Article
Computer Science, Information Systems
Mohammad A. Alzubaidi, Mwaffaq Otoom, Hamza Jaradat
Summary: This study proposed a comprehensive global and local feature extraction framework for lung cancer detection using a set of 1000 CT scan images. Different image feature types were used to build detection models in the global phase, and local blocks with extracted features from the best performing types in the global phase were used to further improve detection accuracy.
Article
Computer Science, Theory & Methods
Xiaobo Zhang
Summary: The paper introduces a two-step non-local means (TSNLM) iterative scheme that combines local Wiener filter and NLM with different center weights to improve denoising performance.
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Automation & Control Systems
Gittaly Dhingra, Vinay Kumar, Hem Dutt Joshi
Summary: The economy of any country heavily relies on agricultural productivity, where timely and accurate detection of plant leave disease is crucial. Traditional manual systems for disease detection are inconsistent and subjective, prompting researchers to propose smart technologies for automatic detection. A computer vision-based technique using a combination of two feature extraction algorithms has shown promising results with high accuracy rates on various data sets.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2021)
Article
Acoustics
Lijie Huang, Jingke Zhang, Xingyue Wei, Linkai Jing, Qiong He, Xia Xie, Guihuai Wang, Jianwen Luo
Summary: The study proposed applying an NLM filter to the spatiotemporal domain of clutter filtered blood flow RF data (St-NLM) to improve the quality of uPDI. Experimental results demonstrate that the St-NLM method can effectively suppress background noise, improve contrast, and preserve details of small vessels.
IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL
(2022)
Article
Biochemistry & Molecular Biology
Jiakun Deng, Puying Tang, Xuegong Zhao, Tian Pu, Chao Qu, Zhenming Peng
Summary: This paper proposes an efficient local structure awareness-based retinal MA detection with multi-feature combination algorithm. By combining a novel local structure feature called RGD with traditional features, the performance of the MA detection model has been improved.
Article
Computer Science, Information Systems
Xiaobo Zhang
Summary: This study proposes a novel weight computation method based on considering the difference of each neighbor pixel including center pixel, which achieves different processing for each neighbor pixel and desired denoising performance.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Biomedical
Madhuri Devi Chodey, C. Noorullah Shariff
Summary: Due to frequent outbreaks of agricultural pests, agricultural production is limited and crop yield is minimized. Different types of agricultural pests pose greater obstacles to workers in recognizing them. Current agricultural pest detection techniques are often unable to meet the demands of agricultural production due to low model efficiency. This paper presents a pest identification model that detects Heliothis armigera (Cotton bollworm) and Leptocorisa acuta (rice bug) using four primary phases: Pre-processing, Object tracking and Segmentation, Feature extraction, and Classification. The proposed scheme's performance is compared to other current schemes using various metrics.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Multidisciplinary
Tingxin Zhou, Guangtao Zhang, Na Lu, Wenlin Yuan, Chaoyu Guo, Jiaming Zhang
Summary: Feature extraction from vibration signals is crucial in diagnosing faults in rotating machinery. Noise in the signals can affect the accuracy of feature extraction. This paper proposes an adaptive wavelet denoising (AWD) method that optimizes wavelet denoising parameters using the whale optimization algorithm, with permutation entropy used to evaluate signal noise level. The AWD method, combined with a synthetic detection index, presents a new approach for feature extraction. Simulation experiments and engineering applications demonstrate the satisfactory denoising performance of the AWD method and fault feature extraction approach.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2023)
Article
Optics
Xiaobo Zhang
Summary: This paper introduces a novel center weight calculation method WFCW and reveals the relationship between non-local total variation and NLM. Experimental results demonstrate that the proposed method achieves better performance and is more efficient compared to other NLM methods.
Article
Geochemistry & Geophysics
Bing Zhang, Yashinov Aziz, Zhicheng Wang, Lina Zhuang, Michael K. Ng, Lianru Gao
Summary: The proposed GF-destriping algorithm efficiently detects and removes stripes in hyperspectral images using Gabor filters and FastHyIn inpainting method, outperforming state-of-the-art destriping algorithms in numerical experiments on simulated and real data sets.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Instruments & Instrumentation
Francisco Restrepo, Junjing Zhao, Utpal Chatterjee
Summary: In this study, a shallow variational auto-encoder neural network is employed to demonstrate the potential of using machine learning for denoising and feature extraction from ARPES dispersion maps.
REVIEW OF SCIENTIFIC INSTRUMENTS
(2022)
Article
Geochemistry & Geophysics
Yimian Dai, Yiquan Wu, Fei Zhou, Kobus Barnard
Summary: In this paper, a novel model-driven deep network is proposed for infrared small target detection, which combines discriminative networks and conventional model-driven methods. By designing a feature map cyclic shift scheme and incorporating bottom-up attentional modulation, the network is able to encode long-range contextual interactions and preserve small target features effectively. Experimental results demonstrate that the proposed network outperforms other model-driven methods and deep networks, showing a performance boost in small target detection.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Yanyan Li, Linqiao Han, Xiaolei Liu
Summary: An improved method based on CEEMD and MPCA was proposed to enhance the accuracy of GNSS positioning and extract features. The results showed that the proposed method outperformed conventional Wavelet Decomposition-Principal Component Analysis (WD-PCA) and Empirical Mode Decomposition-Principal Component Analysis (EMD-PCA) in eliminating low- and high-frequency noise, making it suitable for denoising nonlinear and nonstationary GNSS position sequences.
Article
Computer Science, Information Systems
Shun Fang, Jiaxin Wu, Shiqian Wu
Summary: This paper introduces a new factor based on the Hessian matrix for the non-local means (NLM) algorithm to adjust the smoothing parameter, and proposes a strategy to represent patches using 2D histograms and summed-area tables. The patch similarity metric in this paper is based on statistical features instead of Euclidean distance, requiring fewer predefined thresholds. Experimental results demonstrate better performance in visual quality and numerical results.
Article
Microbiology
Peng Zhao, Chen Li, Md Mamunur Rahaman, Hao Xu, Pingli Ma, Hechen Yang, Hongzan Sun, Tao Jiang, Ning Xu, Marcin Grzegorzek
Summary: Environmental microorganisms have a significant impact on human society, but the lack of existing related datasets, particularly those with ground truth images, hinders progress in related experiments. This study introduces EMDS-6, a dataset containing 21 types of environmental microorganisms, and demonstrates its effectiveness in image processing methods.
FRONTIERS IN MICROBIOLOGY
(2022)
Article
Engineering, Multidisciplinary
Huaduo Wu, Yuanfei Han, Guangfa Huang, Nan Zong, Jianwei Mao, Huigang Shi, Weijie Lu
Summary: A novel fiber-like structural TiB reinforced titanium matrix composite was designed to achieve a combination of high strength and ductility. Through the improvement of structure and microstructure, the material showed enhanced tensile strength, comparable ductility, higher deformation ability, back stress during loading, and increased strain hardening rate. The higher mechanical response of the TiB/Ti composites is attributed to the introduction of TiB reinforcements with the new fiber-like structure, and the coupling effect of consequent grain refinement, load transferring effect, dislocation pinning effect of the fine TiB particles, back stress strengthening and the higher Schmid factors of prismatic slips.
COMPOSITES PART B-ENGINEERING
(2022)
Article
Engineering, Multidisciplinary
Xiaoyan Wang, Shaopeng Li, Yuanfei Han, Guangfa Huang, Jianwei Mao, Weijie Lu
Summary: TiC crystals are important reinforcements in metal matrix composites, but they can accelerate fatigue crack propagation and lead to premature fracture. To improve performance, reducing TiC content and minimizing crystal size are recommended.
COMPOSITES PART B-ENGINEERING
(2022)
Article
Oncology
Jiajian Wang, Jie Dong, Yinjian Zhou, Kaiyi Wang, Min Pan, Zaixing Deng, Pengfei Wang, Ying Du, Weiguo Lu
Summary: This study aimed to assess the clinical performance of an HPV E6/E7 mRNA assay (Aptima HPV, AHPV) and AHPV 16 18/45 genotype assay (AHPV-GT) combined with age stratification for triaging women with atypical squamous cells of undetermined significance (ASC-US) cytology. The results showed that AHPV testing with age stratification is effective for triaging women with ASC-US cytology, and AHPV-GT testing may be a proper risk stratification method for women with AHPV-positive ASC-US cytology.
GYNECOLOGIC ONCOLOGY
(2022)
Article
Pharmacology & Pharmacy
Songli Wang, Ruifeng Wang, Nana Meng, Linwei Lu, Jun Wang, Jianfen Zhou, Jiasheng Lu, Qianzhu Xu, Cao Xie, Changyou Zhan, Yao Li, Yang Yu, Weiyue Lu, Min Liu
Summary: In this study, a platelet-based delivery system was developed for the treatment of thrombotic diseases. The system showed superior thrombolytic efficacy and had the ability to inhibit re-embolism, while reducing the risk of hemorrhage.
ACTA PHARMACEUTICA SINICA B
(2022)
Article
Oncology
Jianying Xu, Xuan Rao, Weiguo Lu, Xing Xie, Xinyu Wang, Xiao Li
Summary: This study aimed to identify risk factors for malignant lesions in asymptomatic endometrial polyps (EPs) diagnosed by ultrasound and establish a noninvasive predictor. The study found that abnormal uterine bleeding, large polyps, and blood flow signal in EPs were independent predictive factors for malignancy. A noninvasive predictor combining these factors showed excellent sensitivity and negative predictive value in distinguishing benign and malignant EPs.
FRONTIERS IN ONCOLOGY
(2022)
Article
Microbiology
Yunfeng Fu, Xiao Li, Ying Li, Weiguo Lu, Xing Xie, Xinyu Wang
Summary: This study compares the clinical performance of DH3 HPV assay and HC2 test for cervical cancer screening and finds similar sensitivity and specificity for detecting high-grade lesions between the two tests. DH3 assay has the advantage of providing 92% sensitivity in primary screening strategy.
MICROBIOLOGY SPECTRUM
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Lin Ma, Weicheng Chi, Howard E. Morgan, Mu-Han Lin, Mingli Chen, David Sher, Dominic Moon, Dat T. Vo, Vladimir Avkshtol, Weiguo Lu, Xuejun Gu
Summary: In this study, a registration-guided DL segmentation framework for online cone beam computed tomography (CBCT) image was proposed. By integrating image registration algorithms and DL segmentation models, this framework overcame the issues of low image quality and limited training data, resulting in more accurate segmentation.
Article
Peripheral Vascular Disease
Gang Peng, Weiping Lu, Kai Chen, Xiaodan Yang, Jianguo Wei, Bo Wang, Bingcang Huang
Summary: Fourdimensional CT angiography-CT perfusion (4D CTA-CTP)-integrated technology was used to evaluate the cerebral collateral circulation in patients with acute ischemic stroke (AIS). It was found that the mCTA cerebral collateral circulation score can independently predict the neurological prognosis of AIS patients, while the baseline serum S100B protein concentration cannot independently predict the neurological prognosis of AIS patients.
MICROVASCULAR RESEARCH
(2022)
Article
Biochemistry & Molecular Biology
Wenying Yang, Dalong Zhu, Shenglian Gan, Xiaolin Dong, Junping Su, Wenhui Li, Hongwei Jiang, Wenjuan Zhao, Minxiu Yao, Weihong Song, Yibing Lu, Xiuzhen Zhang, Huifang Li, Guixia Wang, Wei Qiu, Guoyue Yuan, Jianhua Ma, Wei Li, Ziling Li, Xiaoyue Wang, Jiao'e Zeng, Zhou Yang, Jingdong Liu, Yongqian Liang, Song Lu, Huili Zhang, Hui Liu, Ping Liu, Kuanlu Fan, Xiaozhen Jiang, Yufeng Li, Qing Su, Tao Ning, Huiwen Tan, Zhenmei An, Zhaoshun Jiang, Lijun Liu, Zunhai Zhou, Qiu Zhang, Xuefeng Li, Zhongyan Shan, Yaoming Xue, Hong Mao, Lixin Shi, Shandong Ye, Xiaomei Zhang, Jiao Sun, Ping Li, Tao Yang, Feng Li, Jingna Lin, Zhinong Zhang, Ying Zhao, Ruonan Li, Xiaohui Guo, Qi Yao, Weiping Lu, Shen Qu, Hongmei Li, Liling Tan, Wenbo Wang, Yongli Yao, Daoxiong Chen, Yulan Li, Jialin Gao, Wen Hu, Xiaoqiang Fei, Tianfeng Wu, Song Dong, Wenlong Jin, Chenzhong Li, Dong Zhao, Bo Feng, Yu Zhao, Yi Zhang, Xiaoying Li, Li Chen
Summary: In patients with inadequate glycemic control using metformin alone, dorzagliatin as an add-on therapy resulted in effective glycemic control with good tolerability and safety.
Article
Infectious Diseases
Yuansu Jiang, Shuangshuang Yang, Shaoli Deng, Weiping Lu, Qing Huang, Yun Xia
Summary: The prevalence and molecular characteristics of tigecycline-resistant carbapenem-resistant Enterobacter cloacae (TCREC) in Southwest China were investigated. The study revealed that ST88 strains carrying the carbapenemase gene NDM-1 were the most common and exhibited resistance to tigecycline. Overexpression of efflux pumps contributed to tigecycline resistance. Effective supervision and management are crucial to prevent the transmission of TCREC isolates.
JOURNAL OF GLOBAL ANTIMICROBIAL RESISTANCE
(2022)
Article
Medicine, Research & Experimental
Yixuan Cen, Tingjia Zhu, Yanan Zhang, Lu Zhao, Jiawei Zhu, Lingfang Wang, Junfen Xu, Tian Ding, Xing Xie, Xinyu Wang, Weiguo Lu
Summary: This study identified a downregulated circular RNA (hsa_circ_0005358) derived from the host gene Gli1 in cervical cancer tissues, which suppressed the migration and invasion abilities of cervical cancer cells by interacting with polypyrimidine tract-binding protein 1 (PTBP1), ultimately reducing cancer metastasis.
MOLECULAR THERAPY-NUCLEIC ACIDS
(2022)
Article
Biotechnology & Applied Microbiology
Yanyi Lu, Lin Zeng, Min Li, Bowen Yan, Dandan Gao, Bangfu Zhou, Weiping Lu, Qinghua He
Summary: This study explored the possibility of identifying common wound infection bacteria in mixed culture using gas chromatograph-ion migration spectroscopy (GC-IMS). The headspace gas of single and mixed cultures of Escherichia coli, Staphylococcus aureus, and Pseudomonas aeruginosa was analyzed, and specific volatile organic compounds (mVOCs) were obtained. The findings suggest that GC-IMS can be used to identify compound bacteria based on specific mVOCs.
Article
Engineering, Mechanical
Weiping Lu, Wen Cui, Xiaogang Zhang, Yali Zhang, Shu Yang, Jian Pu, Junyan Li, Zhongmin Jin
Summary: The friction and wear behaviors between cartilage replacement materials and articular cartilage are crucial for the function and performance of the replacements. This study investigated the difference between cross-shear motion and reciprocal linear motion on the frictional and wear behaviors of cartilage, as well as the effect of bearing surface roughness. The results showed that there was no significant difference between the two motion types. The water contact angle of the bearing surface affected the friction and wear behaviors for low roughness implants, while the surface roughness of the material affected the behaviors for high roughness implants. PEEK was found to be a suitable material for osteochondral implants.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART J-JOURNAL OF ENGINEERING TRIBOLOGY
(2023)
Article
Multidisciplinary Sciences
Jiaqi Hu, Zhiwu Wang, Ruocheng Zuo, Chengcai Zheng, Bingjian Lu, Xiaodong Cheng, Weiguo Lu, Chunhui Zhao, Pengyuan Liu, Yan Lu
Summary: Radiomics-based models using preoperative contrast-enhanced computed tomography (CECT) images were developed to predict clinical outcomes of high-grade serous ovarian cancer (HGSOC). Patients with HGSOC can be accurately stratified into high-risk or low-risk groups for cancer-related death or likely recurrence based on their CT images. These radiomic models provide convincing and reliable non-invasive markers for individualized prognostic evaluation and clinical decision-making.
Article
Biochemistry & Molecular Biology
Qianqian Wu, Mingjing Wei, Lifang Yao, Xiaodong Cheng, Weiguo Lu, Xing Xie, Xiao Li
Summary: Hyperthermia can enhance the sensitivity of epithelial ovarian carcinoma cells with sufficient homologous recombination abilities to PARP inhibitors by impairing homologous recombination efficiency and increasing oxidative stress.
BIOCHEMICAL AND BIOPHYSICAL RESEARCH COMMUNICATIONS
(2022)