Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 25.129
Filtrar
1.
Forensic Sci Int ; 307: 110115, 2020 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-31918164

RESUMO

INTRODUCTION: In a case of child pornography, only the dorsum of the offender's hand was clearly visible. After identification of a suspect, the question arose of whether and how it is possible to identify or exclude the suspect as perpetrator according to the morphology of the hand vein pattern. MATERIAL AND METHODS: A simple approach to use the hand vein pattern in crime suspects as a tool for identification was tested. In this study, the hand vein patterns of 30 study participants were analysed from conventional frames on videography. A standardised grid system consisting of six lines and four sectors was applied on the dorsum of the hands. Vein branchings within the sectors and line crossings of the veins were counted, leading to a total of 11 variables for each hand. RESULTS: A positive identification of each of the 30 test participants was possible for each hand when taking only the first five variables into account. A random overlapping prediction was obtained by statistically simulating hand vein patterns of different numbers of persons using this sample. Considering the hand vein frequencies in this sample, the results indicate that the chance for two persons having the same pattern is smaller than 1:1000. CONCLUSIONS: It can be concluded that the introduced grid system approach can be an appropriate simple and non-costly tool for the analysis of the pattern of hand veins for identification purposes.


Assuntos
Mãos/irrigação sanguínea , Processamento de Imagem Assistida por Computador , Reconhecimento Automatizado de Padrão , Veias/anatomia & histologia , Gravação em Vídeo , Adulto , Idoso , Criança , Bem-Estar da Criança/legislação & jurisprudência , Literatura Erótica/legislação & jurisprudência , Feminino , Ciências Forenses/métodos , Humanos , Masculino , Pessoa de Meia-Idade , Adulto Jovem
2.
Medicine (Baltimore) ; 99(4): e18724, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31977863

RESUMO

Deep analysis of radiographic images can quantify the extent of intra-tumoral heterogeneity for personalized medicine.In this paper, we propose a novel content-based multi-feature image retrieval (CBMFIR) scheme to discriminate pulmonary nodules benign or malignant. Two types of features are applied to represent the pulmonary nodules. With each type of features, a single-feature distance metric model is proposed to measure the similarity of pulmonary nodules. And then, multiple single-feature distance metric models learned from different types of features are combined to a multi-feature distance metric model. Finally, the learned multi-feature distance metric is used to construct a content-based image retrieval (CBIR) scheme to assist the doctors in diagnosis of pulmonary nodules. The classification accuracy and retrieval accuracy are used to evaluate the performance of the scheme.The classification accuracy is 0.955 ±â€Š0.010, and the retrieval accuracies outperform the comparison methods.The proposed CBMFIR scheme is effective in diagnosis of pulmonary nodules. Our method can better integrate multiple types of features from pulmonary nodules.


Assuntos
Interpretação de Imagem Assistida por Computador/métodos , Nódulos Pulmonares Múltiplos/diagnóstico , Nódulo Pulmonar Solitário/diagnóstico , Humanos , Reconhecimento Automatizado de Padrão/métodos , Tomografia Computadorizada por Raios X
3.
Neural Netw ; 121: 452-460, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31610416

RESUMO

In the paper, synchronization of coupled neural networks with delayed impulses is investigated. In order to overcome the difficulty that time delays can be flexible and even larger than impulsive interval, we propose a new method of average impulsive delay (AID). By the methods of average impulsive interval (AII) and AID, some sufficient synchronization criteria for coupled neural networks with delayed impulses are obtained. We prove that the time delay in impulses can play double roles, namely, it may desynchronize a synchronous network or synchronize a nonsynchronized network. Moreover, a unified relationship is established among AII, AID and rate coefficients of the impulsive dynamical network such that the network is globally exponentially synchronized (GES). Further, we discuss the case that time delays in impulses may be unbounded, which has not been considered in existing results. Finally, two examples are presented to demonstrate the validity of the derived results.


Assuntos
Reconhecimento Automatizado de Padrão/métodos , Fatores de Tempo
4.
Neural Netw ; 121: 461-473, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31629201

RESUMO

Deep convolutional neural networks (CNNs) have attracted great attention in the field of image denoising. However, there are two drawbacks: (1) it is very difficult to train a deeper CNN for denoising tasks, and (2) most of deeper CNNs suffer from performance saturation. In this paper, we report the design of a novel network called a batch-renormalization denoising network (BRDNet). Specifically, we combine two networks to increase the width of the network, and thus obtain more features. Because batch renormalization is fused into BRDNet, we can address the internal covariate shift and small mini-batch problems. Residual learning is also adopted in a holistic way to facilitate the network training. Dilated convolutions are exploited to extract more information for denoising tasks. Extensive experimental results show that BRDNet outperforms state-of-the-art image-denoising methods. The code of BRDNet is accessible at http://www.yongxu.org/lunwen.html.


Assuntos
Aprendizado Profundo/normas , Reconhecimento Automatizado de Padrão/métodos , Razão Sinal-Ruído
5.
Neural Netw ; 121: 122-131, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31541880

RESUMO

Neurons in the primate middle temporal area (MT) respond to moving stimuli, with strong tuning for motion speed and direction. These responses have been characterized in detail, but the functional significance of these details (e.g. shapes and widths of speed tuning curves) is unclear, because they cannot be selectively manipulated. To estimate their functional significance, we used a detailed model of MT population responses as input to convolutional networks that performed sophisticated motion processing tasks (visual odometry and gesture recognition). We manipulated the distributions of speed and direction tuning widths, and studied the effects on task performance. We also studied performance with random linear mixtures of the responses, and with responses that had the same representational dissimilarity as the model populations, but were otherwise randomized. The width of speed and direction tuning both affected task performance, despite the networks having been optimized individually for each tuning variation, but the specific effects were different in each task. Random linear mixing improved performance of the odometry task, but not the gesture recognition task. Randomizing the responses while maintaining representational dissimilarity resulted in poor odometry performance. In summary, despite full optimization of the deep networks in each case, each manipulation of the representation affected performance of sophisticated visual tasks. Representation properties such as tuning width and representational similarity have been studied extensively from other perspectives, but this work provides new insight into their possible roles in sophisticated visual inference.


Assuntos
Percepção de Movimento/fisiologia , Reconhecimento Automatizado de Padrão/métodos , Estimulação Luminosa/métodos , Lobo Temporal/fisiologia , Animais , Movimento (Física) , Neurônios/fisiologia
6.
Neural Netw ; 121: 148-160, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31563011

RESUMO

Over the past decade, Deep Convolutional Neural Networks (DCNNs) have shown remarkable performance in most computer vision tasks. These tasks traditionally use a fixed dataset, and the model, once trained, is deployed as is. Adding new information to such a model presents a challenge due to complex training issues, such as "catastrophic forgetting", and sensitivity to hyper-parameter tuning. However, in this modern world, data is constantly evolving, and our deep learning models are required to adapt to these changes. In this paper, we propose an adaptive hierarchical network structure composed of DCNNs that can grow and learn as new data becomes available. The network grows in a tree-like fashion to accommodate new classes of data, while preserving the ability to distinguish the previously trained classes. The network organizes the incrementally available data into feature-driven super-classes and improves upon existing hierarchical CNN models by adding the capability of self-growth. The proposed hierarchical model, when compared against fine-tuning a deep network, achieves significant reduction of training effort, while maintaining competitive accuracy on CIFAR-10 and CIFAR-100.


Assuntos
Aprendizado Profundo , Reconhecimento Automatizado de Padrão/métodos , Estimulação Luminosa/métodos , Animais , Aprendizado Profundo/tendências , Humanos , Reconhecimento Automatizado de Padrão/tendências
7.
Neural Netw ; 121: 294-307, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31586857

RESUMO

Artificial neural networks (ANNs), a popular path towards artificial intelligence, have experienced remarkable success via mature models, various benchmarks, open-source datasets, and powerful computing platforms. Spiking neural networks (SNNs), a category of promising models to mimic the neuronal dynamics of the brain, have gained much attention for brain inspired computing and been widely deployed on neuromorphic devices. However, for a long time, there are ongoing debates and skepticisms about the value of SNNs in practical applications. Except for the low power attribute benefit from the spike-driven processing, SNNs usually perform worse than ANNs especially in terms of the application accuracy. Recently, researchers attempt to address this issue by borrowing learning methodologies from ANNs, such as backpropagation, to train high-accuracy SNN models. The rapid progress in this domain continuously produces amazing results with ever-increasing network size, whose growing path seems similar to the development of deep learning. Although these ways endow SNNs the capability to approach the accuracy of ANNs, the natural superiorities of SNNs and the way to outperform ANNs are potentially lost due to the use of ANN-oriented workloads and simplistic evaluation metrics. In this paper, we take the visual recognition task as a case study to answer the questions of "what workloads are ideal for SNNs and how to evaluate SNNs makes sense". We design a series of contrast tests using different types of datasets (ANN-oriented and SNN-oriented), diverse processing models, signal conversion methods, and learning algorithms. We propose comprehensive metrics on the application accuracy and the cost of memory & compute to evaluate these models, and conduct extensive experiments. We evidence the fact that on ANN-oriented workloads, SNNs fail to beat their ANN counterparts; while on SNN-oriented workloads, SNNs can fully perform better. We further demonstrate that in SNNs there exists a trade-off between the application accuracy and the execution cost, which will be affected by the simulation time window and firing threshold. Based on these abundant analyses, we recommend the most suitable model for each scenario. To the best of our knowledge, this is the first work using systematical comparisons to explicitly reveal that the straightforward workload porting from ANNs to SNNs is unwise although many works are doing so and a comprehensive evaluation indeed matters. Finally, we highlight the urgent need to build a benchmarking framework for SNNs with broader tasks, datasets, and metrics.


Assuntos
Potenciais de Ação/fisiologia , Inteligência Artificial , Reconhecimento Automatizado de Padrão/métodos , Algoritmos , Encéfalo/fisiologia , Humanos , Memória/fisiologia , Neurônios/fisiologia
8.
Neural Netw ; 121: 387-395, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31593843

RESUMO

Spiking neural networks (SNNs) possess energy-efficient potential due to event-based computation. However, supervised training of SNNs remains a challenge as spike activities are non-differentiable. Previous SNNs training methods can be generally categorized into two basic classes, i.e., backpropagation-like training methods and plasticity-based learning methods. The former methods are dependent on energy-inefficient real-valued computation and non-local transmission, as also required in artificial neural networks (ANNs), whereas the latter are either considered to be biologically implausible or exhibit poor performance. Hence, biologically plausible (bio-plausible) high-performance supervised learning (SL) methods for SNNs remain deficient. In this paper, we proposed a novel bio-plausible SNN model for SL based on the symmetric spike-timing dependent plasticity (sym-STDP) rule found in neuroscience. By combining the sym-STDP rule with bio-plausible synaptic scaling and intrinsic plasticity of the dynamic threshold, our SNN model implemented SL well and achieved good performance in the benchmark recognition task (MNIST dataset). To reveal the underlying mechanism of our SL model, we visualized both layer-based activities and synaptic weights using the t-distributed stochastic neighbor embedding (t-SNE) method after training and found that they were well clustered, thereby demonstrating excellent classification ability. Furthermore, to verify the robustness of our model, we trained it on another more realistic dataset (Fashion-MNIST), which also showed good performance. As the learning rules were bio-plausible and based purely on local spike events, our model could be easily applied to neuromorphic hardware for online training and may be helpful for understanding SL information processing at the synaptic level in biological neural systems.


Assuntos
Potenciais de Ação/fisiologia , Plasticidade Neuronal/fisiologia , Neurônios/fisiologia , Reconhecimento Automatizado de Padrão , Aprendizado de Máquina Supervisionado , Humanos
9.
BMC Bioinformatics ; 20(1): 619, 2019 Dec 02.
Artigo em Inglês | MEDLINE | ID: mdl-31791234

RESUMO

BACKGROUND: Expression in H-sapiens plays a remarkable role when it comes to social communication. The identification of this expression by human beings is relatively easy and accurate. However, achieving the same result in 3D by machine remains a challenge in computer vision. This is due to the current challenges facing facial data acquisition in 3D; such as lack of homology and complex mathematical analysis for facial point digitization. This study proposes facial expression recognition in human with the application of Multi-points Warping for 3D facial landmark by building a template mesh as a reference object. This template mesh is thereby applied to each of the target mesh on Stirling/ESRC and Bosphorus datasets. The semi-landmarks are allowed to slide along tangents to the curves and surfaces until the bending energy between a template and a target form is minimal and localization error is assessed using Procrustes ANOVA. By using Principal Component Analysis (PCA) for feature selection, classification is done using Linear Discriminant Analysis (LDA). RESULT: The localization error is validated on the two datasets with superior performance over the state-of-the-art methods and variation in the expression is visualized using Principal Components (PCs). The deformations show various expression regions in the faces. The results indicate that Sad expression has the lowest recognition accuracy on both datasets. The classifier achieved a recognition accuracy of 99.58 and 99.32% on Stirling/ESRC and Bosphorus, respectively. CONCLUSION: The results demonstrate that the method is robust and in agreement with the state-of-the-art results.


Assuntos
Algoritmos , Expressão Facial , Imagem Tridimensional , Reconhecimento Automatizado de Padrão , Análise de Variância , Bases de Dados como Assunto , Análise Discriminante , Humanos , Análise de Componente Principal
10.
BMC Bioinformatics ; 20(1): 726, 2019 Dec 18.
Artigo em Inglês | MEDLINE | ID: mdl-31852427

RESUMO

BACKGROUND: Current approaches to identifying drug-drug interactions (DDIs), include safety studies during drug development and post-marketing surveillance after approval, offer important opportunities to identify potential safety issues, but are unable to provide complete set of all possible DDIs. Thus, the drug discovery researchers and healthcare professionals might not be fully aware of potentially dangerous DDIs. Predicting potential drug-drug interaction helps reduce unanticipated drug interactions and drug development costs and optimizes the drug design process. Methods for prediction of DDIs have the tendency to report high accuracy but still have little impact on translational research due to systematic biases induced by networked/paired data. In this work, we aimed to present realistic evaluation settings to predict DDIs using knowledge graph embeddings. We propose a simple disjoint cross-validation scheme to evaluate drug-drug interaction predictions for the scenarios where the drugs have no known DDIs. RESULTS: We designed different evaluation settings to accurately assess the performance for predicting DDIs. The settings for disjoint cross-validation produced lower performance scores, as expected, but still were good at predicting the drug interactions. We have applied Logistic Regression, Naive Bayes and Random Forest on DrugBank knowledge graph with the 10-fold traditional cross validation using RDF2Vec, TransE and TransD. RDF2Vec with Skip-Gram generally surpasses other embedding methods. We also tested RDF2Vec on various drug knowledge graphs such as DrugBank, PharmGKB and KEGG to predict unknown drug-drug interactions. The performance was not enhanced significantly when an integrated knowledge graph including these three datasets was used. CONCLUSION: We showed that the knowledge embeddings are powerful predictors and comparable to current state-of-the-art methods for inferring new DDIs. We addressed the evaluation biases by introducing drug-wise and pairwise disjoint test classes. Although the performance scores for drug-wise and pairwise disjoint seem to be low, the results can be considered to be realistic in predicting the interactions for drugs with limited interaction information.


Assuntos
Interações de Medicamentos , Teorema de Bayes , Conhecimento , Modelos Logísticos , Reconhecimento Automatizado de Padrão
11.
Neural Netw ; 120: 143-157, 2019 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-31575431

RESUMO

Sparse data is known to pose challenges to cluster analysis, as the similarity between data tends to be ill-posed in the high-dimensional Hilbert space. Solutions in the literature typically extend either k-means or spectral clustering with additional steps on representation learning and/or feature weighting. However, adding these usually introduces new parameters and increases computational cost, thus inevitably lowering the robustness of these algorithms when handling massive ill-represented data. To alleviate these issues, this paper presents a class of self-organizing neural networks, called the salience-aware adaptive resonance theory (SA-ART) model. SA-ART extends Fuzzy ART with measures for cluster-wise salient feature modeling. Specifically, two strategies, i.e. cluster space matching and salience feature weighting, are incorporated to alleviate the side-effect of noisy features incurred by high dimensionality. Additionally, cluster weights are bounded by the statistical means and minimums of the samples therein, making the learning rate also self-adaptable. Notably, SA-ART allows clusters to have their own sets of self-adaptable parameters. It has the same time complexity of Fuzzy ART and does not introduce additional hyperparameters that profile cluster properties. Comparative experiments have been conducted on the ImageNet and BlogCatalog datasets, which are large-scale and include sparsely-represented data. The results show that, SA-ART achieves 51.8% and 18.2% improvement over Fuzzy ART, respectively. While both have a similar time cost, SA-ART converges faster and can reach a better local minimum. In addition, SA-ART consistently outperforms six other state-of-the-art algorithms in terms of precision and F1 score. More importantly, it is much faster and exhibits stronger robustness to large and complex data.


Assuntos
Reconhecimento Automatizado de Padrão/métodos , Big Data , Análise por Conglomerados , Lógica Fuzzy , Mídias Sociais
13.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi ; 36(5): 856-861, 2019 Oct 25.
Artigo em Chinês | MEDLINE | ID: mdl-31631636

RESUMO

Brain-computer interface (BCI) provides a direct communicating and controlling approach between the brain and surrounding environment, which attracts a wide range of interest in the fields of brain science and artificial intelligence. It is a core to decode the electroencephalogram (EEG) feature in the BCI system. The decoding efficiency highly depends on the feature extraction and feature classification algorithms. In this paper, we first introduce the commonly-used EEG features in the BCI system. Then we introduce the basic classical algorithms and their advanced versions used in the BCI system. Finally, we present some new BCI algorithms proposed in recent years. We hope this paper can spark fresh thinking for the research and development of high-performance BCI system.


Assuntos
Algoritmos , Interfaces Cérebro-Computador , Eletroencefalografia , Reconhecimento Automatizado de Padrão , Encéfalo/fisiologia , Humanos
14.
Sensors (Basel) ; 19(20)2019 Oct 14.
Artigo em Inglês | MEDLINE | ID: mdl-31615162

RESUMO

Feature extraction, as an important method for extracting useful information from surfaceelectromyography (SEMG), can significantly improve pattern recognition accuracy. Time andfrequency analysis methods have been widely used for feature extraction, but these methods analyzeSEMG signals only from the time or frequency domain. Recent studies have shown that featureextraction based on time-frequency analysis methods can extract more useful information fromSEMG signals. This paper proposes a novel time-frequency analysis method based on the Stockwelltransform (S-transform) to improve hand movement recognition accuracy from forearm SEMGsignals. First, the time-frequency analysis method, S-transform, is used for extracting a feature vectorfrom forearm SEMG signals. Second, to reduce the amount of calculations and improve the runningspeed of the classifier, principal component analysis (PCA) is used for dimensionality reduction of thefeature vector. Finally, an artificial neural network (ANN)-based multilayer perceptron (MLP) is usedfor recognizing hand movements. Experimental results show that the proposed feature extractionbased on the S-transform analysis method can improve the class separability and hand movementrecognition accuracy compared with wavelet transform and power spectral density methods.


Assuntos
Algoritmos , Eletromiografia , Mãos/fisiologia , Movimento/fisiologia , Reconhecimento Automatizado de Padrão , Adulto , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Análise de Ondaletas
16.
Neural Netw ; 119: 323-331, 2019 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-31499356

RESUMO

In many deep neural networks for pattern recognition, the input pattern is classified in the deepest layer based on features extracted through intermediate layers. IntVec (interpolating-vector) is known to be a powerful method for this process of classification. Although the recognition error can be made much smaller by IntVec than by WTA (winner-take-all) or even by SVM (support vector machines), IntVec requires a large computational cost. This paper proposes a new method, by which the computational cost by IntVec can be reduced drastically without increasing the recognition error. Although we basically use IntVec for recognition, we substitute it with WTA, which requires much smaller computational cost, under a certain condition. To be more specific, we first try to classify the input vector using WTA. If a class is a complete loser by WTA, we judge it also a loser by IntVec and omit the calculation of IntVec for that class. If a class is an unrivaled winner by WTA, calculation of IntVec itself can be omitted for all classes.


Assuntos
Reconhecimento Automatizado de Padrão , Máquina de Vetores de Suporte
17.
Database (Oxford) ; 20192019 01 01.
Artigo em Inglês | MEDLINE | ID: mdl-31392324

RESUMO

We introduce Semantic Ontology-Controlled application for web Content Management Systems (SOCCOMAS), a development framework for FAIR ('findable', 'accessible', 'interoperable', 'reusable') Semantic Web Content Management Systems (S-WCMSs). Each S-WCMS run by SOCCOMAS has its contents managed through a corresponding knowledge base that stores all data and metadata in the form of semantic knowledge graphs in a Jena tuple store. Automated procedures track provenance, user contributions and detailed change history. Each S-WCMS is accessible via both a graphical user interface (GUI), utilizing the JavaScript framework AngularJS, and a SPARQL endpoint. As a consequence, all data and metadata are maximally findable, accessible, interoperable and reusable and comply with the FAIR Guiding Principles. The source code of SOCCOMAS is written using the Semantic Programming Ontology (SPrO). SPrO consists of commands, attributes and variables, with which one can describe an S-WCMS. We used SPrO to describe all the features and workflows typically required by any S-WCMS and documented these descriptions in a SOCCOMAS source code ontology (SC-Basic). SC-Basic specifies a set of default features, such as provenance tracking and publication life cycle with versioning, which will be available in all S-WCMS run by SOCCOMAS. All features and workflows specific to a particular S-WCMS, however, must be described within an instance source code ontology (INST-SCO), defining, e.g. the function and composition of the GUI, with all its user interactions, the underlying data schemes and representations and all its workflow processes. The combination of descriptions in SC-Basic and a given INST-SCO specify the behavior of an S-WCMS. SOCCOMAS controls this S-WCMS through the Java-based middleware that accompanies SPrO, which functions as an interpreter. Because of the ontology-controlled design, SOCCOMAS allows easy customization with a minimum of technical programming background required, thereby seamlessly integrating conventional web page technologies with semantic web technologies. SOCCOMAS and the Java Interpreter are available from (https://github.com/SemanticProgramming).


Assuntos
Reconhecimento Automatizado de Padrão , Linguagens de Programação , Web Semântica , Interface Usuário-Computador
18.
J Med Syst ; 43(9): 302, 2019 Aug 09.
Artigo em Inglês | MEDLINE | ID: mdl-31396722

RESUMO

The aim of this work is to develop a Computer-Aided-Brain-Diagnosis (CABD) system that can determine if a brain scan shows signs of Alzheimer's disease. The method utilizes Magnetic Resonance Imaging (MRI) for classification with several feature extraction techniques. MRI is a non-invasive procedure, widely adopted in hospitals to examine cognitive abnormalities. Images are acquired using the T2 imaging sequence. The paradigm consists of a series of quantitative techniques: filtering, feature extraction, Student's t-test based feature selection, and k-Nearest Neighbor (KNN) based classification. Additionally, a comparative analysis is done by implementing other feature extraction procedures that are described in the literature. Our findings suggest that the Shearlet Transform (ST) feature extraction technique offers improved results for Alzheimer's diagnosis as compared to alternative methods. The proposed CABD tool with the ST + KNN technique provided accuracy of 94.54%, precision of 88.33%, sensitivity of 96.30% and specificity of 93.64%. Furthermore, this tool also offered an accuracy, precision, sensitivity and specificity of 98.48%, 100%, 96.97% and 100%, respectively, with the benchmark MRI database.


Assuntos
Doença de Alzheimer/diagnóstico por imagem , Encéfalo/patologia , Diagnóstico por Computador/métodos , Reconhecimento Automatizado de Padrão/métodos , Doença de Alzheimer/classificação , Humanos , Interpretação de Imagem Assistida por Computador/métodos , Imagem por Ressonância Magnética/métodos
19.
Med Hypotheses ; 129: 109242, 2019 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-31371092

RESUMO

Microaneurysms are lesions in the shape of small circular dilations which result from thinning in peripheral retinal blood vessels due to diabetes and increasing intra-retinal blood pressure. Because it is considered as the most important clinical finding in the diagnosis of diabetic retinopathy, accurate detection of these lesions bear utmost importance in the early diagnosis of diabetic retinopathy. The present study aims to accurately, effectively and automatically detect microaneurysms which are difficult to detect in color fundus images in early stage. To this aim, ant colony algorithm, which is an important optimization method, was used instead of conventional image processing techniques. First, retinal vascular structure was extracted from color fundus images in Messidor and DiaretDB1 data sets. Afterwards, the segmentation of microaneurysms was effectively carried out using ant colony algorithm. The same procedure was also applied to five different image processing and clustering algorithms (watershed, random walker, k-means, maximum entropy and region growing) in order to compare the performance of the proposed method with other methods. Microaneurysm images manually detected by a specialist eye doctor were used to measure the performances of above-mentioned methods. The similarities among microaneurysms which were automatically and manually segmented were tested using Dice and Jaccard similarity index values. Dice index values obtained from the study vary between 0.52 and 0.98 in maximum entropy, 0.55 and 0.88 in watershed, 0.75 and 0.86 in region growing, 0.55 and 0.78 in k-means, and 0.66 and 0.83 in random walker, and 0.81 and 0.9 in ant colony. Similar performance values were also obtained in Jaccard index. The results show that different performances were observed in the conventional segmentation of microaneurysms depending on the image quality. On the other hand, the ant colony based method proposed in this paper displays a more stabilized and higher performance irrespective of image contrast. Therefore, it is evident that the proposed method successfully detects microaneurysms even in low quality images, thus helping specialists diagnose them in an easier way.


Assuntos
Retinopatia Diabética/diagnóstico por imagem , Diagnóstico por Computador/métodos , Processamento de Imagem Assistida por Computador/métodos , Microaneurisma/diagnóstico por imagem , Reconhecimento Automatizado de Padrão/métodos , Algoritmos , Cor , Diabetes Mellitus/fisiopatologia , Fundo de Olho , Humanos , Modelos Estatísticos , Reprodutibilidade dos Testes , Vasos Retinianos/patologia
20.
PLoS Biol ; 17(8): e3000388, 2019 08.
Artigo em Inglês | MEDLINE | ID: mdl-31398189

RESUMO

Methods for measuring the properties of individual cells within their native 3D environment will enable a deeper understanding of embryonic development, tissue regeneration, and tumorigenesis. However, current methods for segmenting nuclei in 3D tissues are not designed for situations in which nuclei are densely packed, nonspherical, or heterogeneous in shape, size, or texture, all of which are true of many embryonic and adult tissue types as well as in many cases for cells differentiating in culture. Here, we overcome this bottleneck by devising a novel method based on labelling the nuclear envelope (NE) and automatically distinguishing individual nuclei using a tree-structured ridge-tracing method followed by shape ranking according to a trained classifier. The method is fast and makes it possible to process images that are larger than the computer's memory. We consistently obtain accurate segmentation rates of >90%, even for challenging images such as mid-gestation embryos or 3D cultures. We provide a 3D editor and inspector for the manual curation of the segmentation results as well as a program to assess the accuracy of the segmentation. We have also generated a live reporter of the NE that can be used to track live cells in 3 dimensions over time. We use this to monitor the history of cell interactions and occurrences of neighbour exchange within cultures of pluripotent cells during differentiation. We provide these tools in an open-access user-friendly format.


Assuntos
Processamento de Imagem Assistida por Computador/métodos , Imagem Tridimensional/métodos , Reconhecimento Automatizado de Padrão/métodos , Algoritmos , Animais , Núcleo Celular/fisiologia , Corantes Fluorescentes , Humanos , Indóis , Lamina Tipo B , Membrana Nuclear/metabolismo , Membrana Nuclear/fisiologia
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA