Search results for " mammography"
showing 10 items of 23 documents
Comparative Study of Feature classification Methods for Mass Lesion Recognition in Digitized Mammograms
2007
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…
Underuse of long-term routine hospital follow-up care in patients with a history of breast cancer?
2011
Abstract Background After primary treatment for breast cancer, patients are recommended to use hospital follow-up care routinely. Long-term data on the utilization of this follow-up care are relatively rare. Methods Information regarding the utilization of routine hospital follow-up care was retrieved from hospital documents of 662 patients treated for breast cancer. Utilization of hospital follow-up care was defined as the use of follow-up care according to the guidelines in that period of time. Determinants of hospital follow up care were evaluated with multivariate analysis by generalized estimating equations (GEE). Results The median follow-up time was 9.0 (0.3-18.1) years. At fifth and…
Mammographic images segmentation based on chaotic map clustering algorithm
2013
Background: This work investigates the applicability of a novel clustering approach to the segmentation of mammographic digital images. The chaotic map clustering algorithm is used to group together similar subsets of image pixels resulting in a medically meaningful partition of the mammography. Methods: The image is divided into pixels subsets characterized by a set of conveniently chosen features and each of the corresponding points in the feature space is associated to a map. A mutual coupling strength between the maps depending on the associated distance between feature space points is subsequently introduced. On the system of maps, the simulated evolution through chaotic dynamics leads…
Direct Measurement of Mammographic X-Ray Spectra with a Digital CdTe Detection System
2012
In this work we present a detection system, based on a CdTe detector and an innovative digital pulse processing (DPP) system, for high-rate X-ray spectroscopy in mammography (1–30 keV). The DPP system performs a height and shape analysis of the detector pulses, sampled and digitized by a 14-bit, 100 MHz ADC. We show the results of the characterization of the detection system both at low and high photon counting rates by using monoenergetic X-ray sources and a nonclinical X-ray tube. The detection system exhibits excellent performance up to 830 kcps with an energy resolution of 4.5% FWHM at 22.1 keV. Direct measurements of clinical molybdenum X-ray spectra were carried out by using a pinhole…
Can 3D Digital Breast Tomosynthesis (DBT) improve breast malignant pathology detection? A case-to-case imaging comparison between 3D DBT and 2D Mammo…
2014
Learning objectives Background Findings and procedure details Conclusion Personal information References
SU-E-I-83: Detectability Limits of a New Positron Emission Mammography in Relation to Tumour-Size, Tumour-To-Background Ratio and Activity Concentrat…
2017
Purpose:Positron emission mammography(PEM) improves spatial resolution and sensitivity, making it suitable for early breast tumours detection. The aim of this study is to evaluate the limits of a dedicated breast PET in terms of tumour‐size, tumour‐to‐background activity concentration ratio (TBR) and activity concentration. Methods: A dedicated PEM is evaluated. To characterize the device, we use a phantom of 15 cm of diameter containing 6 inserts of inner diameters 18, 15, 11, 8, 5 and 3 mm. To evaluate the detectability limits images are acquired by varying the TBR from 10 to 2 and without background activity concentration. In all the studies the activity concentration for the 6 inserts i…
Evaluation of DR and CR digital mammography systems based on phantom and breast dosimetry.
2006
Digital mammography has been progressively introduced in screening centers, since recent evolution of CR and DR detectors. However, it is questionable which exposure conditions would be more suitable when these techniques are applied, in order to reduce the glandular breast doses, as they are related with induced carcinogenesis. Several exposures have been performed in CR and DR mammography units for comparing absorbed doses during quality control assessments and during screening, diagnosis and treatment. In the first case, the CIRS11A mammographic phantom has been used with standard exposure conditions (28 kV, AEC mode with blackening +0, 50:50 glandularity and 4.5 compressed breast thickn…
High-rate x-ray spectroscopy in mammography with a CdTe detector: A digital pulse processing approach
2010
Purpose:Direct measurement of mammographic x-ray spectra under clinical conditions is a difficult task due to the high fluence rate of the x-ray beams as well as the limits in the development of high resolution detection systems in a high counting rate environment. In this work we present a detection system, based on a CdTe detector and an innovative digital pulse processing (DPP) system, for high-rate x-ray spectroscopy in mammography. Methods: The DPP system performs a digital pile-up inspection and a digital pulse height analysis of the detector signals, digitized through a 14-bit, 100 MHz digitizer, for x-ray spectroscopy even at high photon counting rates. We investigated on the respon…
Fast Fourier Transform Filtering for Bilateral Mammography Comparison
2010
Bilateral Asymmetry is one of the breast abnormalities that may indicate a cancer in early stage. The computer methods for the bilateral subtraction developed up to now show the problem of large false positives number because the alignment defects. On the other hand the computer methods using FFT approach suffer of a low S/N ratio to distinguish massive lesions from background. In this paper a method (FFT-RF-BMC) is presented to enhanche the bilateral asymmetry using a FFT to detect massive lesions through a Recursive Filtering.
Distributed medical images analysis on a Grid infrastructure
2007
In this paper medical applications on a Grid infrastructure, the MAGIC-5 Project, are presented and discussed. MAGIC-5 aims at developing Computer Aided Detection (CADe) software for the analysis of medical images on distributed databases by means of GRID Services. The use of automated systems for analyzing medical images improves radiologists’ performance; in addition, it could be of paramount importance in screening programs, due to the huge amount of data to check and the cost of related manpower. The need for acquiring and analyzing data stored in different locations requires the use of Grid Services for the management of distributed computing resources and data. Grid technologies allow…