper introduces a novel deep learning framework, termed DL-PPI, for predicting PPIs based on sequence data. The proposed framework comprises two key components aimed at improving the accuracy of feature extraction from individual protein sequences and capturing relationships between proteins in unfamiliar datasets. 1. Protein Node Feature Extraction Module: To enhance the accuracy of feature extraction from individual protein sequences and facilitate the understanding of relationships between proteins in unknown datasets, the paper devised a novel protein node feature extraction module utilizing the Inception method. This module efficiently captures relevant patterns and representations within protein sequences, enabling more informative feature extraction. 2. Feature-Relational Reasoning Network (FRN): In the Global Feature Extraction module of our model, the paper developed a novel FRN that leveraged Graph Neural Networks to determine interactions between pairs of input proteins. The FRN effectively captures the underlying relational information between proteins, contributing to improved PPI predictions. DL-PPI framework demonstrates state-of-the-art performance in the realm of sequence-based PPI prediction.
Effects of pedagogical intervention on Chinese EFL learners' use of motivational regulation strategies and oral English proficiency improvement.
(Elsevier B.V., 2024-10-01) Yan R; Liu B; Zhang LJ
This study investigated the role of motivational regulation strategies (MRSs) in English as a foreign language (EFL) pedagogy, with a focus on Chinese university students. While prior research has explored MRSs, their specific impact on the oral proficiency of Chinese EFL learners remains under-examined. This mixed-methods research offers empirical insights, advocating for the integration of MRSs into EFL instruction to bolster students' oral proficiency. The study is bifurcated, with the first phase dedicated to cataloging MRSs' usage among Chinese university students and crafting the Speaking Strategies for Motivational Regulation Questionnaire (SSMRQ). This initial phase engaged 171 EFL students from a northern Chinese "211 project" university, employing convenience sampling. Factor analysis of participant responses culminated in a 15-item SSMRQ, spanning five dimensions: Environment Structuring (ES), Mastery Self-Talk (MST), Self-Consequating (SC), Self-Oriented Performance Self-Talk (SPST), and Externally-Oriented Performance Self-Talk (EPST). The second phase assessed the efficacy of MRSs-oriented instruction on student application of MRSs and oral English proficiency. This quasi-experimental study involved 22 consenting second-year English majors from the participating university. Data collection instruments encompassed the SSMRQ, oral English proficiency tasks, reflective journals, and semi-structured interviews. The instructional intervention spanned four weekly 30-min sessions, targeting the five MRSs' dimensions and offering feedback on oral performance. Assessments were conducted pre- and post-intervention using the SSMRQ, oral tasks, and reflective journals. Six participants, selected based on their oral English performance, were interviewed in-depth. Results suggest that the instructional intervention had a significant effect on the students' use of MRSs and their oral English proficiency. The study offers pedagogical insights into EFL speaking instruction in the higher education context, underscoring the importance of personalized teaching strategies tailored to individual learner needs. Collectively, this research introduces the SSMRQ and elucidates the pedagogical merits of MRSs-based instruction on oral English proficiency, establishing an empirical base for subsequent inquiry and pedagogical advancement in language education.
Efficient Monocular Human Pose Estimation Based on Deep Learning Methods: A Survey
(IEEE, 2024-05-09) Yan X; Liu B; Qu G
Human pose estimation (HPE) is a crucial computer vision task with a wide range of applications in sports medicine, healthcare, virtual reality, and human-computer interaction. The demand for real-time HPE solutions necessitates the development of efficient deep-learning models that can be deployed on resource-constrained devices. While a few surveys exist in this area, none delve deeply into the critical intersection of efficiency and performance. This survey reviews the state-of-the-art efficient deep learning approaches for real-time HPE, focusing on strategies for improving efficiency without compromising accuracy. We discuss popular backbone networks for HPE, model compression techniques, network pruning and quantization, knowledge distillation, and neural architecture search methods. Furthermore, we critically analyze the existing works, highlighting their strengths, weaknesses, and applicability to different scenarios. We also present an overview of the evaluation datasets, metrics, and design for efficient HPE. Finally, we identify research gaps and challenges in the field, providing insights and recommendations for future research directions in developing efficient and scalable HPE solutions.
Integrative analysis identifies two molecular and clinical subsets in Luminal B breast cancer
(Elsevier Inc, 2023-09-15) Wang H; Liu B; Long J; Yu J; Ji X; Li J; Zhu N; Zhuang X; Li L; Chen Y; Liu Z; Wang S; Zhao S
Comprehensive multiplatform analysis of Luminal B breast cancer (LBBC) specimens identifies two molecularly distinct, clinically relevant subtypes: Cluster A associated with cell cycle and metabolic signaling and Cluster B with predominant epithelial mesenchymal transition (EMT) and immune response pathways. Whole-exome sequencing identified significantly mutated genes including TP53, PIK3CA, ERBB2, and GATA3 with recurrent somatic mutations. Alterations in DNA methylation or transcriptomic regulation in genes (FN1, ESR1, CCND1, and YAP1) result in tumor microenvironment reprogramming. Integrated analysis revealed enriched biological pathways and unexplored druggable targets (cancer-testis antigens, metabolic enzymes, kinases, and transcription regulators). A systematic comparison between mRNA and protein displayed emerging expression patterns of key therapeutic targets (CD274, YAP1, AKT1, and CDH1). A potential ceRNA network was developed with a significantly different prognosis between the two subtypes. This integrated analysis reveals a complex molecular landscape of LBBC and provides the utility of targets and signaling pathways for precision medicine.
Potential rapid intraoperative cancer diagnosis using dynamic full-field optical coherence tomography and deep learning: A prospective cohort study in breast cancer patients
(Elsevier B V on behalf of the Science China Press, 2024-06-15) Zhang S; Yang B; Yang H; Zhao J; Zhang Y; Gao Y; Monteiro O; Zhang K; Liu B; Wang S
An intraoperative diagnosis is critical for precise cancer surgery. However, traditional intraoperative assessments based on hematoxylin and eosin (H&E) histology, such as frozen section, are time-, resource-, and labor-intensive, and involve specimen-consuming concerns. Here, we report a near-real-time automated cancer diagnosis workflow for breast cancer that combines dynamic full-field optical coherence tomography (D-FFOCT), a label-free optical imaging method, and deep learning for bedside tumor diagnosis during surgery. To classify the benign and malignant breast tissues, we conducted a prospective cohort trial. In the modeling group (n = 182), D-FFOCT images were captured from April 26 to June 20, 2018, encompassing 48 benign lesions, 114 invasive ductal carcinoma (IDC), 10 invasive lobular carcinoma, 4 ductal carcinoma in situ (DCIS), and 6 rare tumors. Deep learning model was built up and fine-tuned in 10,357 D-FFOCT patches. Subsequently, from June 22 to August 17, 2018, independent tests (n = 42) were conducted on 10 benign lesions, 29 IDC, 1 DCIS, and 2 rare tumors. The model yielded excellent performance, with an accuracy of 97.62%, sensitivity of 96.88% and specificity of 100%; only one IDC was misclassified. Meanwhile, the acquisition of the D-FFOCT images was non-destructive and did not require any tissue preparation or staining procedures. In the simulated intraoperative margin evaluation procedure, the time required for our novel workflow (approximately 3 min) was significantly shorter than that required for traditional procedures (approximately 30 min). These findings indicate that the combination of D-FFOCT and deep learning algorithms can streamline intraoperative cancer diagnosis independently of traditional pathology laboratory procedures.

Browsing by Author "Liu B"

Results Per Page

Sort Options