G. De Nunzio

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 are used as inputs to a supervised neural network with momentum. The output neuron provides the probability that the ROI is pathological or not. Results are provided in terms of ROC and FROC curves; the area under the ROC curve was found to be Az=(85.6plusmn0.8)%. This software is included in the CAD station actually working in the hospitals belonging to the MAGIC-5 Collaboration

A completely automated CAD system for mass detection in a large mammographic database

Mass localization plays a crucial role in computer-aided detection (CAD) systems for the classification of suspicious regions in mammograms. In this article we present a completely automated classification system for the detection of masses in digitized mammographic images. The tool system we discuss consists in three processing levels: (a) Image segmentation for the localization of regions of interest (ROIs). This step relies on an iterative dynamical threshold algorithm able to select iso-intensity closed contours around gray level maxima of the mammogram. (b) ROI characterization by means of textural features computed from the gray tone spatial dependence matrix (GTSDM), containing second-order spatial statistics information on the pixel gray level intensity. As the images under study were recorded in different centers and with different machine settings, eight GTSDM features were selected so as to be invariant under monotonic transformation. In this way, the images do not need to be normalized, as the adopted features depend on the texture only, rather than on the gray tone levels, too. (c) ROI classification by means of a neural network, with supervision provided by the radiologists diagnosis. The CAD system was evaluated on a large database of 3369 mammographic images [2307 negative, 1062 pathological (or positive), containing at least one confirmed mass, as diagnosed by an expert radiologist]. To assess the performance of the system, receiver operating characteristic (ROC) and free-response ROC analysis were employed. The area under the ROC curve was found to be Az = 0.783 +/- 0.008 for the ROI-based classification. When evaluating the accuracy of the CAD against the radiologist-drawn boundaries, 4.23 false positives per image are found at 80% of mass sensitivity.

Mammogram Segmentation by Contour Searching and Mass Lesions 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 masses in mammographic images will be presented. The database consists of 3762 digital images acquired in several hospitals belonging to the MAGIC-5 collaboration (Medical Applications on a Grid Infrastructure Connection). A reduction of the whole images area under investigation is achieved through a segmentation process, by means of a ROI Hunter algorithm, without loss of meaningful information. 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 are used as inputs to a supervised neural network with momentum. The output neuron provides the probability that the ROI is pathological or not. Results are provided in terms of ROC and FROC curves: the area under the ROC curve was found to be AZ=0.862plusmn0.007, and we get a 2.8 FP/Image at a sensitivity of 82%. This software is included in the CAD station actually working in the hospitals belonging to the MAGIC-5 Collaboration

Pleural nodule identification in low-dose and thin-slice lung computed tomography

A completely automated system for the identification of pleural nodules in low-dose and thin-slice computed tomography (CT) of the lung has been developed. The directional-gradient concentration method has been applied to the pleura surface and combined with a morphological opening-based procedure to generate a list of nodule candidates. Each nodule candidate is characterized by 12 morphological and textural features, which are analyzed by a rule-based filter and a neural classifier. This detection system has been developed and validated on a dataset of 42 annotated CT scans. The k-fold cross validation has been used to evaluate the neural classifier performance. The system performance variability due to different ground truth agreement levels is discussed. In particular, the poor 44% sensitivity obtained on the ground truth with agreement level 1 (nodules annotated by only one radiologist) with six FP per scan grows up to the 72% if the underlying ground truth is changed to the agreement level 2 (nodules annotated by two radiologists).

The MAGIC-5 Project: medical applications on a GRID infrastructure connection

The MAGIC-5 Project aims at developing computer aided detection (CAD) software for medical applications on distributed databases by means of a GRID infrastructure connection. The use of automatic systems for analyzing medical images is of paramount importance in the screening programs, due to the huge amount of data to check. Examples are: mammographies for breast cancer detection, computed-tomography (CT) images for lung cancer analysis, and the positron emission tomography (PET) imaging for the early diagnosis of the Alzheimer disease. The need for acquiring and analyzing data stored in different locations requires a GRID approach of distributed computing system and associated data management. The GRID technologies allow remote image analysis and interactive online diagnosis, with a relevant reduction of the delays actually associated to the screening programs. From this point of view, the MAGIC-5 Collaboration can be seen as a group of distributed users sharing their resources for implementing different virtual organizations (VO), each one aiming at developing screening programs, tele-training, tele-diagnosis and epidemiologic studies for a particular pathology.

Lung Nodule Detection in Screening Computed Tomography

A computer-aided detection (CAD) system for the identification of pulmonary nodules in low-dose multi-detector helical Computed Tomography (CT) images with 1.25 mm slice thickness is presented. The basic modules of our lung-CAD system, a dot-enhancement filter for nodule candidate selection and a neural classifier for false-positive finding reduction, are described. The results obtained on the collected database of lung CT scans are discussed.

Subsurface water-content identification in a crypt using GPR and comparison with microclimatic conditions

The effects of climate, pollution and human negligence cause severe and sometimes irreversible damage to buildings and monuments of cultural interest. It is well known that the presence of water and/or moisture content in a porous material is the initial cause of deterioration. In a previous paper, the authors reported an integrated study on a building of cultural importance, namely the crypt of the Cattedrale di Otranto in Apulia, Italy, based on non-destructive integrated biological and physical surveys. The method described was able to identify the ‘internal’ factors responsible for deterioration. It was discovered that the distribution of moisture in the stone depended mainly on adverse environmental conditions, and the presence of wet buried structures in the ground. The first aim of the present study was to identify subsurface water-content in this same crypt using a ground-penetrating radar (GPR) technique, and to compare these results with those of the previous microclimatic survey. In particular, the existence of underground discontinuities was verified; we located them and analysed their influence. Moreover, by means of velocity analysis, we obtained a quantitative estimate of the volumetric water-content under the pavement of the crypt. This finding completes the results of the previous research, as it indicates the causes of the deterioration in the crypt and provides significant information, on the basis of which, effective decisions can be made for safeguarding the historic building.

Generating a Minimal Set of Templates for the Hippocampal Region in MR Neuroimages

We detail a procedure for generating a set of templates for the hippocampal region in magnetic resonance (MR) images, representative of the clinical conditions of the population under investigation.

Low cost alternatives to commercial lab kits for physics experiments

Conducting experiments in physics using modern measuring techniques, and particularly those utilizing computers, is often much more attractive to students than conducting experiments conventionally. However, the cost of professional kits in the Czech Republic is still very expensive for many schools. The basic equipment for one student workplace in the case of professional kits such as Vernier, Pasco or Coach costs around 800 euros. In this paper some physics experiments in which a computer, or a tablet with Microsoft Windows, is used as the measuring device, along with available physical devices such as a laser pointer, a solar cell or an electret microphone, are presented as suitable and alternative ways to carry out lab work. We show that it is possible to perform very simple school experiments (both as a central demonstration and as individual experimentation), in which high accuracy and clear final conclusions can be achieved at a very low cost. Further information is published on the specialized webpage www.sclpx.eu/index.php?lang=en. The worksheets are in Czech, but the English version is in preparation.

A Percolative Approach to Reliability of Thin Film Interconnects and Ultra-thin Dielectrics

Degradation of thin film interconnects and ultra-thin dielectrics is studied within a stochastic approach based on a percolation technique. The thin film is modelled as a two-dimensional random resistor network at a given temperature and its degradation is characterized by a breaking probability of the single resistor. A recovery of the damage is also allowed so that a steady-state condition can be achieved. The main features of experiments are reproduced. This approach provides a unified description of degradation and failure processes in terms of physical parameters.