Signal classification of submerged aquatic vegetation based on the hemispherical-conical reflectance factor spectrum shape in the yellow and red regions

The water column overlying the submerged aquatic vegetation (SAV) canopy presents difficulties when using remote sensing images for mapping such vegetation. Inherent and apparent water optical properties and its optically active components, which are commonly present in natural waters, in addition to the water column height over the canopy, and plant characteristics are some of the factors that affect the signal from SAV mainly due to its strong energy absorption in the near-infrared. By considering these interferences, a hypothesis was developed that the vegetation signal is better conserved and less absorbed by the water column in certain intervals of the visible region of the spectrum; as a consequence, it is possible to distinguish the SAV signal. To distinguish the signal from SAV, two types of classification approaches were selected. Both of these methods consider the hemispherical-conical reflectance factor (HCRF) spectrum shape, although one type was supervised and the other one was not. The first method adopts cluster analysis and uses the parameters of the band (absorption, asymmetry, height and width) obtained by continuum removal as the input of the classification. The spectral angle mapper (SAM) was adopted as the supervised classification approach. Both approaches tested different wavelength intervals in the visible and near-infrared spectra. It was demonstrated that the 585 to 685-nm interval, corresponding to the green, yellow and red wavelength bands, offered the best results in both classification approaches. However, SAM classification showed better results relative to cluster analysis and correctly separated all spectral curves with or without SAV. Based on this research, it can be concluded that it is possible to discriminate areas with and without SAV using remote sensing. © 2013 by the authors; licensee MDPI, Basel, Switzerland.

Topological K-classification of finitely determined map germs

We consider smooth finitely C 0-K-determined map germs f: (ℝn, 0) → (ℝp, 0) and we look at the classification under C 0-K-equivalence. The main tool is the homotopy type of the link, which is obtained by intersecting the image of f with a small enough sphere centered at the origin. When f -1(0) = {0}, the link is a smooth map between spheres and f is C 0-K-equivalent to the cone of its link. When f -1(0) ≠ {0}, we consider a link diagram, which contains some extra information, but again f is C 0-K-equivalent to the generalized cone. As a consequence, we deduce some known results due to Nishimura (for n = p) or the first named author (for n < p). We also prove some new results of the same nature. © 2012 Springer Science+Business Media Dordrecht.

Automatic segmentation and classification of human intestinal parasites from microscopy images

Human intestinal parasites constitute a problem in most tropical countries, causing death or physical and mental disorders. Their diagnosis usually relies on the visual analysis of microscopy images, with error rates that may range from moderate to high. The problem has been addressed via computational image analysis, but only for a few species and images free of fecal impurities. In routine, fecal impurities are a real challenge for automatic image analysis. We have circumvented this problem by a method that can segment and classify, from bright field microscopy images with fecal impurities, the 15 most common species of protozoan cysts, helminth eggs, and larvae in Brazil. Our approach exploits ellipse matching and image foresting transform for image segmentation, multiple object descriptors and their optimum combination by genetic programming for object representation, and the optimum-path forest classifier for object recognition. The results indicate that our method is a promising approach toward the fully automation of the enteroparasitosis diagnosis. © 2012 IEEE.

Padrões neuropatológicos nas substâncias branca e cinzenta revelados por tomografia computadorizada ou ressonância magnética e déficits neurológicos correspondentes em crianças e com encefalopatia crônica não progressiva da infância

A Encefalopatia Crônica Não Progressiva da Infância (ECNP) é a sequela neurológica com maior comprometimento motor para a criança, e continua sendo na atualidade a hipóxicoisquemia perinatal a maior causa de lesão cerebral. É conhecida como Paralisia Cerebral, sendo definida por uma sequela de agressão encefálica, caracterizada, principalmente, por um transtorno persistente, mas não invariável do tônus, da postura e do movimento, que aparece na primeira infância. A caracterização da ECNP se faz considerando as condições anatômicas, etiológicas, semiológicas e não evolutiva. Neste estudo adotou-se a classificação baseada em aspectos anatômicos e clínicos, que enfatizam o sintoma motor, enquanto elemento principal do quadro clínico. A neuroimagem tem fundamental importância para o diagnóstico e prognóstico de lesões cerebrais, exercendo a importante função de descartar ou confirmar a presença de lesões em recém-nascidos e nas crianças com alterações no desenvolvimento. A Tomografia Cerebral (TAC) e a Ressonância Magnética do Crânio (RM) vêm desempenhando enorme papel para o estudo dos vários tecidos que constituem o sistema nervoso. Assim este estudo teve o objetivo geral de avaliar os padrões neuropatológicos nas substâncias branca e cinzenta, obtidos por TAC ou RM de Crânio, de pacientes com história clínica de ECNP hipóxico-isquêmica perinatal, correlacionando os dados obtidos por neuroimagem com os padrões motores obtidos por exame clínico-neurológico. Foram obedecidas as normas vigentes para estudo em seres humanos impostas pela Resolução CNS 196/96, submetida ao Comitê de Ética e Pesquisa da Plataforma Brasil sob o Nº 112168. A população foi constituída por pacientes com idade de zero a sete anos, de ambos os sexos, atendidos no Ambulatório de Paralisia Cerebral do Projeto Caminhar do Hospital Universitário Bettina Ferro de Souza (HUBFS), com diagnóstico de ECNP. A amostra do estudo foi composta por 15 crianças com diagnóstico de ECNP por Hipóxia neonatal. Para o diagnóstico radiológico em neuroimagem foram utilizados os dados dos laudos da TAC e da RM de Crânio. A avaliação clínico-neurológica utilizou para a avaliação do movimento o modelo da escala Gross Motor Function Classification System (GMFCS E&R), elaborada por Palisano, que gradua a criança em cinco níveis no qual o Nível I corresponde à normalidade e o Nível V a maior gravidade de limitação. Das 15 crianças avaliadas quanto ao movimento e a relação do Nível de Motricidade pela GMFCS E&R 05 crianças apresentavam nível V, 04 crianças nível IV, 05 crianças nível III e 01 criança nível II. Quanto ao imageamento cerebral 46% realizaram TAC e 54% RM do Crânio. A RM de Crânio apresentou-se neste estudo como a imagem de eleição, pois das 8 crianças que realizaram o exame, 6 apresentavam alterações. Ficou evidente que o exame por imagem de eleição para a criança que apresenta Encefalopatia Crônica não Progressiva é a RM de Crânio, podendo se adotar como protocolo para a conclusão diagnóstica, evitando expor a criança a uma carga elevada de RX como ocorre na TAC, e ainda, evitando gastos desnecessários para a saúde pública.

EEG signal classification for epilepsy diagnosis via optimum path forest - A systematic assessment

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Optimum-Path Forest Applied for Breast Masses Classification

In Computer-Aided Diagnosis-based schemes in mammography analysis each module is interconnected, which directly affects the system operation as a whole. The identification of mammograms with and without masses is highly needed to reduce the false positive rates regarding the automatic selection of regions of interest for further image segmentation. This study aims to evaluate the performance of three techniques in classifying regions of interest as containing masses or without masses (without clinical findings), as well as the main contribution of this work is to introduce the Optimum-Path Forest (OPF) classifier in this context, which has never been done so far. Thus, we have compared OPF against with two sorts of neural networks in a private dataset composed by 120 images: Radial Basis Function and Multilayer Perceptron (MLP). Texture features have been used for such purpose, and the experiments have demonstrated that MLP networks have been slightly better than OPF, but the former is much faster, which can be a suitable tool for real-time recognition systems.

Classification of histological images based on the stationary wavelet transform

Non-Hodgkin lymphomas are of many distinct types, and different classification systems make it difficult to diagnose them correctly. Many of these systems classify lymphomas only based on what they look like under a microscope. In 2008 the World Health Organisation (WHO) introduced the most recent system, which also considers the chromosome features of the lymphoma cells and the presence of certain proteins on their surface. The WHO system is the one that we apply in this work. Herewith we present an automatic method to classify histological images of three types of non-Hodgkin lymphoma. Our method is based on the Stationary Wavelet Transform (SWT), and it consists of three steps: 1) extracting sub-bands from the histological image through SWT, 2) applying Analysis of Variance (ANOVA) to clean noise and select the most relevant information, 3) classifying it by the Support Vector Machine (SVM) algorithm. The kernel types Linear, RBF and Polynomial were evaluated with our method applied to 210 images of lymphoma from the National Institute on Aging. We concluded that the following combination led to the most relevant results: detail sub-band, ANOVA and SVM with Linear and RBF kernels.

Patch-based local histograms and contour estimation for static foreground classification

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

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.