Article
Computer Science, Interdisciplinary Applications
Chao Liu, Deli Wang, Han Zhang, Wei Wu, Wenzhi Sun, Ting Zhao, Nenggan Zheng
Summary: Reconstructing neuron morphologies from fluorescence microscope images is crucial for neuroscience studies. This study proposes a strategy of using two-stage generative models to simulate training data with voxel-level labels, resulting in realistic 3D images with underlying voxel labels. The results show that networks trained on synthetic data outperform those trained on manually labeled data in segmentation performance.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Computer Science, Interdisciplinary Applications
Bo Yang, Min Liu, Yaonan Wang, Kang Zhang, Erik Meijering
Summary: This paper presents a 3D neuron segmentation network called SGSNet that enhances weak neuronal structures and removes background noises. The network utilizes two decoding paths, one for acquiring segmentation maps and the other for detecting neuronal structures. A structure attention module is designed to integrate features and provide contextual guidance to improve segmentation performance.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Biochemical Research Methods
Qiufu Li, Linlin Shen
Summary: The paper introduces a 3D wavelet and deep learning-based method for neuron segmentation, utilizing 3D WaveUNet to process neuronal cubes and improve performance in noisy neuronal images. The integrated 3D wavelets efficiently assist in 3D neuron segmentation and reconstruction.
Article
Biology
Bohao Xu, Yingwei Fan, Jingming Liu, Guobin Zhang, Zhiping Wang, Zhili Li, Wei Guo, Xiaoying Tang
Summary: In this study, an automatic segmentation network (CHSNet) was proposed to segment lesions in cranial CT images based on the characteristics of acute cerebral hemorrhage images. The network achieved 3D visualization and localization of the cranial lesions after segmentation. Experimental results demonstrated the effectiveness of the model on a dataset of 203 patients, achieving high performance in segmenting hemorrhage in CT images of stroke patients.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Interdisciplinary Applications
Kisuk Lee, Ran Lu, Kyle Luther, H. Sebastian Seung
Summary: This study demonstrates that dense voxel embeddings learned through deep metric learning can accurately segment neurons from 3D electron microscopy images. A metric graph is constructed from the dense voxel embeddings generated by a convolutional network, and partitioning the graph with long-range edges as repulsive constraints results in precise initial segmentation, particularly useful for very thin objects. The convolutional embedding network is reused without modification to aggregate systematic splits caused by complex self-contact motifs, achieving state-of-the-art accuracy in reconstructing 3D neurons from brain images acquired through serial section electron microscopy. The proposed object-centered representation may have broader applications in automated neural circuit reconstruction.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Mathematical & Computational Biology
Liya Ding, Xuan Zhao, Shuxia Guo, Yufeng Liu, Lijuan Liu, Yimin Wang, Hanchuan Peng
Summary: SNAP is a structure-based neuron morphology reconstruction pruning pipeline that improves the usability of reconstruction results by reducing erroneous extra reconstruction and splitting entangled neurons. Experimental results show that SNAP achieves pruning with high precision and recall, making it an effective tool for neuron morphology analysis.
FRONTIERS IN NEUROINFORMATICS
(2023)
Article
Mathematics
Javier Martinez, Daniel Perez-Palau, Myriam Cilla, Neus Garrido, Ana Larranaga, Ignacio Perez-Rey
Summary: The occurrence of atheroma plaques in the arteries can lead to diseases such as atherosclerosis, necessitating a shorter time spent in locating and reconstructing the plaque. This paper presents a 3-D reconstruction of the atheroma plaque using an image processing algorithm on intravascular ultrasound images, providing an important decision-support tool in medical procedures. The results can contribute to early detection and prediction of atheroma plaques.
Article
Oncology
Max C. Lindemann, Lukas Glaenzer, Anjali A. Roeth, Thomas Schmitz-Rode, Ioana Slabu
Summary: Three-dimensional models of tumor vascular networks are important for in vitro and in silico investigations, and can potentially be used for the development of in vitro systems. This work presents an algorithm-based method using histologic slices to reconstruct a 3D vascular network model with high resolution and accuracy.
Article
Biochemical Research Methods
Mariusz Marzec, Adam Piorkowski, Arkadiusz Gertych
Summary: In this study, a new algorithm was developed to accurately segment cell nuclei in 3D images and achieved the best results in fluorescence image evaluation.
BMC BIOINFORMATICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Xiaodan Wei, Qinghao Liu, Min Liu, Yaonan Wang, Erik Meijering
Summary: In this paper, we propose a two-stage deep neural network for fast and accurate soma detection in large-scale and high-resolution whole mouse brain images. A lightweight Multi-level Cross Classification Network (MCC-Net) is first used to filter out images without somas and generate coarse candidate images, followed by a Scale Fusion Segmentation Network (SFS-Net) to accurately segment soma regions. Experimental results demonstrate excellent performance of the proposed method and a public dataset named WBMSD is established for further research on soma detection.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Chemistry, Analytical
Mengfan Xue, Lu Han, Yiran Song, Fan Rao, Dongliang Peng
Summary: The study introduces a learning-based method for lung lobe segmentation, which combines local fissures, the whole lung, and prior pulmonary anatomy knowledge for robust and accurate segmentation in COPD patients. The method performs comparably to a former approach but demonstrates greater robustness in cases with morphological specificity.
Article
Computer Science, Interdisciplinary Applications
Ioannis Andrikos, Kostas Stefanou, Christos Bellos, George Stergios, Elisa Alchera, Irene Locatelli, Massimo Alfano
Summary: This study presents a software tool called EDIT for the visualization and semi-automatic 3D reconstruction of urinary bladder anatomy. The software computes the inner bladder wall using a feedback-based active contour algorithm on ultrasound images and calculates the outer bladder wall by expanding the inner borders on photoacoustic images. Validation was done on phantom objects and in-vivo bladder cancer cases, showing high precision and similarity with true volumes. The EDIT software is a novel tool that extracts different 3D components of the bladder using ultrasound and photoacoustic images.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Computer Science, Interdisciplinary Applications
Yi Jiang, Weixun Chen, Min Liu, Yaonan Wang, Erik Meijering
Summary: This paper proposes a neuronal structure segmentation method for 3D neuron microscopy images based on a combination of ray-shooting model and LSTM network, enhancing weak-signal neuronal structures and removing background noise. By transforming the 3D image segmentation task into multiple 1D ray/sequence segmentation tasks, the labeling of training samples is made much easier compared to existing CNN-based methods.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Engineering, Manufacturing
Weifeng Li, Bin Li, Shuanlong Niu, Zhenrong Wang, Miao Wang, Tongzhi Niu
Summary: This article proposes an end-to-end network to solve the problem of defect location and shape feature fusion. The location attention module enhances the perception of defect locations, while the shape detection module with feature difference loss strengthens the detection of defect shapes. In the decoding stage, the features of different scales are fused to obtain the final defect region. The experimental results confirm the effectiveness of the proposed location and shape detection modules in the intersection over union on four datasets.
JOURNAL OF MANUFACTURING PROCESSES
(2023)
Article
Mathematics
Chung Feng Jeffrey Kuo, Zheng-Xun Yang, Wen-Sen Lai, Shao-Cheng Liu
Summary: This study presents the development of a computer tomography (CT) system for automatic segmentation and quantitative analysis of the pulmonary bronchus. The proposed system can automatically detect the location of the pulmonary airway and identify multiple generations of bronchi with high accuracy and automation.
Article
Clinical Neurology
Marta Montero-Crespo, Marta Dominguez-Alvaro, Lidia Alonso-Nanclares, Javier DeFelipe, Lidia Blazquez-Llorca
Summary: Alzheimer's disease is a common form of dementia characterized by persistent and progressive impairment of cognitive functions. Early-stage cases show normal synaptic morphology, but late-stage cases experience decreased synaptic density and morphological alterations.
Article
Neurosciences
Nicolas Cano-Astorga, Javier DeFelipe, Lidia Alonso-Nanclares
Summary: This study used FIB/SEM to investigate the synaptic organization in human tissue samples, revealing significant differences in synaptic density between autopsy and biopsy samples but a similar asymmetric:symmetric ratio. Synaptic junctions were primarily established on dendritic shafts and spines depending on their type.
Article
Computer Science, Artificial Intelligence
Antonio LaTorre, Lidia Alonso-Nanclares, Jose Maria Pena, Javier DeFelipe
Summary: The study presents a method to improve 3D reconstruction of neuronal nuclei for accurate identification, excluding non-neuronal cell types. It highlights the differences and inaccuracies in existing automatic tools and emphasizes the importance of automatic segmentation tools for neuroanatomical studies.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Antonio LaTorre, Daniel Molina, Eneko Osaba, Javier Poyatos, Javier Del Ser, Francisco Herrera
Summary: Bio-inspired optimization is a growing research field where proposing a new algorithm with significant advancement over previous ones is challenging. Selecting appropriate benchmarks for comparison and conducting rigorous validation processes are crucial for ensuring the significance of the results presented in studies. This work reviews recommendations and proposes methodological guidelines to help authors, reviewers, and editors in evaluating new contributions to the field.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Mathematics
Jose Javier Galan, Ramon Alberto Carrasco, Antonio LaTorre
Summary: This paper presents a machine learning architecture model applied to a military organization, supported by a bibliometric study. Machine learning is used to analyze a large volume of data and make predictions, providing automatic learning and decision support. A research methodology used in a nonmilitary organization is explained and applied to draw a conceptual architecture for practical use of machine learning in a military environment.
Article
Neurosciences
Katrin Amunts, Javier DeFelipe, Cyriel Pennartz, Alain Destexhe, Michele Migliore, Philippe Ryvlin, Steve Furber, Alois Knoll, Lise Bitsch, Jan G. Bjaalie, Yannis Ioannidis, Thomas Lippert, Maria V. Sanchez-Vives, Rainer Goebel, Viktor Jirsa
Summary: Understanding the human brain is a Grand Challenge for 21st century research. Computational approaches and dynamic generative multiscale models are instrumental for linking brain structure and function. The intersection of neuroscience, computing, and robotics has the potential to advance neuro-inspired technologies. To facilitate research sharing and collaboration, the Human Brain Project has launched the digital neuroscience research infrastructure EBRAINS.
Article
Neurosciences
Lidia Alonso-Nanclares, J. Rodrigo Rodriguez, Angel Merchan-Perez, Juncal Gonzalez-Soriano, Sergio Plaza-Alonso, Nicolas Cano-Astorga, Robert K. K. Naumann, Michael Brecht, Javier DeFelipe
Summary: The study aimed to compare the synaptic characteristics between the small brain of Etruscan shrew and the larger human brain. The findings showed that while some synaptic characteristics are similar, there are significant differences in the number and size of synapses, suggesting adaptations of synaptic circuits to specific functions.
JOURNAL OF COMPARATIVE NEUROLOGY
(2023)
Review
Anatomy & Morphology
Javier DeFelipe, Jesus DeFelipe-Oroquieta, Diana Furcila, Mar Munoz-Alegre, Fernando Maestu, Rafael G. Sola, Lidia Blazquez-Llorca, Ruben Armananzas, Asta Kastanaskaute, Lidia Alonso-Nanclares, Kathleen S. Rockland, Jon Arellano
Summary: Temporal lobe epilepsy (TLE) is the most common form of focal epilepsy, and it is associated with structural and psychological alterations. When using resected brain tissue for research, it is important to consider the clinical, anatomical, and psychological characteristics of the patients. Unfortunately, this information is often incomplete or not fully understood by the neuroscientists analyzing the brain samples.
FRONTIERS IN NEUROANATOMY
(2022)
Article
Computer Science, Artificial Intelligence
Pablo S. Naharro, Pablo Toharia, Antonio LaTorre, Jose-Maria Pena
Summary: Heuristic optimisation is widely used in the sciences and engineering, but the expensive fitness function limits the number of evaluations. Surrogate models, including regression and pairwise models, are proposed as alternatives to address this issue. Experimental analysis shows that the performance of online machine learning-based surrogate models depends on the accuracy of the predictive model, as well as the bias towards positive or negative cases and how the optimization utilizes the predictions.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Neurosciences
Nicolas Cano-Astorga, Sergio Plaza-Alonso, Javier DeFelipe, Lidia Alonso-Nanclares
Summary: The synaptic organization of the human anterior cingulate and temporopolar cortices was studied using FIB/SEM and revealed that Brodmann areas 24, 21, and ventral area 38 have similar synaptic density and size, whereas dorsal area 38 has the highest density and smallest size. However, the proportion and shapes of excitatory and inhibitory synapses were similar across all regions.
Review
Clinical Neurology
Raquel Martinez-Serra, Lidia Alonso-Nanclares, Kwangwook Cho, K. Peter Giese
Summary: Martinez-Serra et al. found that synaptic changes in post-mortem Alzheimer's disease brain regions are diverse, with multi-synapses being the most prominent. This suggests that synaptic dysfunction and loss might underlie the pathophysiology of the disease.
BRAIN COMMUNICATIONS
(2022)
Article
Neurosciences
M. Dominguez-Alvaro, M. Montero-Crespo, L. Blazquez-Llorca, S. Plaza-Alonso, N. Cano-Astorga, J. DeFelipe, L. Alonso-Nanclares
Summary: The study revealed alterations in the volume fraction of neuronal and glial cell bodies in layers II and III of the entorhinal cortex in AD cases, as well as changes in synaptic density and morphology. These structural differences may contribute to the impairment of cognitive functions in AD.
Article
Clinical Neurology
Marta Montero-Crespo, Marta Dominguez-Alvaro, Lidia Alonso-Nanclares, Javier DeFelipe, Lidia Blazquez-Llorca
Summary: Alzheimer's disease is a common form of dementia characterized by cognitive impairment, with extracellular protein deposits and abnormal protein accumulation in neurons. Synaptic alterations were found in different stages of the disease, with more severe changes observed in late-stage cases.