Automated detection of GFAP-labeled astrocytes in micrographs using YOLOv5.

Astrocytes, a subtype of glial cells with a complex morphological structure, are active players in many aspects of the physiology of the central nervous system (CNS). However, due to their highly involved interaction with other cells in the CNS, made possible by their morphological complexity, the precise mechanisms regulating astrocyte function within the CNS are still poorly understood. This knowledge gap is also due to the current limitations of existing quantitative image analysis tools that are unable to detect and analyze images of astrocyte with sufficient accuracy and efficiency. To address this need, we introduce a new deep learning framework for the automated detection of GFAP-immunolabeled astrocytes in brightfield or fluorescent micrographs. A major novelty of our approach is the applications of YOLOv5, a sophisticated deep learning platform designed for object detection, that we customized to derive optimized classification models for the task of astrocyte detection. Extensive numerical experiments using multiple image datasets show that our method performs very competitively against both conventional and state-of-the-art methods, including the case of images where astrocytes are very dense. In the spirit of reproducible research, our numerical code and annotated data are released open source and freely available to the scientific community.

Automated sorting of neuronal trees in fluorescent images of neuronal networks using NeuroTreeTracer.

Fluorescence confocal microscopy has become increasingly more important in neuroscience due to its applications in image-based screening and profiling of neurons. Multispectral confocal imaging is useful to simultaneously probe for distribution of multiple analytes over networks of neurons. However, current automated image analysis algorithms are not designed to extract single-neuron arbors in images where neurons are not separated, hampering the ability map fluorescence signals at the single cell level. To overcome this limitation, we introduce NeuroTreeTracer - a novel image processing framework aimed at automatically extracting and sorting single-neuron traces in fluorescent images of multicellular neuronal networks. This method applies directional multiscale filters for automated segmentation of neurons and soma detection, and includes a novel tracing routine that sorts neuronal trees in the image by resolving network connectivity even when neurites appear to intersect. By extracting each neuronal tree, NeuroTreetracer enables to automatically quantify the spatial distribution of analytes of interest in the subcellular compartments of individual neurons. This software is released open-source and freely available with the goal to facilitate applications in neuron screening and profiling.

Multiscale Analysis of Neurite Orientation and Spatial Organization in Neuronal Images.

The spatial organization of neurites, the thin processes (i.e., dendrites and axons) that stem from a neuron's soma, conveys structural information required for proper brain function. The alignment, direction and overall geometry of neurites in the brain are subject to continuous remodeling in response to healthy and noxious stimuli. In the developing brain, during neurogenesis or in neuroregeneration, these structural changes are indicators of the ability of neurons to establish axon-to-dendrite connections that can ultimately develop into functional synapses. Enabling a proper quantification of this structural remodeling would facilitate the identification of new phenotypic criteria to classify developmental stages and further our understanding of brain function. However, adequate algorithms to accurately and reliably quantify neurite orientation and alignment are still lacking. To fill this gap, we introduce a novel algorithm that relies on multiscale directional filters designed to measure local neurites orientation over multiple scales. This innovative approach allows us to discriminate the physical orientation of neurites from finer scale phenomena associated with local irregularities and noise. Building on this multiscale framework, we also introduce a notion of alignment score that we apply to quantify the degree of spatial organization of neurites in tissue and cultured neurons. Numerical codes were implemented in Python and released open source and freely available to the scientific community.

Multi-scale segmentation of neurons based on one-class classification.

BACKGROUND: High resolution multiphoton and confocal microscopy has allowed the acquisition of large amounts of data to be analyzed by neuroscientists. However, manual processing of these images has become infeasible. Thus, there is a need to create automatic methods for the morphological reconstruction of 3D neuronal image stacks. NEW METHOD: An algorithm to extract the 3D morphology from a neuron is presented. The main contribution of the paper is the segmentation of the neuron from the background. Our segmentation method is based on one-class classification where the 3D image stack is analyzed at different scales. First, a multi-scale approach is proposed to compute the Laplacian of the 3D image stack. The Laplacian is used to select a training set consisting of background points. A decision function is learned for each scale from the training set that allows determining how similar an unlabeled point is to the points in the background class. Foreground points (dendrites and axons) are assigned as those points that are rejected as background. Finally, the morphological reconstruction of the neuron is extracted by applying a state-of-the-art centerline tracing algorithm on the segmentation. RESULTS: Quantitative and qualitative results on several datasets demonstrate the ability of our algorithm to accurately and robustly segment and trace neurons. COMPARISON WITH EXISTING METHOD(S): Our method was compared to state-of-the-art neuron tracing algorithms. CONCLUSIONS: Our approach allows segmentation of thin and low contrast dendrites that are usually difficult to segment. Compared to our previous approach, this algorithm is more accurate and much faster.

Automated detection of soma location and morphology in neuronal network cultures.

Automated identification of the primary components of a neuron and extraction of its sub-cellular features are essential steps in many quantitative studies of neuronal networks. The focus of this paper is the development of an algorithm for the automated detection of the location and morphology of somas in confocal images of neuronal network cultures. This problem is motivated by applications in high-content screenings (HCS), where the extraction of multiple morphological features of neurons on large data sets is required. Existing algorithms are not very efficient when applied to the analysis of confocal image stacks of neuronal cultures. In addition to the usual difficulties associated with the processing of fluorescent images, these types of stacks contain a small number of images so that only a small number of pixels are available along the z-direction and it is challenging to apply conventional 3D filters. The algorithm we present in this paper applies a number of innovative ideas from the theory of directional multiscale representations and involves the following steps: (i) image segmentation based on support vector machines with specially designed multiscale filters; (ii) soma extraction and separation of contiguous somas, using a combination of level set method and directional multiscale filters. We also present an approach to extract the soma's surface morphology using the 3D shearlet transform. Extensive numerical experiments show that our algorithms are computationally efficient and highly accurate in segmenting the somas and separating contiguous ones. The algorithms presented in this paper will facilitate the development of a high-throughput quantitative platform for the study of neuronal networks for HCS applications.

Automatic Morphological Reconstruction of Neurons from Multiphoton and Confocal Microscopy Images Using 3D Tubular Models.

The challenges faced in analyzing optical imaging data from neurons include a low signal-to-noise ratio of the acquired images and the multiscale nature of the tubular structures that range in size from hundreds of microns to hundreds of nanometers. In this paper, we address these challenges and present a computational framework for an automatic, three-dimensional (3D) morphological reconstruction of live nerve cells. The key aspects of this approach are: (i) detection of neuronal dendrites through learning 3D tubular models, and (ii) skeletonization by a new algorithm using a morphology-guided deformable model for extracting the dendritic centerline. To represent the neuron morphology, we introduce a novel representation, the Minimum Shape-Cost (MSC) Tree that approximates the dendrite centerline with sub-voxel accuracy and demonstrate the uniqueness of such a shape representation as well as its computational efficiency. We present extensive quantitative and qualitative results that demonstrate the accuracy and robustness of our method.

Improved automatic centerline tracing for dendritic and axonal structures.

Centerline tracing in dendritic structures acquired from confocal images of neurons is an essential tool for the construction of geometrical representations of a neuronal network from its coarse scale up to its fine scale structures. In this paper, we propose an algorithm for centerline extraction that is both highly accurate and computationally efficient. The main novelties of the proposed method are (1) the use of a small set of Multiscale Isotropic Laplacian filters, acting as self-steerable filters, for a quick and efficient binary segmentation of dendritic arbors and axons; (2) an automated centerline seed points detection method based on the application of a simple 3D finite-length filter. The performance of this algorithm, which is validated on data from the DIADEM set appears to be very competitive when compared with other state-of-the-art algorithms.

Oxidative stress response pathways: Fission yeast as archetype.

Schizosaccharomyces pombe is a popular model eukaryotic organism to study diverse aspects of mammalian biology, including responses to cellular stress triggered by redox imbalances within its compartments. The review considers the current knowledge on the signaling pathways that govern the transcriptional response of fission yeast cells to elevated levels of hydrogen peroxide. Particular attention is paid to the mechanisms that yeast cells employ to promote cell survival in conditions of intermediate and acute oxidative stress. The role of the Sty1/Spc1/Phh1 mitogen-activated protein kinase in regulating gene expression at multiple levels is discussed in detail.

Natural genetic variation impacts expression levels of coding, non-coding, and antisense transcripts in fission yeast.

Our current understanding of how natural genetic variation affects gene expression beyond well-annotated coding genes is still limited. The use of deep sequencing technologies for the study of expression quantitative trait loci (eQTLs) has the potential to close this gap. Here, we generated the first recombinant strain library for fission yeast and conducted an RNA-seq-based QTL study of the coding, non-coding, and antisense transcriptomes. We show that the frequency of distal effects (trans-eQTLs) greatly exceeds the number of local effects (cis-eQTLs) and that non-coding RNAs are as likely to be affected by eQTLs as protein-coding RNAs. We identified a genetic variation of swc5 that modifies the levels of 871 RNAs, with effects on both sense and antisense transcription, and show that this effect most likely goes through a compromised deposition of the histone variant H2A.Z. The strains, methods, and datasets generated here provide a rich resource for future studies.

Rigid-motion-invariant classification of 3-D textures.

This paper studies the problem of 3-D rigid-motion-invariant texture discrimination for discrete 3-D textures that are spatially homogeneous by modeling them as stationary Gaussian random fields. The latter property and our formulation of a 3-D rigid motion of a texture reduce the problem to the study of 3-D rotations of discrete textures. We formally develop the concept of 3-D texture rotations in the 3-D digital domain. We use this novel concept to define a "distance" between 3-D textures that remains invariant under all 3-D rigid motions of the texture. This concept of "distance" can be used for a monoscale or a multiscale 3-D rigid-motion-invariant testing of the statistical similarity of the 3-D textures. To compute the "distance" between any two rotations R(1) and R(2) of two given 3-D textures, we use the Kullback-Leibler divergence between 3-D Gaussian Markov random fields fitted to the rotated texture data. Then, the 3-D rigid-motion-invariant texture distance is the integral average, with respect to the Haar measure of the group SO(3), of all of these divergences when rotations R(1) and R(2) vary throughout SO(3). We also present an algorithm enabling the computation of the proposed 3-D rigid-motion-invariant texture distance as well as rules for 3-D rigid-motion-invariant texture discrimination/classification and experimental results demonstrating the capabilities of the proposed 3-D rigid-motion texture discrimination rules when applied in a multiscale setting, even on very general 3-D texture models.

Yeast biological networks unfold the interplay of antioxidants, genome and phenotype, and reveal a novel regulator of the oxidative stress response.

BACKGROUND: Identifying causative biological networks associated with relevant phenotypes is essential in the field of systems biology. We used ferulic acid (FA) as a model antioxidant to characterize the global expression programs triggered by this small molecule and decipher the transcriptional network controlling the phenotypic adaptation of the yeast Saccharomyces cerevisiae. METHODOLOGY/PRINCIPAL FINDINGS: By employing a strict cut off value during gene expression data analysis, 106 genes were found to be involved in the cell response to FA, independent of aerobic or anaerobic conditions. Network analysis of the system guided us to a key target node, the FMP43 protein, that when deleted resulted in marked acceleration of cellular growth (∼15% in both minimal and rich media). To extend our findings to human cells and identify proteins that could serve as drug targets, we replaced the yeast FMP43 protein with its human ortholog BRP44 in the genetic background of the yeast strain Δfmp43. The conservation of the two proteins was phenotypically evident, with BRP44 restoring the normal specific growth rate of the wild type. We also applied homology modeling to predict the 3D structure of the FMP43 and BRP44 proteins. The binding sites in the homology models of FMP43 and BRP44 were computationally predicted, and further docking studies were performed using FA as the ligand. The docking studies demonstrated the affinity of FA towards both FMP43 and BRP44. CONCLUSIONS: This study proposes a hypothesis on the mechanisms yeast employs to respond to antioxidant molecules, while demonstrating how phenome and metabolome yeast data can serve as biomarkers for nutraceutical discovery and development. Additionally, we provide evidence for a putative therapeutic target, revealed by replacing the FMP43 protein with its human ortholog BRP44, a brain protein, and functionally characterizing the relevant mutant strain.

Three-dimensional isotropic wavelets for post-acquisitional extraction of latent images of atherosclerotic plaque components from micro-computed tomography of human coronary arteries.

RATIONALE AND OBJECTIVES: The capability of wavelet transforms to separate signals into frequency bands is the basis for its use in image compression and storage, data management and transmission, and, recently, extraction of latent images of tissue components from noisy medical images. Analysis of temporal variations of radiofrequency backscatter of intravascular ultrasound with one-dimensional wavelets can detect lipid-laden plaque in coronary arteries with a sensitivity and specificity of >80%. In this study we evaluate the capability of a novel, 3-dimensional isotropic wavelet analysis to perform high resolution, non-directionally biased, statistically reliable, non-invasive discrimination between components of human coronary atherosclerotic plaques in micro-CT. MATERIALS AND METHODS: Coronary artery segments (5-15 mm) were excised at necropsy from 18 individuals with advanced coronary atherosclerosis. Specimens were imaged using a GE Locus SP ex vivo micro-CT scanner and processed for histological correlation (833 sections). The isotropic wavelet constructs were applied to the entire volume of CT data of each arterial segment to distinguish tissue textures of varying scales and intensities. Voxels were classified and plaque characterization achieved by comparing the relative magnitudes of these wavelet constituents to that of several reference plaque tissue components. RESULTS: Processing of micro-CT images via these isotropic wavelet algorithms permitted 3-D, color-coded, high resolution, digital discrimination between lumen, calcific deposits, lipid-rich deposits, and fibromuscular tissue providing detail not possible with conventional thresholding based on Hounsfield intensity units. Using the isotropic wavelets (with histology as the gold standard), lipid-rich pools approaching the size of the filter for the isotropic wavelet algorithm (0.25 mm [250 microns] in length) were identified with 81% sensitivity and 86% specificity. Calcific deposits, fibromuscular tissue, and lumen equal to or larger than the wavelet filter size were detected without error (100% sensitivity and specificity). CONCLUSION: Isotropic wavelet analysis permits high resolution, multi-dimensional identification of coronary atherosclerotic plaque components in micro-CT with sensitivity and specificity similar to that achieved with data obtained invasively (from IVUS in vivo) using one-dimensional wavelets. Further studies are necessary to test the applicability of this technology to clinical, multi-detector scanners.

Quantification of roughness of calcific deposits in computed tomography scans of human coronary arteries.

OBJECTIVES: The incidence of coronary artery disease has been shown to be greater in patients with calcific deposits than in those without. It has been suggested that the pattern of distribution of coronary calcific deposits within coronary arteries is of greater predictive value for acute coronary events than the overall quantity. Whether roughness of calcific deposits is a predictor of acute coronary events is not known. We derived and tested an algorithm, Voxel-Based Bosselation (VBB), for noninvasive quantification of roughness of calcific deposits in human coronary arteries imaged by computed tomography (CT). METHODS AND RESULTS: VBB was tested on 213 coronary calcific deposits from electron beam CT scans of 27 patients. This algorithm evaluates the 3-dimensional connectedness of surface voxels of each deposit: smooth masses have low VBB and rough masses high VBB. The algorithm was calibrated with artificially generated phantoms as well as background noise mimicking calcific deposits and surrounding heart tissue. The VBB algorithm is applicable to calcific deposits of all scales and gradations. The VBB values of the deposits in this study did not correlate with deposit size further supporting its validity as a measurement of roughness. The VBB index corresponded directly with visual reconstruction using Phong-shaded algorithms. CONCLUSIONS: The VBB index, derived here, is a noninvasive method of quantifying the roughness of calcific deposits in CT scan data which can now be used in future clinical studies to determine possible correlations with increased plaque vulnerability and major acute coronary events.

Image denoising using a tight frame.

We present a general mathematical theory for lifting frames that allows us to modify existing filters to construct new ones that form Parseval frames. We apply our theory to design nonseparable Parseval frames from separable (tensor) products of a piecewise linear spline tight frame. These new frame systems incorporate the weighted average operator, the Sobel operator, and the Laplacian operator in directions that are integer multiples of 45 degrees. A new image denoising algorithm is then proposed, tailored to the specific properties of these new frame filters. We demonstrate the performance of our algorithm on a diverse set of images with very encouraging results.

Usefulness of multidetector computed tomography for noninvasive evaluation of coronary arteries in asymptomatic patients.

This editorial addresses the capabilities, limitations, and potential of multidetector computed tomography (MDCT) for the noninvasive evaluation of coronary arteries in asymptomatic patients. The quantification of coronary calcium with MDCT correlates highly with that obtained by electron-beam computed tomography, but to date, neither has the capability of assessing the distribution of various morphologic patterns of calcium and their relation to other "soft" plaque components. Although MDCT can assess the thickness of the atherosclerotic wall and can readily identify calcific deposits, further plaque characterization (e.g., lipid pools and fibrous tissue), a prerequisite for the identification of most vulnerable lesions, is not yet a workable reality, even with the 64-slice machines in their current configuration. The noninvasive identification by MDCT of plaque components subtending vulnerable lesions will require additional improvement in the primary instrumentation, the use of hybrid constructs (e.g., with positron emission tomography and magnetic resonance imaging), the development of novel methods of post-acquisitional analysis to extract latent images of plaque components (e.g., signal analysis based on 3-dimensional wavelets), or the adaptation of molecular imaging techniques at the cell and gene levels to computed tomography. Such unique approaches may soon contribute a long list of additional parameters that could be evaluated on a noninvasive basis as predictors of acute coronary syndromes and overall patient vulnerability.

Sputum carcinoembryonic antigen, neuron-specific enolase and cytokeratin fragment 19 levels in lung cancer diagnosis.

OBJECTIVE: The aim of the present study was to examine the impact of sputum carcinoembryonic antigen (CEA), neuron-specific enolase (NSE) and cytokeratin fragment 19 (CYFRA 21-1) levels in lung cancer diagnosis and to compare the diagnostic usefulness of sputum assays with that of serum assays. METHODOLOGY: Forty-seven patients with lung cancer and 62 with benign lung disease were studied. Tumour marker levels in sputum (sp.) and serum (ser) were measured by immunoradiometric assays. RESULTS: Sputum and serum tumour marker levels were significantly higher in lung cancer than in benign disease. When the specificity was 95%, the sensitivity was 57%, 43%, 36%, 30%, 28% and 19%, for spCEA, serCYFRA 21-1, spCYFRA 21-1, serCEA, serNSE, and spNSE, respectively. Bayesian analysis showed that the best predictive values correspond to spCEA and serCYFRA 21-1. The maximum overall gain was obtained in pretest probability of 0.35 for both spCEA and serCYFRA 21-1, with predictive values of 84% and 80% for spCEA and serCYFRA 21-1, respectively. CONCLUSION: Sputum tumour marker levels were no more useful than the serum levels in lung cancer diagnosis. SpCEA offered the best predictive values but these were still not sufficiently satisfactory for spCEA to be proposed for routine use.