Comparison of multiple definitions for ventilator-associated pneumonia in patients requiring mechanical ventilation for non-pulmonary conditions: preliminary data from PULMIVAP, an Italian multi-centre cohort study.

OBJECTIVES: To compare intensivist-diagnosed ventilator-associated pneumonia (iVAP) with four established definitions, assessing their agreement in detecting new episodes. METHODS: A multi-centric prospective study on pulmonary microbiota was carried out in patients requiring mechanical ventilation (MV). Data collected were used to compare hypothetical VAP onset according to iVAP with the study consensus criteria, the European Centre for Disease Control and Prevention definition, and two versions of the latter adjusted for leukocyte count and fever. RESULTS: In our cohort of 186 adult patients, iVAPs were 36.6% (68/186, 95% confidence interval 30.0-44.0%), with an incidence rate of 4.64/100 patient-MV-days, and median MV-day at diagnosis of 6. Forty-seven percent of patients (87/186) were identified as VAP by at least one criterion, with a median MV-day at diagnosis of 5. Agreement between intensivist judgement (iVAP/no-iVAP) and the criteria was highest for the study consensus criteria (50/87, 57.4%), but still one-third of iVAP were not identified and 9% of patients were identified as VAP contrary to intensivist diagnosis. VAP proportion differed between criteria (25.2-30.1%). CONCLUSIONS: Caution is needed when evaluating studies describing VAP incidence. Pre-agreed criteria and definitions that capture VAP's evolving nature provide greater consistency, but new clinically driven definitions are needed to align surveillance and diagnostic criteria with clinical practice.

Microcalcification detection in full-field digital mammograms: A fully automated computer-aided system.

BACKGROUND: Microcalcification clusters in mammograms can be considered as early signs of breast cancer. However, their detection is a very challenging task because of different factors: large variety of breast composition, highly textured breast anatomy, impalpable size of microcalcifications in some cases, as well as inherent low contrast of mammograms. Thus, the need to support the clinicians' work with an automatic tool. METHODS: In this work a three-phases approach for clustered microcalcification detection is presented. Specifically, it is made up of a pre-processing step, aimed at highlighting potentially interesting breast structures, followed by a single microcalcification detection step, based on Hough transform, that is able to grasp the innate characteristic shape of the structures of interest. Finally, a cluster identification step to group microcalcifications is carried out by means of a clustering algorithm able to codify expert domain rules. RESULTS: The detection performance of the proposed method has been evaluated on 364 mammograms of 182 patients obtaining a true positive ratio of 91.78% with 2.87 false positives per image. CONCLUSIONS: Experimental results demonstrated that the proposed method is able to detect microcalcification clusters in digital mammograms showing performance comparable to different methodologies exploited in the state-of-art approaches, with the advantage that it does not require any training phase and a large set of data. The performance of the proposed approach remains high even for more difficult clinical cases of mammograms of young women having high-density breast tissue thus resulting in a reduced contrast between microcalcifications and surrounding dense tissues.

A Gradient-Based Approach for Breast DCE-MRI Analysis.

Breast cancer is the main cause of female malignancy worldwide. Effective early detection by imaging studies remains critical to decrease mortality rates, particularly in women at high risk for developing breast cancer. Breast Magnetic Resonance Imaging (MRI) is a common diagnostic tool in the management of breast diseases, especially for high-risk women. However, during this examination, both normal and abnormal breast tissues enhance after contrast material administration. Specifically, the normal breast tissue enhancement is known as background parenchymal enhancement: it may represent breast activity and depends on several factors, varying in degree and distribution in different patients as well as in the same patient over time. While a light degree of normal breast tissue enhancement generally causes no interpretative difficulties, a higher degree may cause difficulty to detect and classify breast lesions at Magnetic Resonance Imaging even for experienced radiologists. In this work, we intend to investigate the exploitation of some statistical measurements to automatically characterize the enhancement trend of the whole breast area in both normal and abnormal tissues independently from the presence of a background parenchymal enhancement thus to provide a diagnostic support tool for radiologists in the MRI analysis.

MAGIC-5: an Italian mammographic database of digitised images for research.

The implementation of a database of digitised mammograms is discussed. The digitised images were collected beginning in 1999 by a community of physicists in collaboration with radiologists in several Italian hospitals as a first step in developing and implementing a computer-aided detection (CAD) system. All 3,369 mammograms were collected from 967 patients and classified according to lesion type and morphology, breast tissue and pathology type. A dedicated graphical user interface was developed to visualise and process mammograms to support the medical diagnosis directly on a high-resolution screen. The database has been the starting point for developing other medical imaging applications, such as a breast CAD, currently being upgraded and optimised for use in a distributed environment with grid services, in the framework of the Instituto Nazionale di Fisicia Nucleare (INFN)-funded Medical Applications on a Grid Infrastructure Connection (MAGIC)-5 project.

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 radiologist's 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.

Topographic classification of EEG patterns in Huntington's disease.

The aim of this study is to perform a topographic classification of electroencephalographic (EEG) patterns in subjects affected by the Huntington's disease (HD). The alpha activity is a discriminating feature for HD, as its amplitude reduction turns out to be a clear mark of the illness. When used as input variable to a supervised neural network, a good classification of pathological patterns and control ones is achieved with high values of sensitivity and specificity. It should be useful to get more insight into the local discriminating capabilities of the alpha rhythm by implementing a neural network approach to classify EEG patterns extracted from groups of channels corresponding to specific regions of the scalp. Receiver operating characteristic (ROC) curve analysis enables one to label each region with the value of the area under the curve, thus providing a local significance for HD classification. A reduction of the area when processing regions of the scalp, with respect to the whole, suggests that all channels provide significant contribution to HD pattern discrimination. These results can be interpreted as an effect of an abnormal subcortical modulation of the alpha rhythm, due to the dysfunctional action of the thalamus on the cortical activities. In a further study, morphometric features of thalamus and basal ganglia, evaluated by MRI, will be matched with the electrophysiological findings.

Detection of subclinical brain electrical activity changes in Huntington's disease using artificial neural networks.

OBJECTIVE: The aim of this study was to analyze EEG background activity in Huntington's disease (HD) patients and relatives at risk, in relation to CAG repeat size and clinical state, in order to detect an electrophysiological marker of early disease. METHODS: We selected 13 patients and 7 subjects at risk. Thirteen normal subjects, sex- and age-matched, were also evaluated. Artifact-free epochs were selected and analyzed through Fast-Fourier Transform. EEG background activity was tested using both linear analysis and artificial neural network (ANN) classifier in order to evaluate whether EEG abnormalities were linked to functional changes preceding the onset of the disease. RESULTS: The most important EEG classification pattern was the absolute alpha power not correlated with cognitive decline. The ANN correctly classified 11/13 patients and 12/13 normals. Moreover, the neural scores for subjects at risk seemed to be correlated to the expected time before the onset of the disease. CONCLUSIONS: ANN is a very powerful method to discriminate between normals and patients. It could be used as an automatic diagnostic tool. EEG changes in positive gene-carriers for HD confirm an early functional impairment which should be taken into account in the genetic counseling and in the management of the early stages of the disease.