RESUMO
Semen analysis is the first step in the evaluation of an infertile couple. Within this process, an accurate and objective morphological analysis becomes more critical as it is based on the correct detection and segmentation of human sperm components. In this paper, we present an improved two-stage framework for detection and segmentation of human sperm head characteristics (including acrosome and nucleus) that uses three different color spaces. The first stage detects regions of interest that define sperm heads, using k-means, then candidate heads are refined using mathematical morphology. In the second stage, we work on each region of interest to segment accurately the sperm head as well as nucleus and acrosome, using clustering and histogram statistical analysis techniques. Our proposal is also characterized by being fully automatic, where a user intervention is not required. Our experimental evaluation shows that our proposed method outperforms the state-of-the-art. This is supported by the results of different evaluation metrics. In addition, we propose a gold-standard built with the cooperation of a referent expert in the field, aiming to compare methods for detecting and segmenting sperm cells. Our results achieve notable improvement getting above 98% in the sperm head detection process at the expense of having significantly fewer false positives obtained by the state-of-the-art method. Our results also show an accurate head, acrosome and nucleus segmentation achieving over 80% overlapping against hand-segmented gold-standard. Our method achieves higher Dice coefficient, lower Hausdorff distance and less dispersion with respect to the results achieved by the state-of-the-art method.
Assuntos
Aumento da Imagem/métodos , Interpretação de Imagem Assistida por Computador/normas , Microscopia/métodos , Microscopia/normas , Reconhecimento Automatizado de Padrão/normas , Análise do Sêmen/normas , Cabeça do Espermatozoide/ultraestrutura , Inteligência Artificial , Células Cultivadas , Chile , Humanos , Interpretação de Imagem Assistida por Computador/métodos , Masculino , Reconhecimento Automatizado de Padrão/métodos , Padrões de Referência , Reprodutibilidade dos Testes , Análise do Sêmen/métodos , Sensibilidade e EspecificidadeRESUMO
UNLABELLED: Physicians do not always keep the problem list accurate, complete and updated. OBJECTIVE: To analyze natural language processing (NLP) techniques and inference rules as strategies to maintain completeness and accuracy of the problem list in EHRs. METHODS: Non systematic literature review in PubMed, in the last 10 years. Strategies to maintain the EHRs problem list were analyzed in two ways: inputting and removing problems from the problem list. RESULTS: NLP and inference rules have acceptable performance for inputting problems into the problem list. No studies using these techniques for removing problems were published Conclusion: Both tools, NLP and inference rules have had acceptable results as tools for maintain the completeness and accuracy of the problem list.
Assuntos
Algoritmos , Registros Eletrônicos de Saúde/organização & administração , Armazenamento e Recuperação da Informação/métodos , Registros Médicos Orientados a Problemas , Processamento de Linguagem Natural , Garantia da Qualidade dos Cuidados de Saúde/métodos , Vocabulário Controlado , Inteligência Artificial , Reconhecimento Automatizado de Padrão/métodos , Reconhecimento Automatizado de Padrão/normas , Interface Usuário-ComputadorRESUMO
We study the reconstruction of visual stimuli from spike trains, representing the reconstructed stimulus by a Volterra series up to second order. We illustrate this procedure in a prominent example of spiking neurons, recording simultaneously from the two H1 neurons located in the lobula plate of the fly Chrysomya megacephala. The fly views two types of stimuli, corresponding to rotational and translational displacements. Second-order reconstructions require the manipulation of potentially very large matrices, which obstructs the use of this approach when there are many neurons. We avoid the computation and inversion of these matrices using a convenient set of basis functions to expand our variables in. This requires approximating the spike train four-point functions by combinations of two-point functions similar to relations, which would be true for gaussian stochastic processes. In our test case, this approximation does not reduce the quality of the reconstruction. The overall contribution to stimulus reconstruction of the second-order kernels, measured by the mean squared error, is only about 5% of the first-order contribution. Yet at specific stimulus-dependent instants, the addition of second-order kernels represents up to 100% improvement, but only for rotational stimuli. We present a perturbative scheme to facilitate the application of our method to weakly correlated neurons.
Assuntos
Potenciais de Ação/fisiologia , Dípteros/fisiologia , Neurônios/fisiologia , Lobo Óptico de Animais não Mamíferos/fisiologia , Processamento de Sinais Assistido por Computador , Vias Visuais/fisiologia , Algoritmos , Animais , Simulação por Computador , Eletrofisiologia/métodos , Redes Neurais de Computação , Distribuição Normal , Reconhecimento Automatizado de Padrão/normas , Processos EstocásticosRESUMO
We present an off-line cursive word recognition system based completely on neural networks: reading models and models of early visual processing. The first stage (normalization) preprocesses the input image in order to reduce letter position uncertainty; the second stage (feature extraction) is based on the feedforward model of orientation selectivity; the third stage (letter pre-recognition) is based on a convolutional neural network, and the last stage (word recognition) is based on the interactive activation model.