Multi-q pattern analysis: A case study in image classification

This paper compares the effectiveness of the Tsallis entropy over the classic Boltzmann-Gibbs-Shannon entropy for general pattern recognition, and proposes a multi-q approach to improve pattern analysis using entropy. A series of experiments were carried out for the problem of classifying image patterns. Given a dataset of 40 pattern classes, the goal of our image case study is to assess how well the different entropies can be used to determine the class of a newly given image sample. Our experiments show that the Tsallis entropy using the proposed multi-q approach has great advantages over the Boltzmann-Gibbs-Shannon entropy for pattern classification, boosting image recognition rates by a factor of 3. We discuss the reasons behind this success, shedding light on the usefulness of the Tsallis entropy and the multi-q approach. (C) 2012 Elsevier B.V. All rights reserved.

Smart histogram analysis applied to the skull-stripping problem in T1-weighted MRI

In this paper we address the "skull-stripping" problem in 3D MR images. We propose a new method that employs an efficient and unique histogram analysis. A fundamental component of this analysis is an algorithm for partitioning a histogram based on the position of the maximum deviation from a Gaussian fit. In our experiments we use a comprehensive image database, including both synthetic and real MRI. and compare our method with other two well-known methods, namely BSE and BET. For all datasets we achieved superior results. Our method is also highly independent of parameter tuning and very robust across considerable variations of noise ratio.

Classificação híbrida: pixel a pixel e baseada em objetos para o monitoramento da condição da superfície dos pavimentos rodoviários

Monitorar a condição de uso de toda a extensão das rodovias brasileiras é tarefa dispendiosa e demorada. Este trabalho trata de novas técnicas que permitem o levantamento da condição da superfície dos pavimentos rodoviários de forma ágil utilizando imagens hiperespectrais de sensor digital aeroembarcado. Nos últimos anos, um número crescente de imagens de alta resolução espacial tem surgido no mercado mundial com o aparecimento dos novos satélites e sensores aeroembarcados de sensoriamento remoto. Propõe-se uma metodologia para identificação dos pavimentos asfálticos e classificação das principais ocorrências dos defeitos na superfície do pavimento. A primeira etapa da metodologia é a identificação da superfície asfáltica na imagem, utilizando uma classificação híbrida baseada inicialmente em pixel e depois refinada por objetos. A segunda etapa da metodologia é a identificação e classificação das ocorrências dos principais defeitos nos pavimentos flexíveis que são observáveis nas imagens de alta resolução espacial. Esta última etapa faz uso intensivo das novas técnicas de classificação de imagens baseadas em objetos. O resultado final é a geração de índices da condição da superfície do pavimento a partir das imagens que possam ser comparados com os indicadores vigentes da condição da superfície do pavimento já normatizados pelos órgãos competentes no país.

Classification of polymers insulators hydrophobicity basead on digital image processing

Although the hydrophobicity is usually an arduous parameter to be determined in the field, it has been pointed out as a good option to monitor aging of polymeric outdoor insulators. Concerning this purpose, digital image processing of photos taken from wet insulators has been the main technique nowadays. However, important challenges on this technique still remain to be overcome, such as; images from non-controlled illumination conditions can interfere on analyses and no existence of standard surfaces with different levels of hydrophobicity. In this paper, the photo image samples were digitally filtered to reduce the illumination influence, and hydrophobic surface samples were prepared from wetting silicon surfaces with solution of water-alcohol. Furthermore norevious studies triying to quantify and relate these properties in a mathematical function were found, that could be used in the field by the electrical companies. Based on such considerations, high quality images of countless hydrophobic surfaces were obtained and three different image processing methodologies, the fractal dimension and two Haralick textures descriptors, entropy and homogeneity, associated with several digital filters, were compared. The entropy parameter Haralick's descriptors filtered with the White Top-Hat filter presented the best result to classify the hydrophobicity.

0.1T magnetic resonance image in the study of experimental hydrocephalus in rats. Accuracy of the method in the measurements of the ventricular size

PURPOSE: To investigate the accuracy of 1.0T Magnetic Resonance Imaging (MRI) to measure the ventricular size in experimental hydrocephalus in pup rats. METHODS: Wistar rats were subjected to hydrocephalus by intracisternal injection of 20% kaolin (n=13). Ten rats remained uninjected to be used as controls. At the endpoint of experiment animals were submitted to MRI of brain and killed. The ventricular size was assessed using three measures: ventricular ratio (VR), the cortical thickness (Cx) and the ventricles area (VA), performed on photographs of anatomical sections and MRI. RESULTS: The images obtained through MR present enough quality to show the lateral ventricular cavities but not to demonstrate the difference between the cortex and the white matter, as well as the details of the deep structures of the brain. There were no statistically differences between the measures on anatomical sections and MRI of VR and Cx (p=0.9946 and p=0.5992, respectively). There was difference between VA measured on anatomical sections and MRI (p<0.0001). CONCLUSION: The parameters obtained through 1.0T MRI were sufficient in quality to individualize the ventricular cavities and the cerebral cortex, and to calculate the ventricular ratio in hydrocephalus rats when compared to their respective anatomic slice.

Intraoperative ultrasonography for presumed brain metastases: a case series study

Brain metastases (BM) are one of the most common intracranial tumors and surgical treatment can improve both the functional outcomes and patient survival, particularly when systemic disease is controlled. Image-guided BM resection using intraoperative exams, such as intraoperative ultrasound (IOUS), can lead to better surgical results. Methods: To evaluate the use of IOUS for BM resection, 20 consecutives patients were operated using IOUS to locate tumors, identify their anatomical relationships and surgical cavity after resection. Technical difficulties, complications, recurrence and survival rates were noted. Results: IOUS proved effective for locating, determining borders and defining the anatomical relationships of BM, as well as to identify incomplete tumor resection. No complications related to IOUS were seen. Conclusion: IOUS is a practical supporting method for the resection of BM, but further studies comparing this method with other intraoperative exams are needed to evaluate its actual contribution and reliability.

Frequent ATRX, CIC, FUBP1 and IDH1 mutations refine the classification of malignant gliomas

Mutations in the critical chromatin modifier ATRX and mutations in CIC and FUBP1, which are potent regulators of cell growth, have been discovered in specific subtypes of gliomas, the most common type of primary malignant brain tumors. However, the frequency of these mutations in many subtypes of gliomas, and their association with clinical features of the patients, is poorly understood. Here we analyzed these loci in 363 brain tumors. ATRX is frequently mutated in grade II-III astrocytomas (71%), oligoastrocytomas (68%), and secondary glioblastomas (57%), and ATRX mutations are associated with IDH1 mutations and with an alternative lengthening of telomeres phenotype. CIC and FUBP1 mutations occurred frequently in oligodendrogliomas (46% and 24%, respectively) but rarely in astrocytomas or oligoastrocytomas (<10%). This analysis allowed us to define two highly recurrent genetic signatures in gliomas: IDH1/ATRX (I-A) and IDH1/CIC/FUBP1 (I-CF). Patients with I-CF gliomas had a significantly longer median overall survival (96 months) than patients with I-A gliomas (51 months) and patients with gliomas that did not harbor either signature (13 months). The genetic signatures distinguished clinically distinct groups of oligoastrocytoma patients, which usually present a diagnostic challenge, and were associated with differences in clinical outcome even among individual tumor types. In addition to providing new clues about the genetic alterations underlying gliomas, the results have immediate clinical implications, providing a tripartite genetic signature that can serve as a useful adjunct to conventional glioma classification that may aid in prognosis, treatment selection, and therapeutic trial design.

Near-Term Fetal Hypoxia-Ischemia in Rabbits MRI Can Predict Muscle Tone Abnormalities and Deep Brain Injury

Background and Purpose-The pattern of antenatal brain injury varies with gestational age at the time of insult. Deep brain nuclei are often injured at older gestational ages. Having previously shown postnatal hypertonia after preterm fetal rabbit hypoxia-ischemia, the objective of this study was to investigate the causal relationship between the dynamic regional pattern of brain injury on MRI and the evolution of muscle tone in the near-term rabbit fetus. Methods-Serial MRI was performed on New Zealand white rabbit fetuses to determine equipotency of fetal hypoxia-ischemia during uterine ischemia comparing 29 days gestation (E29, 92% gestation) with E22 and E25. E29 postnatal kits at 4, 24, and 72 hours after hypoxia-ischemia underwent T2- and diffusion-weighted imaging. Quantitative assessments of tone were made serially using a torque apparatus in addition to clinical assessments. Results-Based on the brain apparent diffusion coefficient, 32 minutes of uterine ischemia was selected for E29 fetuses. At E30, 58% of the survivors manifested hind limb hypotonia. By E32, 71% of the hypotonic kits developed dystonic hypertonia. Marked and persistent apparent diffusion coefficient reduction in the basal ganglia, thalamus, and brain stem was predictive of these motor deficits. Conclusions-MRI observation of deep brain injury 6 to 24 hours after near-term hypoxia-ischemia predicts dystonic hypertonia postnatally. Torque-displacement measurements indicate that motor deficits in rabbits progressed from initial hypotonia to hypertonia, similar to human cerebral palsy, but in a compressed timeframe. The presence of deep brain injury and quantitative shift from hypo-to hypertonia may identify patients at risk for developing cerebral palsy. (Stroke. 2012;43:2757-2763.)

Network-based high level data classification

Traditional supervised data classification considers only physical features (e. g., distance or similarity) of the input data. Here, this type of learning is called low level classification. On the other hand, the human (animal) brain performs both low and high orders of learning and it has facility in identifying patterns according to the semantic meaning of the input data. Data classification that considers not only physical attributes but also the pattern formation is, here, referred to as high level classification. In this paper, we propose a hybrid classification technique that combines both types of learning. The low level term can be implemented by any classification technique, while the high level term is realized by the extraction of features of the underlying network constructed from the input data. Thus, the former classifies the test instances by their physical features or class topologies, while the latter measures the compliance of the test instances to the pattern formation of the data. Our study shows that the proposed technique not only can realize classification according to the pattern formation, but also is able to improve the performance of traditional classification techniques. Furthermore, as the class configuration's complexity increases, such as the mixture among different classes, a larger portion of the high level term is required to get correct classification. This feature confirms that the high level classification has a special importance in complex situations of classification. Finally, we show how the proposed technique can be employed in a real-world application, where it is capable of identifying variations and distortions of handwritten digit images. As a result, it supplies an improvement in the overall pattern recognition rate.

Computerized brain tumor segmentation in magnetic resonance imaging

OBJECTIVE: To propose an automatic brain tumor segmentation system. METHODS: The system used texture characteristics as its main source of information for segmentation. RESULTS: The mean correct match was 94% of correspondence between the segmented areas and ground truth. CONCLUSION: Final results showed that the proposed system was able to find and delimit tumor areas without requiring any user interaction.

Brain activity and medical diagnosis: an EEG study

Abstract Background Despite new brain imaging techniques that have improved the study of the underlying processes of human decision-making, to the best of our knowledge, there have been very few studies that have attempted to investigate brain activity during medical diagnostic processing. We investigated brain electroencephalography (EEG) activity associated with diagnostic decision-making in the realm of veterinary medicine using X-rays as a fundamental auxiliary test. EEG signals were analysed using Principal Components (PCA) and Logistic Regression Analysis Results The principal component analysis revealed three patterns that accounted for 85% of the total variance in the EEG activity recorded while veterinary doctors read a clinical history, examined an X-ray image pertinent to a medical case, and selected among alternative diagnostic hypotheses. Two of these patterns are proposed to be associated with visual processing and the executive control of the task. The other two patterns are proposed to be related to the reasoning process that occurs during diagnostic decision-making. Conclusions PCA analysis was successful in disclosing the different patterns of brain activity associated with hypothesis triggering and handling (pattern P1); identification uncertainty and prevalence assessment (pattern P3), and hypothesis plausibility calculation (pattern P2); Logistic regression analysis was successful in disclosing the brain activity associated with clinical reasoning success, and together with regression analysis showed that clinical practice reorganizes the neural circuits supporting clinical reasoning.

Combining fractal and deterministic walkers for texture analysis and classification

In this paper,we present a novel texture analysis method based on deterministic partially self-avoiding walks and fractal dimension theory. After finding the attractors of the image (set of pixels) using deterministic partially self-avoiding walks, they are dilated in direction to the whole image by adding pixels according to their relevance. The relevance of each pixel is calculated as the shortest path between the pixel and the pixels that belongs to the attractors. The proposed texture analysis method is demonstrated to outperform popular and state-of-the-art methods (e.g. Fourier descriptors, occurrence matrix, Gabor filter and local binary patterns) as well as deterministic tourist walk method and recent fractal methods using well-known texture image datasets.

Supervised classification of basaltic aggregate particles based on texture properties

The strength and durability of materials produced from aggregates (e.g., concrete bricks, concrete, and ballast) are critically affected by the weathering of the particles, which is closely related to their mineral composition. It is possible to infer the degree of weathering from visual features derived from the surface of the aggregates. By using sound pattern recognition methods, this study shows that the characterization of the visual texture of particles, performed by using texture-related features of gray scale images, allows the effective differentiation between weathered and nonweathered aggregates. The selection of the most discriminative features is also performed by taking into account a feature ranking method. The evaluation of the methodology in the presence of noise suggests that it can be used in stone quarries for automatic detection of weathered materials.