Epigenetic Activation of Pro-angiogenic Signaling Pathways in Human Endothelial Progenitors Increases Vasculogenesis.

Human endothelial colony-forming cells (ECFCs) represent a promising source of adult stem cells for vascular repair, yet their regenerative capacity is limited. Here, we set out to understand the molecular mechanism restricting the repair function of ECFCs. We found that key pro-angiogenic pathways are repressed in ECFCs due to the presence of bivalent (H3K27me3/H3K4me3) epigenetic marks, which decreases the cells' regenerative potential. Importantly, ex vivo treatment with a combination of epigenetic drugs that resolves bivalent marks toward the transcriptionally active H3K4me3 state leads to the simultaneous activation of multiple pro-angiogenic signaling pathways (VEGFR, CXCR4, WNT, NOTCH, SHH). This in turn results in improved capacity of ECFCs to form capillary-like networks in vitro and in vivo. Furthermore, restoration of perfusion is accelerated upon transplantation of drug-treated ECFCs in a model of hindlimb ischemia. Thus, ex vivo treatment with epigenetic drugs increases the vascular repair properties of ECFCs through transient activation of pro-angiogenic signaling pathways.

Learning a cost function for microscope image segmentation.

Quantitative analysis of microscopy images is increasingly important in clinical researchers' efforts to unravel the cellular and molecular determinants of disease, and for pathological analysis of tissue samples. Yet, manual segmentation and measurement of cells or other features in images remains the norm in many fields. We report on a new system that aims for robust and accurate semi-automated analysis of microscope images. A user interactively outlines one or more examples of a target object in a training image. We then learn a cost function for detecting more objects of the same type, either in the same or different images. The cost function is incorporated into an active contour model, which can efficiently determine optimal boundaries by dynamic programming. We validate our approach and compare it to some standard alternatives on three different types of microscopic images: light microscopy of blood cells, light microscopy of muscle tissue sections, and electron microscopy cross-sections of axons and their myelin sheaths.

FiloDetect: automatic detection of filopodia from fluorescence microscopy images.

BACKGROUND: Filopodia are small cellular projections that help cells to move through and sense their environment. Filopodia play crucial roles in processes such as development and wound-healing. Also, increases in filopodia number or size are characteristic of many invasive cancers and are correlated with increased rates of metastasis in mouse experiments. Thus, one possible route to developing anti-metastatic therapies is to target factors that influence the filopodia system. Filopodia can be detected by eye using confocal fluorescence microscopy, and they can be manually annotated in images to quantify filopodia parameters. Although this approach is accurate, it is slow, tedious and not entirely objective. Manual detection is a significant barrier to the discovery and quantification of new factors that influence the filopodia system. RESULTS: Here, we present FiloDetect, an automated tool for detecting, counting and measuring the length of filopodia in fluorescence microscopy images. The method first segments the cell from the background, using a modified triangle threshold method, and then extracts the filopodia using a series of morphological operations. We verified the accuracy of FiloDetect on Rat2 and B16F1 cell images from three different labs, showing that per-cell filopodia counts and length estimates are highly correlated with the manual annotations. We then used FiloDetect to assess the role of a lipid kinase on filopodia production in breast cancer cells. Experimental results show that PI4KIII ß expression leads to an increase in filopodia number and length, suggesting that PI4KIII ß is involved in driving filopodia production. CONCLUSION: FiloDetect provides accurate and objective quantification of filopodia in microscopy images, and will enable large scale comparative studies to assess the effects of different genetic and chemical perturbations on filopodia production in different cell types, including cancer cell lines.

Object detection with DoG scale-space: a multiple kernel learning approach.

Difference of Gaussians (DoG) scale-space for an image is a significant way to generate features for object detection and classification. While applying DoG scale-space features for object detection/classification, we face two inevitable issues: dealing with high dimensional data and selecting/weighting of proper scales. The scale selection process is mostly ad-hoc to date. In this paper, we propose a multiple kernel learning (MKL) method for both DoG scale selection/weighting and dealing with high dimensional scale-space data. We design a novel shift invariant kernel function for DoG scale-space. To select only the useful scales in the DoG scale-space, a novel framework of MKL is also proposed. We utilize a 1-norm support vector machine (SVM) in the MKL optimization problem for sparse weighting of scales from DoG scale-space. The optimized data-dependent kernel accommodates only a few scales that are most discriminatory according to the large margin principle. With a 2-norm SVM this learned kernel is applied to a challenging detection problem in oil sand mining: to detect large lumps in oil sand videos. We tested our method on several challenging oil sand data sets. Our method yields encouraging results on these difficult-to-process images and compares favorably against other popular multiple kernel methods.

Airway segmentation and measurement in CT images.

In this paper we describe a methodology for constructing the airways from Cone Beam CT data and representing changes before and after a medical procedure. A seed region is automatically detected for the first CT slice using a heuristic algorithm incorporating morphological filtering. Our approach then extracts relevant contours on 3D slices by using gradient vector flow (GVF) snakes, modified by an edge detection and snake-shifting step. Following this, a 3D model is constructed. We then estimate the volume of the airway based on segmented 3D shape.

A districted neural network for start codon prediction.

Following the theory on regional and national voting, we constructed a regional voting version NN from Pedersen-Nielsen's NN for start codon prediction in nucleotide sequences. Experiments on the TIS data of vertebrate and Arabidopsis thaliana sequences showed improved performances (Matthews correlation coefficients) of 7% and 14% over the original NN.