Article
Engineering, Biomedical
Ziye Chen, Xue Yin, Lin Lin, Guohua Shi, Jianhua Mo
Summary: This study aims to improve the accuracy and universality of centerline extraction in corneal nerve fiber (CNF). A new thinning algorithm called neighborhood-statistics thinning (NST) was developed to extract the centerline of CNF, which exhibited better preservation of fine structures and less influence from image segmentation compared to traditional methods. The NST method was evaluated on three datasets segmented with five different deep learning networks, showing superior precision rates above 0.82. Moreover, the measured biomarkers from the extracted centerlines were successfully applied for the diagnosis of keratitis, demonstrating the potential of NST in aiding the diagnostics of eye diseases in clinic.
PHYSICS IN MEDICINE AND BIOLOGY
(2022)
Article
Computer Science, Software Engineering
Yuxuan Hou, Zhong Ren, Qiming Hou, Yubo Tao, Yankai Jiang, Wei Chen
Summary: Neuron tracing, or reconstruction, is crucial for studying neuronal circuits and brain mechanisms. We present InstantTrace, a novel framework that utilizes parallel tracing on GPUs and achieves a more than 20x speed boost compared to state-of-the-art methods, while maintaining comparable reconstruction quality. The framework takes advantage of the sparse feature and tree structure of the neuron image and parallelizes all stages of the tracing pipeline on GPU. A test on a whole mouse brain OM Image demonstrated that our framework can achieve a preliminary reconstruction within 1 hour on a single GPU, which is an order of magnitude faster than existing methods. This framework has the potential to significantly improve the efficiency of the neuron tracing process and provide instant preliminary results for manual verification and refinement.
Article
Computer Science, Interdisciplinary Applications
Xuan Wang, Min Liu, Yaonan Wang, Jiawang Fan, Erik Meijering
Summary: This paper proposes a neuron centerline extraction method based on a 3D tubular flux model using a two-stage CNN framework. The method learns flux features from neuron images and extracts the centerline with a spatial weighted average strategy. The experiments show that the proposed method outperforms other state-of-the-art methods and the extracted centerline improves neuron reconstruction performance.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Computer Science, Interdisciplinary Applications
Xinyue Zhang, Hongwei Du, Gang Song, Fangxun Bao, Yunfeng Zhang, Wei Wu, Peide Liu
Summary: In this study, a centerline extraction method based on deep learning and conventional methods is proposed, which can automatically and accurately extract vascular centerlines from X-ray coronary angiography images.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Multidisciplinary Sciences
Li-Syuan Pan, Chia-Wei Li, Shun-Feng Su, Shee-Yen Tay, Quoc-Viet Tran, Wing P. Chan
Summary: The study utilized a U-Net-based 3D Dense-U-Net network architecture for fully automatic segmentation of coronary arteries, achieving a high level of accuracy through optimization and the adoption of focal loss concept. The results demonstrate a significant advantage of the proposed method in coronary artery segmentation, showing potential for assisting clinical diagnosis.
SCIENTIFIC REPORTS
(2021)
Article
Computer Science, Artificial Intelligence
Tian Yang, Shiwei Wu, Song Zhang, Shichao Yang, Yanxue Wu, Fei Liu
Summary: Multiple laser stripe measurement is a vital technique in optical 3D measurement. In this study, we propose an adaptive step size gradient centerline extraction method based on a 2D linear filter to accurately extract laser stripe centerlines in complex measurement scenarios. Comprehensive comparative experiments demonstrate that our method enables more precise centerline extraction, exhibits enhanced stability, and yields lower measurement errors.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Yuzhun Lin, Fei Jin, Dandi Wang, Shuxiang Wang, Xiao Liu
Summary: This article proposes a dual task-driven deep convolutional neural network for road extraction, which combines road shape patterns and scale differences. The network utilizes residual convolution and multiscale convolution to improve feature extraction and connectivity, resulting in superior performance compared to existing methods.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Oncology
Dongqin Wu, Di Gao, Haitao Yu, Guilin Pi, Rui Xiong, Huiyang Lei, Xin Wang, Enjie Liu, Jinwang Ye, Huilin Yu, Yang Gao, Ting He, Tao Jiang, Fei Sun, Jingfen Su, Guoda Song, Wenju Peng, Ying Yang, Jian-Zhi Wang
Summary: The study found a causal relationship between tau accumulation and cholinergic neuron impairment in Alzheimer's disease. Overexpression of hTau protein in the medial septum of mice resulted in spatial memory impairment and reduction of cholinergic neurons over time. Treatment with donepezil showed improvement in spatial memory deficits induced by hTau accumulation, potentially suggesting a new disease-modifying effect.
CLINICAL AND TRANSLATIONAL MEDICINE
(2021)
Article
Computer Science, Information Systems
Qing Huang, Tingting Cao, Shaoqun Zeng, Anan Li, Tingwei Quan
Summary: In this paper, a graph connectivity theoretical method for precise filamentary structure tracing in neuron image is proposed. The method uses CNN technique and linear programming function to trace broken traces from noisy background, and it achieves good results in experiments.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Biochemistry & Molecular Biology
Daniel A. D. Flormann, Moritz Schu, Emmanuel Terriac, Divyendu Thalla, Lucina Kainka, Marcus Koch, Annica K. B. Gad, Franziska Lautenschlaeger
Summary: Advancements in advanced microscopy techniques have enhanced imaging quality and understanding of subcellular structures, but computational analysis techniques have not progressed at the same pace. A new algorithm for tracing filament networks has been developed, capable of extracting important parameters and distinguishing sub-networks in two-dimensional images. This algorithm can be widely applied in analyzing images obtained from different advanced microscopy methods.
Article
Computer Science, Artificial Intelligence
Jamie Burke, Stuart King
Summary: We propose a novel edge tracing algorithm using Gaussian process regression. This algorithm models the edge of interest using Gaussian process regression and iteratively searches for edge pixels in the image. It is not restricted to a specific type of imaging domain and is robust to artifacts and occlusions in images.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Computer Science, Information Systems
Diego Patino, John W. Branch
Summary: CPMA is a new method for medial axis pruning that is noise-robust and equivariant to isometric transformations. It utilizes the discrete cosine transform to create smooth versions of a shape and computes a score function to filter out spurious branches. The method has been compared extensively with state-of-the-art pruning methods and has shown competitive results in various datasets.
Article
Multidisciplinary Sciences
Weijia Fan, Yudi Sang, Hanyue Zhou, Jiayu Xiao, Zhaoyang Fan, Dan Ruan
Summary: Analysis of vessel morphology is crucial in evaluating intracranial atherosclerosis disease (ICAD), and magnetic resonance vessel wall imaging (VWI) has been introduced to image ICAD and characterize atherosclerotic lesions. This study aims to investigate the feasibility of inferring vessel location directly from VWI by combining an atlas-based method with a deep learning network. The proposed pipeline shows clinically feasible performance in localizing intracranial vessels, demonstrating the potential of VWI in vessel morphology analysis.
SCIENTIFIC REPORTS
(2022)
Article
Engineering, Electrical & Electronic
Chuan Ye, Yunhan Li, Chao Wang, Yuanyao Hu
Summary: A deep learning line laser 3-D measurement method based on feature fusion and attention mechanism is proposed to address the impact of reflected workpieces. A UNet segmentation model is established to solve the interference caused by reflection and segment the overall distribution and bending characteristics of laser stripes. The Steger algorithm is used to extract the center of the laser stripe, and the contour polygon segmentation method is used to obtain the segmentation points of the laser stripe. Polynomial fitting is then performed to obtain a smoother laser stripe centerline. The proposed method effectively overcomes interference and generates a smoother 3-D model.
IEEE SENSORS JOURNAL
(2023)
Article
Mathematical & Computational Biology
Xintong Wu, Yingyi Geng, Xinhong Wang, Jucheng Zhang, Ling Xia
Summary: This study proposes a deep learning algorithm for continuous extraction of coronary artery centerlines from cardiac computed tomography angiography (CTA) images. The algorithm uses a regression method and a CNN module to extract features, and includes a branch classifier and direction predictor for direction and lumen radius prediction. A new loss function is developed to associate the direction vector with the lumen radius. The method achieves high accuracy in centerline extraction, making it useful for assisting in the diagnosis of coronary artery disease (CAD).
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2023)
Article
Biochemical Research Methods
Aline Silva da Cruz, Maria Margarida Drehmer, Wagner Baetas-da-Cruz, Joao Carlos Machado
Summary: This study quantified microcirculation cerebral blood flow in a rat model of ischemic stroke using ultrasound biomicroscopy and ultrasound contrast agents. The results showed high sensitivity and specificity of this method, making it a valuable tool for preclinical studies.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Christina Dalla, Ivana Jaric, Pavlina Pavlidi, Georgia E. Hodes, Nikolaos Kokras, Anton Bespalov, Martien J. Kas, Thomas Steckler, Mohamed Kabbaj, Hanno Wuerbel, Jordan Marrocco, Jessica Tollkuhn, Rebecca Shansky, Debra Bangasser, Jill B. Becker, Margaret McCarthy, Chantelle Ferland-Beckham
Summary: Many funding agencies have emphasized the importance of considering sex as a biological variable in experimental design to improve the reproducibility and translational relevance of preclinical research. Omitting the female sex from experimental designs in neuroscience and pharmacology can result in biased or limited understanding of disease mechanisms. This article provides methodological considerations for incorporating sex as a biological variable in in vitro and in vivo experiments, including the influence of age and hormone levels, and proposes strategies to enhance methodological rigor and translational relevance in preclinical research.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Wenyu Gu, Dongxu Li, Jia-Hong Gao
Summary: We developed a precise and rapid method for positioning and labelling triaxial OPMs on a wearable magnetoencephalography (MEG) system, improving the efficiency of OPM positioning and labelling.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Kai Lin, Linhang Zhang, Jing Cai, Jiaqi Sun, Wenjie Cui, Guangda Liu
Summary: The article introduces an EEG feature map processing model for emotion recognition, which achieves significantly improved accuracy by fusing EEG information at different spatial scales and introducing a channel attention mechanism.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
John E. Parker, Asier Aristieta, Aryn H. Gittis, Jonathan E. Rubin
Summary: This work presents a toolbox that implements a methodology for automated classification of neural responses based on spike train recordings. The toolbox provides a user-friendly and efficient approach to detect various types of neuronal responses that may not be identified by traditional methods.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Yun Liang, Ke Bo, Sreenivasan Meyyappan, Mingzhou Ding
Summary: This study compared the performance of SVM and CNN on the same datasets and found that CNN achieved consistently higher classification accuracies. The classification accuracies of SVM and CNN were generally not correlated, and the heatmaps derived from them did not overlap significantly.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Antonino Visalli, Maria Montefinese, Giada Viviani, Livio Finos, Antonino Vallesi, Ettore Ambrosini
Summary: This study introduces an analytical strategy that allows the use of mixed-effects models (LMM) in mass univariate analyses of EEG data. The proposed method overcomes the computational costs and shows excellent performance properties, making it increasingly important in the field of neuroscience.
JOURNAL OF NEUROSCIENCE METHODS
(2024)
Article
Biochemical Research Methods
Xavier Cano-Ferrer, Alexandra Tran -Van -Minh, Ede Rancz
Summary: This study developed a novel rotation platform for studying neural processes and spatial navigation. The platform is modular, affordable, and easy to build, and can be driven by the experimenter or animal movement. The research demonstrated the utility of the platform, which combines the benefits of head fixation and intact vestibular activity.
JOURNAL OF NEUROSCIENCE METHODS
(2024)