0000000000120904
AUTHOR
P. Oliva
Comparative Study of Feature classification Methods for Mass Lesion Recognition in Digitized Mammograms
In this work a comparison of different classification methods for the identification of mass lesions in digitized mammograms is performed. These methods, used in order to develop Computer Aided Detection (CAD) systems, have been implemented in the framework of the MAGIC-5 Collaboration. The system for identification of mass lesions is based on a three-step procedure: a) preprocessing and segmentation, b) region of interest (ROI) searching, c) feature extraction and classification. It was tested on a very large mammographic database (3369 mammographic images from 967 patients). Each ROI is characterized by eight features extracted from a co-occurrence matrix containing spatial statistics inf…
Search for signatures of magnetically-induced alignment in the arrival directions measured by the Pierre Auger Observatory
We present the results of an analysis of data recorded at the Pierre Auger Observatory in which we search for groups of directionally-aligned events (or ‘multiplets’) which exhibit a correlation between arrival direc- tion and the inverse of the energy. These signatures are expected from sets of events coming from the same source after having been deflected by intervening coherent magnetic fields. The observation of several events from the same source would open the possibility to accurately reconstruct the position of the source and also measure the integral of the component of the magnetic field orthogonal to the trajectory of the cos- mic rays. We describe the largest multiplets found an…
Superior Performances of the Neural Network on the Masses Lesions Classification through Morphological Lesion Differences
Purpose of this work is to develop an automatic classification system that could be useful for radiologists in the breast cancer investigation. The software has been designed in the framework of the MAGIC-5 collaboration. In an automatic classification system the suspicious regions with high probability to include a lesion are extracted from the image as regions of interest (ROIs). Each ROI is characterized by some features based generally on morphological lesion differences. A study in the space features representation is made and some classifiers are tested to distinguish the pathological regions from the healthy ones. The results provided in terms of sensitivity and specificity will be p…
Dissimilarity Application in Digitized Mammographic Images Classification.
Purpose of this work is the development of an automatic classification system which could be useful for radiologists in the investigation of breast cancer. The software has been designed in the framework of the MAGIC-5 collaboration. In the traditional way of learning from examples of objects the classifiers are built in a feature space. However, an alternative ways can be found by constructing decision rules on dissimilarity (distance) representations. In such a recognition process a new object is described by its distances to (a subset of) the training samples. The use of the dissimilarities is especially of interest when features are difficult to obtain or when they have a little discrim…
Massive Lesions Classification using Features based on Morphological Lesion Differences
Purpose of this work is the development of an automatic classification system which could be useful for radiologists in the investigation of breast cancer. The software has been designed in the framework of the MAGIC-5 collaboration. In the automatic classification system the suspicious regions with high probability to include a lesion are extracted from the image as regions of interest (ROIs). Each ROI is characterized by some features based on morphological lesion differences. Some classifiers as a Feed Forward Neural Network, a K-Nearest Neighbours and a Support Vector Machine are used to distinguish the pathological records from the healthy ones. The results obtained in terms of sensiti…
Mammogram segmentation by contour searching and massive lesion classification with neural network
The mammography is the most effective procedure for an early diagnosis of the breast cancer. In this paper, an algorithm for detecting massive lesions in mammographic images will be presented. The database consists of 3762 digital images acquired in several hospitals belonging to the MAGIC-5 collaboration. A reduction of the surface under investigation is achieved, without loss of meaningful information, through segmentation of the whole image, by means of a ROI Hunter algorithm. In the following classification step, feature extraction plays a fundamental role: some features give geometrical information, other ones provide shape parameters. Once the features are computed for each ROI, they …
A study of the effect of molecular and aerosol conditions in the atmosphere on air fluorescence measurements at the Pierre Auger Observatory
The air fluorescence detector of the Pierre Auger Observatory is designed to perforin calorimetric measurements of extensive air showers created by Cosmic rays of above 10(18) eV. To correct these measurements for the effects introduced by atmospheric fluctuations, the Observatory contains a group Of monitoring instruments to record atmospheric conditions across the detector site, ail area exceeding 3000 km(2). The atmospheric data are used extensively in the reconstruction of air showers, and are particularly important for the correct determination of shower energies and the depths of shower maxima. This paper contains a summary of the molecular and aerosol conditions measured at the Pierr…
Search for First Harmonic Modulation in the Right Ascension Distribution of Cosmic Rays Detected at the Pierre Auger Observatory
We present the results of searches for dipolar-type anisotropies in different energy ranges above 2.5 × 1017 eV with the surface detector array of the Pierre Auger Observatory, reporting on both the phase and the amplitude measurements of the first harmonic modulation in the right-ascension distribution. Upper limits on the amplitudes are obtained, which provide the most stringent bounds at present, being below 2% at 99% C.L. for EeV energies. We also compare our results to those of previous experiments as well as with some theoretical expectations.
Measurement of the Depth of Maximum of Extensive Air Showers above 10(18) eV
We describe the measurement of the depth of maximum, Xmax, of the longitudinal development of air showers induced by cosmic rays. Almost four thousand events above 10¹⁸ eV observed by the fluorescence detector of the Pierre Auger Observatory in coincidence with at least one surface detector station are selected for the analysis. The average shower maximum was found to evolve with energy at a rate of (106⁺³⁵₋₂₁) g/cm²/decade below 1018.24 ± 0.05 eV and (24 ± 3) g/cm²/decade above this energy. The measured shower-to-shower fluctuations decrease from about 55 to 26 g/cm². The interpretation of these results in terms of the cosmic ray mass composition is briefly discussed.
Search for ultrahigh energy neutrinos in highly inclined events at the Pierre Auger Observatory
Erratum: Phys. Rev. D 85, 029902(E) (2012) [http://dx.doi.org/10.1103/PhysRevD.85.029902]
The effect of the geomagnetic field on cosmic ray energy estimates and large scale anisotropy searches on data from the Pierre Auger Observatory
We present a comprehensive study of the influence of the geomagnetic field on the energy estimation of extensive air showers with a zenith angle smaller than $60^\circ$, detected at the Pierre Auger Observatory. The geomagnetic field induces an azimuthal modulation of the estimated energy of cosmic rays up to the ~2% level at large zenith angles. We present a method to account for this modulation of the reconstructed energy. We analyse the effect of the modulation on large scale anisotropy searches in the arrival direction distributions of cosmic rays. At a given energy, the geomagnetic effect is shown to induce a pseudo-dipolar pattern at the percent level in the declination distribution t…