Papers by Michele Ceccarelli
2008 20th IEEE International Conference on Tools with Artificial Intelligence, 2008
The application of scientific methodology to clinical practice is typically realized through reco... more The application of scientific methodology to clinical practice is typically realized through recommendations, policies and protocols represented as Clinical Practice Guidelines (CPG). CPGs have the purpose to help the clinicians in their choices and to improve the patient care process.
2009 24th International Symposium on Computer and Information Sciences, 2009
Microarrays are state technologies of the art for the measurement of expression of thousands of g... more Microarrays are state technologies of the art for the measurement of expression of thousands of genes in a single experiment. The treatment of these data are typically performed with a wide range of tools, but the understanding of complex biological system by means of gene expression usually requires integrating different types of data from multiple sources and different services and tools. Many efforts are being developed on the new area of scientific workflows in order to create a technology that links both data and tools to create workflows that can easily be used by researchers. Currently technologies in this area aren't mature yet, making arduous the use of these technologies by the researcher. In this paper we present an architecture that helps the researchers to make large-scale gene expression data analysis with cutting edge technologies. The main underlying idea is to automate and rearrange the activities involved in gene expression data analysis, in order to freeing the user of superfluous technological details and tedious and errorprone tasks.
Earth Surface Processes and Landforms - EARTH SURF PROCESS LANDF, 2005
The spatial variability of precipitation has often been a topic of research, since accurate model... more The spatial variability of precipitation has often been a topic of research, since accurate modelling of precipitation is a crucial condition for obtaining reliable results in hydrology and geomorphology. In mountainous areas, the sparsity of the measurement networks makes an accurate and reliable spatialization of rainfall amounts at the local scale difficult. The purpose of this paper is to show how the use of a digital elevation model can improve interpolation processes at the subregional scale for mapping the mean annual and monthly precipitation from rainfall observations (40 years) recorded in a region of 1400 km 2 in southern Italy. Besides linear regression of precipitation against elevation, two methods of interpolation are applied: inverse squared distance and ordinary cokriging. Cross-validation indicates that the inverse distance interpolation, which ignores the information on elevation, yields the largest prediction errors. Smaller prediction errors are produced by linear regression and ordinary cokriging. However, the results seem to favour the multivariate geostatistical method including auxiliary information (related to elevation). We conclude that ordinary cokriging is a very flexible and robust interpolation method because it can take into account several properties of the landscape; it should therefore be applicable in other mountainous regions, especially where precipitation is an important geomorphological factor. Figure 4. Experimental semivariance and cross-covariance function (dots) and their coregionalization model (continuous line). 266 N. Diodato and M. Ceccarelli Figure 5. Annual precipitation fields estimated by linear regression (a), inverse squared distance (b) and ordinary cokriging.
Natural Hazards, 2005
Abstract. The Chernobyl plume contaminated vast lands of Europe with radiocaesium (137Cs) in 1986... more Abstract. The Chernobyl plume contaminated vast lands of Europe with radiocaesium (137Cs) in 1986 because of the deposition of radionuclides on the ground by wet and dry deposition processes. Nevertheless, in a nuclear emergency, contamination data may be very ...
2010 IEEE International Conference on Imaging Systems and Techniques, 2010
The paper presents a non parametric image registration method based on an explicit representation... more The paper presents a non parametric image registration method based on an explicit representation of the warping function. The image registration problem is approached in the Bayesian framework with a prior term given by a Gaussian random field accounting the regularity of a deformable grid. The observation term is accounted with two terms in the energy functional, the first depends on the quality of recontruction of the target image with respect the source image, the second is based on a set of landmarks automatically detected between the images to be registered. The algorithm is completely unsupervised, making it suitable for high throughput biomedical applications such as proteomics and cellular imaging.
Lecture Notes in Computer Science, 2005
Abstract. We investigate the properties of edge preserving smoothing in the context of Finite Mar... more Abstract. We investigate the properties of edge preserving smoothing in the context of Finite Markov Random Fields (FMRF). Our main result follows from the definition of discontinuity adaptive potential for FMRF which imposes to penalize linearly image gradients. This is in agreement with ...
… , 2009. MeMeA 2009. …, 2009
This paper reports a novel method for Nucleus and Micro Nucleuses segmentation. These biological ... more This paper reports a novel method for Nucleus and Micro Nucleuses segmentation. These biological structures are very handy to biologists for relieving structural chromosome aberration. The adopted method consists into a pipeline of advanced computer vision algorithms same of them specifically tailored for the current segmentation problem. Starting from the knowledge of approximate size and shape of Micro Nucleuses it is possible to efficiently segment all the image features by computer vision approach.
BMC bioinformatics, 2009
Background: Mass spectrometry spectra, widely used in proteomics studies as a screening tool for ... more Background: Mass spectrometry spectra, widely used in proteomics studies as a screening tool for protein profiling and to detect discriminatory signals, are high dimensional data. A large number of local maxima (a.k.a. peaks) have to be analyzed as part of computational pipelines aimed at the realization of efficient predictive and screening protocols. With this kind of data dimensions and samples size the risk of over-fitting and selection bias is pervasive. Therefore the development of bio-informatics methods based on unsupervised feature extraction can lead to general tools which can be applied to several fields of predictive proteomics.
PloS one, 2013
Embryonic stem cells (ESCs) are characterized by two remarkable peculiarities: the capacity to pr... more Embryonic stem cells (ESCs) are characterized by two remarkable peculiarities: the capacity to propagate as undifferentiated cells (self-renewal) and the ability to differentiate in ectoderm, endoderm, and mesoderm derivatives (pluripotency). Although the majority of ESCs divide without losing the pluripotency, it has become evident that ESC cultures consists of multiple cell populations highlighted by the expression of early germ lineage markers during spontaneous differentiation. Hence, the identification and characterization of ESCs subpopulations represents an efficient approach to improve the comprehension of correlation between gene expression and cell specification status. To study markers of ESCs heterogeneity, we developed an analysis pipeline which can automatically process images of stem cell colonies in optical microscopy. The question we try to address is to find out the statistically significant preferred locations of the marked cells. We tested our algorithm on a set of images of stem cell colonies to analyze the expression pattern of the Zscan4 gene, which was an elite candidate gene to be studied because it is specifically expressed in subpopulation of ESCs. To validate the proposed method we analyzed the behavior of control genes whose pattern had been associated to biological status such as differentiation (EndoA), pluripotency (Pou5f1), and pluripotency fluctuation (Nanog). We found that Zscan4 is not uniformly expressed inside a stem cell colony, and that it tends to be expressed towards the center of the colony, moreover cells expressing Zscan4 cluster each other. This is of significant importance because it allows us to hypothesize a biological status where the cells expressing Zscan4 are preferably associated to the inner of colonies suggesting pluripotent cell status features, and the clustering between themselves suggests either a colony paracrine effect or an early phase of cell specification through proliferation. Also, the analysis on the control genes showed that they behave as expected. Citation: Paduano V, Tagliaferri D, Falco G, Ceccarelli M (2013) Automated Identification and Location Analysis of Marked Stem Cells Colonies in Optical Microscopy Images. PLoS ONE 8(12): e80776.
Lecture Notes in Computer Science, 2003
... 1 RCOST - Research Centre on Software Technology University of Sannio, Department of Engineer... more ... 1 RCOST - Research Centre on Software Technology University of Sannio, Department of Engineering Palazzo ex Poste, Via Traiano, I-82100 Benevento, Italy 2 Institute of Genetic and Biophysics, “A. Buzzati Traverso”, CNR, Napoli Abstract. ...
Lecture Notes in Computer Science, 2011
Signature learning from gene expression consists into selecting a subset of molecular markers whi... more Signature learning from gene expression consists into selecting a subset of molecular markers which best correlate with prognosis. It can be cast as a feature selection problem. Here we use as optimality criterion the separation between survival curves of clusters induced by the selected features. We address some important problems in this fields such as developing an unbiased search procedure and significance analysis of a set of generated signatures. We apply the proposed procedure to the selection of gene signatures for Non Small Lung Cancer prognosis by using a real data-set.
Lecture Notes in Computer Science, 2008
Abstract. Many indexes have been proposed in literature for the com-parison of two crisp data par... more Abstract. Many indexes have been proposed in literature for the com-parison of two crisp data partitions, as resulting from two different clas-sifications attempts, two different clustering solutions or the comparison of a predicted vs. a true labeling. Most of these indexes ...
Lecture Notes in Computer Science, 2009
Abstract. Mass spectrometry spectra are recognized as a screening tool for detecting discriminato... more Abstract. Mass spectrometry spectra are recognized as a screening tool for detecting discriminatory protein patterns. Mass spectra, however, are high dimensional data and a large number of local maxima (aka peaks) have to be analyzed; to tackle this problem we have developed a ...
International Journal of Pattern Recognition and Artificial Intelligence, 2006
Image descriptions aimed at the realization of content-based image retrieval (CBIR) should handle... more Image descriptions aimed at the realization of content-based image retrieval (CBIR) should handle the vagueness of both data representations and user queries. Here show how multiscale textural gradient can be used as an efficient visual cue for image description. This feature has been already efficiently used in problems of image segmentation and texture separation. Our main idea is based on the assumption that, for image description, shape and textures should be considered together within a unified model. We report an efficient image description algorithm where the multiscale analysis is modeled by a differential morphological filter. Experiments with large image databases and comparisons with classical methods are reported.
Perspectives in Neural Computing, 1997
2013 IEEE 13th International Working Conference on Source Code Analysis and Manipulation (SCAM), 2013
Emails and issue reports capture useful knowledge about development practices, bug fixing, and ch... more Emails and issue reports capture useful knowledge about development practices, bug fixing, and change activities. Extracting such a content is challenging, due to the mix-up of source code and natural language, unstructured text.
Proceedings of the 32nd ACM/IEEE International Conference on Software Engineering - ICSE '10, 2010
Change impact analysis aims at identifying software artifacts being affected by a change. In the ... more Change impact analysis aims at identifying software artifacts being affected by a change. In the past, this problem has been addressed by approaches relying on static, dynamic, and textual analysis. Recently, techniques based on historical analysis and association rules have been explored.
2010 IEEE International Conference on Software Maintenance, 2010
In recent years, techniques based on association rules discovery have been extensively used to de... more In recent years, techniques based on association rules discovery have been extensively used to determine changecoupling relations between artifacts that often changed together. Although association rules worked well in many cases, they fail to capture logical coupling relations between artifacts modified in subsequent change sets.
American Journal of Clinical Pathology, 2014
: We explored the impact of ePVI on different BC subtypes. In a total of 2,116 BCs, 91 ePVI-BCs, ... more : We explored the impact of ePVI on different BC subtypes. In a total of 2,116 BCs, 91 ePVI-BCs, 70 inflammatory breast carcinomas (IBCs), and 114 casual BCs as a control group (CG-BC) were recruited. Results: Patients affected by ePVI-BC were younger, had larger tumors, higher histologic grade, elevated Ki-67 score, Her2/neu overexpressed, and more lymph node metastases compared with CG-BC (P < .001). Interestingly, only younger mean age at diagnosis differentiated patients with ePVI-BC from patients affected by IBC. ePVI-BC showed a clinical outcome intermediate between the prognoses of IBC and CG-BC. by guest on
Lecture Notes in Computer Science, 2011
Supervised learning methods have been recently exploited to learn gene regulatory networks from g... more Supervised learning methods have been recently exploited to learn gene regulatory networks from gene expression data. The basic approach consists into building a binary classifier from feature vectors composed by expression levels of a set of known regulatory connections, available in public databases or known in literature. Such a classifier is then used to predict new unknown connections. The quality of the training set plays a crucial role in such an inference scheme. In binary classification the training set should be composed ...
Uploads
Papers by Michele Ceccarelli