Fabio A. M. Cappabianco

Characterization of dual effects induced by antimicrobial peptides: Regulated cell death or membrane disruption

BACKGROUND Some reports describe lysis mechanisms by antimicrobial peptides (AMPs), while others describe the activation of regulated cell death. In this study, we compare the cell death-inducing activities of four β-hairpin AMPs (gomesin, protegrin, tachyplesin and polyphemusin II) along with their linear analogs in the human erythroleukemia K562 cell line to investigate the relationship between their structure and activity. METHODS K562 cells were exposed to AMPs. Morphological and biochemistry alterations were evaluated using light microscopy, confocal microscopy and flow cytometry. RESULTS Gomesin and protegrin displayed cytotoxic properties that their linear counterparts did not. Tachyplesin and polyphemusin II and also their linear analogs induced cell death. We were able to distinguish two ways in which these AMPs induced cell death. Lower concentrations of AMPs induced controlled cell death mechanisms. Gomesin, tachyplesin and linear-tachyplesin promoted apoptosis that was characterized by annexin labeling, sensitivity to Z-VAD, and caspase-3 activation, but was also inhibited by necrostatin-1. Gomesin and protegrin induced cell death was dependent on intracellular Ca2+ mechanisms and the participation of free radicals was observed in protegrin induced cell death. Polyphemusin II and its linear analog mainly induced necrosis. Conversely, treatment with higher concentrations of AMPs primarily resulted in cell membrane disruption, but with clearly different patterns of action for each AMP tested. CONCLUSION Different actions by β-hairpin AMPs were observed at low concentrations and at higher concentrations despite the structure similarity. GENERAL SIGNIFICANCE Controlled intracellular mechanism and direct membrane disruption were clearly distinguished helping to understand the real action of AMPs in mammalian cells.

Brain tissue MR-image segmentation via optimum-path forest clustering

We present an accurate and fast approach for MR-image segmentation of brain tissues, that is robust to anatomical variations and takes an average of less than 1min for completion on modern PCs. The method first corrects voxel values in the brain based on local estimations of the white-matter intensities. This strategy is inspired by other works, but it is simple, fast, and very effective. Tissue classification exploits a recent clustering approach based on the motion of optimum-path forest (OPF), which can find natural groups such that the absolute majority of voxels in each group belongs to the same class. First, a small random set of brain voxels is used for OPF clustering. Cluster labels are propagated to the remaining voxels, and then class labels are assigned to each group. The experiments used several datasets from three protocols (involving normal subjects, phantoms, and patients), two state-of-the-art approaches, and a novel methodology which finds the best choice of parameters for each method within the operational range of these parameters using a training dataset. The proposed method outperformed the compared approaches in speed, accuracy, and robustness.

Improving land cover classification through contextual-based optimum-path forest

A new contextual classifier based on optimum-path forest has been presented (OPF-MRF).A meta-heuristic-based framework has been proposed to estimate the contextual-dependent parameter for OPF-MRF.The proposed approach has been validated in the context of satellite image classification. Traditional machine learning algorithms very often assume statistically independent data samples. However, this is clearly not the case in remote sensing image applications, in which pixels present spatial and/or temporal dependencies. In this work, it has been presented an approach to improve land cover image classification using a contextual approach based on optimum-path forest (OPF) and the well-known Markov random fields (MRFs), hereinafter called OPF-MRF. In addition, it is also introduced a framework to the optimization of the amount of contextual information used by OPF-MRF. Experiments over high- and medium-resolution satellite (CBERS-2B, Landsat 5 TM, Ikonos-2 MS and Geoeye) and radar (ALOS-PALSAR) images covering the area of two Brazilian cities have shown the proposed approach can overcome several shortcomings related to standard OPF classification. In some cases, the proposed approach outperformed traditional OPF in about 9% of recognition rate, which is crucial for land cover classification.

Optimizing Optimum-Path Forest Classification for Huge Datasets

Traditional pattern recognition techniques can not handle the classification of large datasets with both efficiency and effectiveness. In this context, the Optimum-Path Forest (OPF) classifier was recently introduced, trying to achieve high recognition rates and low computational cost. Although OPF was much faster than Support Vector Machines for training, it was slightly slower for classification. In this paper, we present the Efficient OPF (EOPF), which is an enhanced and faster version of the traditional OPF, and validate it for the automatic recognition of white matter and gray matter in magnetic resonance images of the human brain.

Memory impairment is not necessarily related to seizure frequency in mesial temporal lobe epilepsy with hippocampal sclerosis

To investigate the effect of seizure frequency on memory, we performed a cross sectional study comparing mesial temporal lobe epilepsy (MTLE) patients with frequent and infrequent seizures.

How to fix any 3D segmentation interactively via Image Foresting Transform and its use in MRI brain segmentation

In medical imaging, there are many approaches for automatic segmentation. However, none of these methods provide any effective solution to correct segmentation interactively, which becomes a necessity in the case of poorly defined structures. Manual segmentation can not be an alternative given that it might be unfeasible in many cases. On the other hand, how to complete a poor automatic segmentation in an interactive tool is an issue, since the automatic approach and the tool may have been designed with different optimization criteria. We propose solutions to this problem using the framework of the “Image Foresting Transform” (IFT), with evaluation in the context of the segmentation of MR-T1 brain structures. The results indicate that effective semi-automatic correction is possible using just a few markers.

Clustering by optimum path forest and its application to automatic GM/WM classification in MR-T1 images of the brain

A new approach to identify clusters as trees of an optimum- path forest has been presented. We are extending the method for large datasets with application to automatic GM/WM classification in MR-T1 images of the brain. The method is computed for a few randomly selected voxels, such that GM and WM define two optimum-path trees. The remaining voxels are classified incrementally, by identifying which tree would contain each voxel if it were part of the forest. Our method produces accurate results on phantom and real images, similarly to those obtained by the state-of-the-art, does not rely on templates, and takes less than 1.5 minute on modern PCs.

Image Segmentation by Image Foresting Transform with Non-smooth Connectivity Functions

In the framework of the Image Foresting Transform (IFT), there is a class of connectivity functions that were vaguely explored, which corresponds to the non-smooth connectivity functions (NSCF). These functions are more adaptive to cope with the problems of field in homogeneity, which are common in MR images of 3 Tesla. In this work, we investigate the NSCF from the standpoint of theoretical and experimental aspects. We formally classify several non-smooth functions according to a proposed diagram representation. Then, we investigate some theoretical properties for some specific regions of the diagram. Our analysis reveals that many NSCFs are, in fact, the result of a sequence of optimizations, each of them involving a maximal set of elements, in a well-structured way. Our experimental results indicate that substantial improvements can be obtained by NSCFs in the 3D segmentation of MR images of 3 Tesla, when compared to smooth connectivity functions.

Oriented image foresting transform segmentation with connectivity constraints

A new algorithm, named Connected Oriented Image Foresting Transform (COIFT), is proposed, which provides global optimum solutions according to a graph-cut measure, subject to high-level boundary constraints. COIFT incorporates the connectivity constraint in the Oriented Image Foresting Transform (OIFT), ensuring the generation of connected objects, and can also handle simultaneously the boundary polarity. While the connectivity constraint usually leads to NP-hard problems in other frameworks, such as the min-cut/max-flow algorithm, COIFT conserves the low complexity of the OIFT algorithm. Experiments show that COIFT can improve the segmentation of thin and elongated objects, for the same amount of user interaction.

Classification of Detected Changes From Multitemporal High-Res Xband SAR Images: Intensity and Texture Descriptors From SuperPixels

Remote sensing has been widely employed for monitoring land cover and usage by change detection techniques. In this paper, we cope with the early detection of the first signs of deforestation, which is the gateway for illegal activities, such as unauthorized urban sprawl and grazing use. In recent years, object-based approaches have emerged as a more suitable alternative than pixel-based methods for change detection in remote sensing images. Even though several classifiers have been tested, there was little effort in selecting appropriated features for the classification of detected changes. After a deep analysis of the existing segmentation, feature extraction, and classification approaches, we propose an object-based methodology that consists of: 1) segmenting multitemporal Xband high-resolution synthetic aperture radar (SAR) images into superpixels employing the simple linear iterative clustering algorithm; 2) extracting features using the object correlation images framework and with the gray-level cooccurrence matrix; and 3) classifying areas into unchanged, deforestation, and other changes by means of a multilayer perceptron supervised learning technique. Experiments were performed using high-resolution SAR images obtained by the airborne sensor OrbiSAR-2 from BRADAR in challenging scenarios of the Brazilian Atlantic Forest, including a wide variety of vegetation, rivers, sea coasts, urban, harvest and open areas, and humidity changes. We perform an extensive experimental analysis of the results, comparing the proposed method with a state-of-the-art approach. The results demonstrate that our method yields an improvement of over 10% in the accuracy while detecting changes and classifying deforested areas.