-
[show abstract]
[hide abstract]
ABSTRACT: In this work we explored class separability in feature spaces built on extended representations of pixel planes (EPP) produced using scale pyramid, subband pyramid, and image transforms. The image transforms included Chebyshev, Fourier, wavelets, gradient and Laplacian; we also utilized transform combinations, including Fourier, Chebyshev and wavelets of the gradient transform, as well as Fourier of the Laplacian transform. We demonstrate that all three types of EPP promote class separation. We also explored the effect of EPP on suboptimal feature libraries, using only textural features in one case and only Haralick features in another. The effect of EPP was especially clear for these suboptimal libraries, where the transform-based representations were found to increase separability to a greater extent than scale or subband pyramids. EPP can be particularly useful in new applications where optimal features have not yet been developed.
Machine Vision and Applications 09/2012; 23(5):1047-1058. · 1.01 Impact Factor
-
D Mark Eckley,
Salim Rahimi,
Sandra Mantilla,
Nikita V Orlov,
Christopher E Coletta,
Mark A Wilson,
Wendy B Iser,
John D Delaney,
Yongqing Zhang,
William Wood,
Kevin G Becker,
Catherine A Wolkow,
Ilya G Goldberg
[show abstract]
[hide abstract]
ABSTRACT: We present an initial molecular characterization of a morphological transition between two early aging states. In previous work, an age score reflecting physiological age was developed using a machine classifier trained on images of worm populations at fixed chronological ages throughout their lifespan. The distribution of age scores identified three stable post-developmental states and transitions. The first transition occurs at day 5 post-hatching, where a significant percentage of the population exists in both state I and state II. The temperature dependence of the timing of this transition (Q (10) ~ 1.17) is too low to be explained by a stepwise process with an enzymatic or chemical rate-limiting step, potentially implicating a more complex mechanism. Individual animals at day 5 were sorted into state I and state II groups using the machine classifier and analyzed by microarray expression profiling. Despite being isogenic, grown for the same amount of time, and indistinguishable by eye, these two morphological states were confirmed to be molecularly distinct by hierarchical clustering and principal component analysis of the microarray results. These molecular differences suggest that pharynx morphology reflects the aging state of the whole organism. Our expression profiling yielded a gene set that showed significant overlap with those from three previous age-related studies and identified several genes not previously implicated in aging. A highly represented group of genes unique to this study is involved in targeted ubiquitin-mediated proteolysis, including Skp1-related (SKR), F-box-containing, and BTB motif adaptors.
Age 05/2012; · 6.28 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We present results from machine classification of melanoma biopsies sectioned and stained with hematoxylin/eosin (H&E) on tissue microarrays (TMA). The four stages of melanoma progression were represented by seven tissue types, including benign nevus, primary tumors with radial and vertical growth patterns (stage I) and four secondary metastatic tumors: subcutaneous (stage II), lymph node (stage III), gastrointestinal and soft tissue (stage IV). Our experiment setup comprised 14,208 image samples based on 164 TMA cores. In our experiments, we constructed an HE color space by digitally deconvolving the RGB images into separate H (hematoxylin) and E (eosin) channels. We also compared three different classifiers: Weighted Neighbor Distance (WND), Radial Basis Functions (RBF), and k-Nearest Neighbors (kNN). We found that the HE color space consistently outperformed other color spaces with all three classifiers, while the different classifiers did not have as large of an effect on accuracy. This showed that a more physiologically relevant representation of color can have a larger effect on correct image interpretation than downstream processing steps. We were able to correctly classify individual fields of view with an average of 96% accuracy when randomly splitting the dataset into training and test fields. We also obtained a classification accuracy of 100% when testing entire cores that were not previously used in training (four random trials with one test core for each of 7 classes, 28 tests total). Because each core corresponded to a different patient, this test more closely mimics a clinically relevant setting where new patients are evaluated based on training with previous cases. The analysis method used in this study contains no parameters or adjustments that are specific to melanoma morphology, suggesting it can be used for analyzing other tissues and phenotypes, as well as potentially different image modalities and contrast techniques.
Cytometry Part A 03/2012; 81(5):364-73. · 3.73 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: The increasing prevalence of automated image acquisition systems is enabling new types of microscopy experiments that generate large image datasets. However, there is a perceived lack of robust image analysis systems required to process these diverse datasets. Most automated image analysis systems are tailored for specific types of microscopy, contrast methods, probes, and even cell types. This imposes significant constraints on experimental design, limiting their application to the narrow set of imaging methods for which they were designed. One of the approaches to address these limitations is pattern recognition, which was originally developed for remote sensing, and is increasingly being applied to the biology domain. This approach relies on training a computer to recognize patterns in images rather than developing algorithms or tuning parameters for specific image processing tasks. The generality of this approach promises to enable data mining in extensive image repositories, and provide objective and quantitative imaging assays for routine use. Here, we provide a brief overview of the technologies behind pattern recognition and its use in computer vision for biological and biomedical imaging. We list available software tools that can be used by biologists and suggest practical experimental considerations to make the best use of pattern recognition techniques for imaging assays.
PLoS Computational Biology 11/2010; 6(11):e1000974. · 5.22 Impact Factor
-
Ilias Kazanis,
Justin D Lathia,
Tegy J Vadakkan,
Eric Raborn,
Ruiqian Wan,
Mohamed R Mughal, D Mark Eckley,
Takako Sasaki,
Bruce Patton,
Mark P Mattson,
Karen K Hirschi,
Mary E Dickinson,
Charles ffrench-Constant
[show abstract]
[hide abstract]
ABSTRACT: The subependymal zone (SEZ) of the lateral ventricles is one of the areas of the adult brain where new neurons are continuously generated from neural stem cells (NSCs), via rapidly dividing precursors. This neurogenic niche is a complex cellular and extracellular microenvironment, highly vascularized compared to non-neurogenic periventricular areas, within which NSCs and precursors exhibit distinct behavior. Here, we investigate the possible mechanisms by which extracellular matrix molecules and their receptors might regulate this differential behavior. We show that NSCs and precursors proceed through mitosis in the same domains within the SEZ of adult male mice--albeit with NSCs nearer ependymal cells--and that distance from the ventricle is a stronger limiting factor for neurogenic activity than distance from blood vessels. Furthermore, we show that NSCs and precursors are embedded in a laminin-rich extracellular matrix, to which they can both contribute. Importantly, they express differential levels of extracellular matrix receptors, with NSCs expressing low levels of alpha6beta1 integrin, syndecan-1, and lutheran, and in vivo blocking of beta1 integrin selectively induced the proliferation and ectopic migration of precursors. Finally, when NSCs are activated to reconstitute the niche after depletion of precursors, expression of laminin receptors is upregulated. These results indicate that the distinct behavior of adult NSCs and precursors is not necessarily regulated via exposure to differential extracellular signals, but rather via intrinsic regulation of their interaction with their microenvironment.
Journal of Neuroscience 07/2010; 30(29):9771-81. · 7.11 Impact Factor
-
TAP. 01/2010; 7.
-
[show abstract]
[hide abstract]
ABSTRACT: The post genomic era introduced the need to define single gene functions within biological pathways. A systems biology approach can be realized by automating image acquisition and phenotype classification. While machinery for automated data acquisition have been developing rapidly in the past years, the main bottleneck remains the effectiveness of the computer vision algorithms. Here we describe a fully automated process for finding phenotype similarities within a dataset acquired from an RNAi screen. The source code for the algorithms is available for free download.
IEEE/NIH Life Science Systems and Applications Workshop. IEEE/NIH Life Science Systems and Applications Workshop. 04/2009; 2009:96-99.
-
[show abstract]
[hide abstract]
ABSTRACT: We describe a method for automated detection of radiographic osteoarthritis (OA) in knee X-ray images. The detection is based on the Kellgren-Lawrence (KL) classification grades, which correspond to the different stages of OA severity. The classifier was built using manually classified X-rays, representing the first four KL grades (normal, doubtful, minimal, and moderate). Image analysis is performed by first identifying a set of image content descriptors and image transforms that are informative for the detection of OA in the X-rays and assigning weights to these image features using Fisher scores. Then, a simple weighted nearest neighbor rule is used in order to predict the KL grade to which a given test X-ray sample belongs. The dataset used in the experiment contained 350 X-ray images classified manually by their KL grades. Experimental results show that moderate OA (KL grade 3) and minimal OA (KL grade 2) can be differentiated from normal cases with accuracy of 91.5% and 80.4%, respectively. Doubtful OA (KL grade 1) was detected automatically with a much lower accuracy of 57%. The source code developed and used in this study is available for free download at www.openmicroscopy.org.
IEEE transactions on bio-medical engineering 03/2009; 56(2):407-15. · 2.15 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Biological imaging is an emerging field, covering a wide range of applications in biological and clinical research. However, while machinery for automated experimenting and data acquisition has been developing rapidly in the past years, automated image analysis often introduces a bottleneck in high content screening.
Wndchrm is an open source utility for biological image analysis. The software works by first extracting image content descriptors from the raw image, image transforms, and compound image transforms. Then, the most informative features are selected, and the feature vector of each image is used for classification and similarity measurement.
Wndchrm has been tested using several publicly available biological datasets, and provided results which are favorably comparable to the performance of task-specific algorithms developed for these datasets. The simple user interface allows researchers who are not knowledgeable in computer vision methods and have no background in computer programming to apply image analysis to their data.
We suggest that wndchrm can be effectively used for a wide range of biological image analysis tasks. Using wndchrm can allow scientists to perform automated biological image analysis while avoiding the costly challenge of implementing computer vision and pattern recognition algorithms.
Source Code for Biology and Medicine 08/2008; 3:13.
-
[show abstract]
[hide abstract]
ABSTRACT: We describe a multi-purpose image classifier that can be applied to a wide variety of image classification tasks without modifications or fine-tuning, and yet provide classification accuracy comparable to state-of-the-art task-specific image classifiers. The proposed image classifier first extracts a large set of 1025 image features including polynomial decompositions, high contrast features, pixel statistics, and textures. These features are computed on the raw image, transforms of the image, and transforms of transforms of the image. The feature values are then used to classify test images into a set of pre-defined image classes. This classifier was tested on several different problems including biological image classification and face recognition. Although we cannot make a claim of universality, our experimental results show that this classifier performs as well or better than classifiers developed specifically for these image classification tasks. Our classifier's high performance on a variety of classification problems is attributed to (i) a large set of features extracted from images; and (ii) an effective feature selection and weighting algorithm sensitive to specific image classification problems. The algorithms are available for free download from openmicroscopy.org.
Pattern Recognition Letters 02/2008; 29(11):1684-1693. · 1.03 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: The extracellular matrix (ECM) provides both a physical framework and a microenvironment that supplies instructive signals from the earliest stages of multicellular development. As a first step toward understanding the role of the ECM in regulating the behavior of neural stem cells (NSCs), here we show the localization of laminins, a heterotrimeric family of ECM molecules expressed in many different stem cell microenvironments, and their corresponding receptors in the embryonic murine ventricular zone (VZ) within which the NSCs undergo symmetrical and asymmetrical divisions required for cortical development. In addition to the presence of laminins containing both the alpha2 and alpha4 chains, we find distinct patterns of ECM receptor expression in the VZ and in the overlying cortex. Neural stem cells derived from the VZ express high levels of the integrin laminin receptor alpha6beta1. At developmental stages at which NSCs undergo asymmetrical divisions, integrin beta1 was unevenly distributed in some mitotic pairs at the ventricular wall. These results suggest a significant role in the regulation of NSC fate for laminin/integrin signaling within the microenvironment of the VZ and provide a framework for future molecular and cellular analyses of the role of the ECM in neural development.
The Journal of Comparative Neurology 01/2008; 505(6):630-43. · 3.81 Impact Factor
-
Tim Magnus,
Turhan Coksaygan,
Thomas Korn,
Haipeng Xue,
Thiruma V Arumugam,
Mohamed R Mughal, D Mark Eckley,
Sung-Chun Tang,
Louis Detolla,
Mahendra S Rao,
Riccardo Cassiani-Ingoni,
Mark P Mattson
[show abstract]
[hide abstract]
ABSTRACT: The mechanisms by which neural and glial progenitor cells in the adult brain respond to tissue injury are unknown. We studied the responses of these cells to stab wound injury in rats and in two transgenic mouse models in which Y/GFP is driven either by Sox2 (a neural stem cell marker) or by Talpha-1 (which marks newly born neurons). The response of neural progenitors was low in all nonneurogenic regions, and no neurogenesis occurred at the injury site. Glial progenitors expressing Olig2 and NG2 showed the greatest response. The appearance of these progenitors preceded the appearance of reactive astrocytes. Surprisingly, we found evidence of the translocation of the transcription factor Olig2 into cytoplasm in the first week after injury, a mechanism that is known to mediate the differentiation of astrocytes during brain development. Translocation of Olig2, down-regulation of NG2, and increased glial fibrillary acidic protein expression were recapitulated in vitro after exposure of glial progenitors to serum components or bone morphogentic protein by up-regulation of Notch-1. The glial differentiation and Olig2 translocation could be blocked by inhibition of Notch-1 with the gamma-secretase inhibitor DAPT. Together, these data indicate that the prompt maturation of numerous Olig2(+) glial progenitors to astrocytes underlies the repair process after a traumatic injury. In contrast, neural stem cells and neuronal progenitor cells appear to play only a minor role in the injured adult CNS.
Journal of Neuroscience Research 09/2007; 85(10):2126-37. · 2.74 Impact Factor
