M. Salmeri

Oslo University Hospital, Oslo, Oslo, Norway

Are you M. Salmeri?

Claim your profile

Publications (66)23.53 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: We hypothesize that quantification of structural similarity or dissimilarity between paired mammographic regions can be effective in detecting asymmetric signs of breast cancer. Bilateral masking procedures are applied for this purpose by using automatically detected anatomical landmarks. Changes in structural information of the extracted regions are investigated using spherical semivariogram descriptors and correlation-based structural similarity indices in the spatial and complex wavelet domains. The spatial distribution of grayscale values as well as of the magnitude and phase responses of multidirectional Gabor filters are used to represent the structure of mammographic density and of the directional components of breast tissue patterns, respectively. A total of 188 mammograms from the DDSM and mini-MIAS databases, consisting of 47 asymmetric cases and 47 normal cases, were analyzed. For the combined dataset of mammograms, areas under the receiver operating characteristic curves of 0.83, 0.77, and 0.87 were obtained, respectively, with linear discriminant analysis, the Bayesian classifier, and an artificial neural network with radial basis functions, using the features selected by stepwise logistic regression and leave-onepatient- out cross-validation. Two-view analysis provided accuracy up to 0.94, with sensitivity and specificity of 1 and 0.88, respectively.
    IEEE transactions on medical imaging. 10/2014;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Segmentation of the breast region is a fundamental step in any system for computerized analysis of mammograms. In this work, we propose a novel procedure for the estimation of the breast skin-line based upon multidirectional Gabor filtering. The method includes an adaptive values-of-interest (VOI) transformation, extraction of the skin-air ribbon by Otsu's thresholding method and the Euclidean distance transform, Gabor filtering with 18 real kernels, and a step for suppression of false edge points using the magnitude and phase responses of the filters. On a test set of 361 images from different acquisition modalities (screen-film and full-field digital mammograms), the average Hausdorff and polyline distances obtained were 2.85mm and 0.84mm, respectively, with reference to the ground-truth boundaries provided by an expert radiologist. When compared with the results obtained by other state-of-the-art methods on the same set of images and with respect to the same ground-truth boundaries, our method mostly outperformed the other approaches. The results demonstrate the effectiveness and robustness of the proposed algorithm.
    Computers in biology and medicine 11/2013; 43(11):1870-81. · 1.27 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a novel approach for classification of breast masses is presented that quantifies the texture of masses without relying on accurate extraction of their contours. Two novel feature descriptors based on 2D extensions of the reverse arrangement (RA) and Mantel's tests were designed for this purpose. Measures of radial correlation and radial trend were extracted from the original gray-scale values as well as from the Gabor magnitude response of 146 regions of interest, including 120 benign masses and 26 malignant tumors. Four classifiers, Fisher-linear discriminant analysis, Bayesian, support vector machine, and an artificial neural network based on radial basis functions (ANN-RBF), were employed to predict the diagnosis, using stepwise logistic regression for feature selection and the leave-one-patient-out method for cross-validation. The ANN-RBF resulted in an area under the receiver operating characteristic curve of 0.93. The experimental results show the effectiveness of the proposed approach.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 07/2013; 2013:6490-6493.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Automatic detection of the nipple in mammograms is an important step in computerized systems that combine multiview information for accurate detection and diagnosis of breast cancer. Locating the nipple is a difficult task owing to variations in image quality, presence of noise, and distortion and displacement of the breast tissue due to compression. In this work, we propose a novel Hessian-based method to locate automatically the nipple in screen-film and full-field digital mammograms (FFDMs). The method includes detection of a plausible nipple/retroareolar area in a mammogram using geometrical constraints, analysis of the gradient vector field by mean and Gaussian curvature measurements, and local shape-based conditions. The proposed procedure was tested on 566 mammographic images consisting of 372 randomly selected scanned films from two public databases (mini-MIAS and DDSM), and 194 digital mammograms acquired with a GE Senographe 2000D FFDM system. A radiologist independently marked the centers of the nipples for evaluation of the results. The average error obtained was 6.7 mm (22 pixels) with reference to the center of the nipple as identified by the radiologist. Only two out of the 566 detected nipples (0.35 %) had an error larger than 50 mm. The method was also directly compared with two other techniques for the detection of the nipple. The results indicate that the proposed method outperforms other algorithms presented in the literature and can be used to identify accurately the nipple on various types of mammographic images.
    Journal of Digital Imaging 03/2013; · 1.10 Impact Factor
  • Arianna Mencattini, Marcello Salmeri, Paola Casti
    [Show abstract] [Hide abstract]
    ABSTRACT: Receiving Operating Curve (ROC) analysis is a powerful and statistical accepted method to assess the performance of a diagnostic test. ROC curve plots true positive rate against false positive rate, evaluated on a certain population. Instrumental and model uncertainty contributions can strongly affect the performance of the ROC analysis especially in the evaluation of performance metrics such as Area Under ROC (AUC) and Optimal Operating Points. Supplement 2 reports detailed instructions to handle and propagate uncertainty through a Multiple Input Multiple Output system, in case of correlate output variables, such as TPR and FPR. After a detailed revision of the existing literature, the present paper describes and applies a novel methodology, totally framed in the GUM and its supplements, to represent and propagate the uncertainty contributions estimated in a medical context, throughout the ROC analysis, providing new concepts such as ROC confidence region and Optimal Operating Region.
    Measurement. 01/2013; 46(1):66–79.
  • [Show abstract] [Hide abstract]
    ABSTRACT: We propose a method to analyze bilateral asymmetry in mammograms based upon systematic comparison of paired mammographic strips of the right and left breasts of a patient. Similarity between corresponding directional structures was quantified by applying measures of similarity to the masked strips. A novel application of Moran's index was designed to measure the angular covariance between rose diagrams related to the phase and magnitude responses of multidirectional Gabor filters. A set of 128 mammograms from the DDSM database, including 32 normal and 32 asymmetric pairs, was used to validate the procedure. The leave-one-patient-out method was used for cross-validation of the results. The best result, with an area under the receiver operating characteristic curve of 0.8435, was achieved using similarity measures on craniocaudal views and Fisher-linear discriminant analysis. The results indicate that the proposed techniques can be applied for computer-aided detection of bilateral asymmetry.
    E-Health and Bioengineering Conference (EHB), 2013; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: We present new feature descriptors specifically designed to quantify angular nonstationarity and angular dependence of pixel values in sectors of mammographic lesions. A key novelty of this work is that the proposed measures characterize the texture of masses without relying on accurate determination of their contours. An artificial neural network based on radial basis functions was used to predict the diagnosis of 120 benign masses and 26 malignant tumors in a database of full-field digital mammograms. Features were selected using stepwise logistic regression and the leave-one-patient-out method was used for cross-validation of results. An area under the receiver operating characteristic curve of 0.9890 ± 0.0114 was obtained using randomly selected centroids and an expected size of the masses. Results indicate that the use of the proposed contour-independent features can be an effective approach for computer-aided classification of mammographic lesions.
    E-Health and Bioengineering Conference (EHB), 2013; 01/2013
  • Source
    Manish Kakar, Arianna Mencattini, Marcello Salmeri
    [Show abstract] [Hide abstract]
    ABSTRACT: Automatic tools for detection and identification of lung and lesion from high-resolution CT (HRCT) are becoming increasingly important both for diagnosis and for delivering high-precision radiation therapy. However, development of robust and interpretable classifiers still presents a challenge especially in case of non-small cell lung carcinoma (NSCLC) patients. In this paper, we have attempted to devise such a classifier by extracting fuzzy rules from texture segmented regions from HRCT images of NSCLC patients. A fuzzy inference system (FIS) has been constructed starting from a feature extraction procedure applied on overlapping regions from the same organs and deriving simple if-then rules so that more linguistically interpretable decisions can be implemented. The proposed method has been tested on 138 regions extracted from CT scan images acquired from patients with lung cancer. Assuming two classes of tissues C1 (healthy tissues) and C2 (lesion) as negative and positive, respectively; preliminary results report an AUC = 0.98 for lesions and AUC = 0.93 for healthy tissue, with an optimal operating condition related to sensitivity = 0.96, and specificity = 0.98 for lesions and sensitivity 0.99, and specificity = 0.94 for healthy tissue. Finally, the following results have been obtained: false-negative rate (FNR) = 6 % (C1), FNR = 2 % (C2), false-positive rate (FPR) = 4 % (C1), FPR = 3 % (C2), true-positive rate (TPR) = 94 %, (C1) and TPR = 98 % (C2).
    Journal of Digital Imaging 08/2012; · 1.10 Impact Factor
  • Source
    Arianna Mencattini, Marcello Salmeri
    Mammography - Recent Advances, 03/2012; , ISBN: 978-953-51-0285-4
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this work we propose a joint two-side masking procedure for automatic analysis of mammographic images. The primary objective is the improvement of computerized systems capability in revealing additional findings, as the asymmetrical changes of the breast parenchyma. The method allows the proper comparison of the left and right breast by progressive selection of paired small areas on the mammogram, primarily the so-called "forbidden areas", zones that need special attention in mammographic interpretation. The masking of specific areas of the mammogram requires the identification of two anatomical structures of the breast: the pectoral muscle and the nipple used, together with the breast skin line, to find paired matching points on the images for comparison. With this purpose, specific algorithms have been developed. In particular, a new method for nipple extraction will be presented and validated by expert radiologists, by the use of a proprietary program developed by the authors. Finally, an application example of the automatic Tabar masking procedure will be shown, in order to point out the potential of this method in detection of suspicious areas in mammograms.
    Computer-Based Medical Systems (CBMS), 2012 25th International Symposium on; 01/2012
  • Arianna Mencattini, Marcello Salmeri
    [Show abstract] [Hide abstract]
    ABSTRACT: Breast masses exhibit variability in margins, shapes, and dimensions, so their detection is a difficult task in mammographic computer-aided diagnosis. Mass detection is usually a two-step procedure: mass identification and false-positive reduction. A new method to automatically detect mass lesions in mammographic images with tuning according to the breast tissue density was developed and tested. A modified phase portrait analysis method was introduced, based on the eigenvalue condition number and an eigenvalue intensity map. The method uses an iterative and tissue density-adaptive segmentation procedure with extraction of geometric features. False-positive reduction is accomplished using a fuzzy inference-based classifier. A leave-one-image-out cross-validation procedure was implemented, and stepwise regression analysis was used to automatically extract an optimal set of features. Testing and validation were performed on two different data sets containing at least one malignant mass D1 (388 images) and D2 (674 images), and a third data set N1 (50 images) was used consisting of normal controls. These three data sets were taken from the Digital Database for Screening Mammography. For sensitivities of 0.9, 0.85, 0.80, and 0.75, the best results on cancer images exhibit an False-Positive per Image (FPpI) equal to 0.6, 0.45, 0.35, and 0.3, respectively, using a Bayes Linear Discriminant Analysis (LDA) classifier and an FPpI of 0.85, 0.7, 0.55, and 0.45 using a fuzzy inference system (FIS) for false-positive reduction. When the algorithm is tested on normal images, an FPpI equal to 0.4, 0.3, 0.25, and 0.2 was observed using LDA and 0.3, 0.25, 0.2, and 0.15 using the FIS. A preclinical study of an automatic breast mass detection algorithm provided promising results in terms of sensitivity and low false-positive rate. Further development and clinical testing are justified based on the results.
    International Journal of Computer Assisted Radiology and Surgery 10/2011; 7(4):573-83. · 1.36 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Patients in the Intensive Care Unit (ICU) require huge resources because of the dysfunction of several of their vital organs. The heterogeneity and complexity of the ICU patients have generated interest in systems able to measure severity of illness as a method of predicting outcome, compare quality-of-care, analyze the costs of treating critically ill patients, evaluate stratification of clinical trials. The present work aims at developing a new scoring system to assess the severity of illness of patients admitted to general ICUs, by an observational, prospective, cohort study. The model will be developed in the period of study considering a population of the general ICU at the University Hospital Polyclinic of Tor Vergata so that the data obtained will be usable for Italian health care resource management and ICU performance evaluation within the hospital, the region, and nationwide. The proposed scoring system will revise the presently available systems, in the attempt to overcome their major drawbacks in the definition of the input variables, in the mathematical model employed to process them and the considered outcome. An important and qualifying point of this work lies in the attention paid to quantify and process the different sources of uncertainty, originated by the approximations introduced in the considered model and in the collection stage of the predictor variables.
    Medical Measurements and Applications Proceedings (MeMeA), 2011 IEEE International Workshop on; 07/2011
  • A. Mencattini, M. Salmeri, P. Casti
    [Show abstract] [Hide abstract]
    ABSTRACT: Breast cancer is the second most common cancer overall and the leading cause of cancer deaths in women. Mammography is, at present, the only viable method for detecting most of tumors early enough for effective treatment. The secret of setting up the accurate diagnosis is to detect and understand the most subtle signs of breast lesions. Analysis of asymmetry between the left and right mammograms can provide clues about the presence of early signs of tumors. In this work we present an automated procedure for bilateral asymmetry detection composed of the following steps: (1) mammography density analysis and fibro-glandular disc detection through adaptive clustering techniques, (2) analysis and implementation of bilateral asymmetries detection algorithms based on Gabor filters analysis, (3) use of a linear Bayes classifier with the leave-one-out method to asses the asymmetry degree of the two breasts, (4) metrological evaluation of the whole system through random and systematic measurement uncertainty contributions modeling.
    Medical Measurements and Applications Proceedings (MeMeA), 2011 IEEE International Workshop on; 07/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a novel approach for the automatic breast boundary segmentation using spatial fuzzy c-means clustering and active contours models. We will evaluate the performance of the approach on screen film mammographic images digitized by specific scanner devices and full-field digital mammographic images at different spatial and pixel resolutions. Expert radiologists have supplied the reference boundary for the massive lesions along with the biopsy proven pathology assessment. A performance assessment procedure will be developed considering metrics such as precision, recall, F-measure, and accuracy of the segmentation results. A Montecarlo simulation will be also implemented to evaluate the sensitivity of the boundary extracted on the initial settings and on the image noise.
    Medical Measurements and Applications Proceedings (MeMeA), 2011 IEEE International Workshop on; 07/2011
  • MIAD 2011 - Proceedings of the 2nd International Workshop on Medical Image Analysis and Description for Diagnosis Systems, Rome, Italy, January, 2011; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: At present, mammography is the most effective examination for an early diagnosis of breast cancer. Nevertheless, the detection of cancer signs in mammograms is a difficult procedure owing to the great number of non-pathological structures which are also present in the image. Recent statistics show that in current breast cancer screenings 10%–25% of the tumors are missed by the radiologists. For this reason, a lot of research is currently being done to develop systems for Computer Aided Detection (CADe). Probably, some causes of the false-negative screening examinations are that tumoral masses have varying dimension and irregular shape, their borders are often ill-defined and their contrast is very low, thus making difficult the discrimination from parenchymal structures. Therefore, in a CADe system a preliminary segmentation procedure has to be implemented in order to separate the mass from the background tissue. In this way, various characteristics of the segmented mass can be evaluated and used in a classification step to discriminate benign and malignant cases. In this paper, we describe an effective algorithm for massive lesions segmentation based on a region-growing technique and we provide full details the performance evaluation procedure used in this specific context.
    Computer Standards & Interfaces. 01/2011; 33:128-135.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we perform the assessment of a CAD for the tumoral masses classification in mammograms by the uncertainty propagation through the system. Carrying on the work of the authors concerning the metrological characterization of the developed CAD, we validate the features extraction, features selection, and classification steps in this paper. In particular, suitable metrics such as the Receiving Operating Curve (ROC) and the Area Under ROC (AUC) are widely used in order to provide a quantitative evaluation of the performance. Finally, we implement a Monte Carlo simulation in order to provide the confidence interval for some coverage probabilities for all involved parameters. The procedure is tested on mammographic images containing both malignant and benign breast masses.
    IEEE Transactions on Instrumentation and Measurement 12/2010; · 1.71 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Breast cancer is the main cause of cancer deaths among women in the world. About one million new cases appear every year, and about 25% of them lead to the death of the patient. The best solution is the early detection of suspicious tumoral signs through an effective mammographic screening program. Unfortunately, this kind of images is very difficult to interpret by the radiologists because of its very low contrast, so proper image-processing procedures could help them to achieve better diagnoses. This paper improves and assesses an algorithm, already proposed by the authors, that suggests to doctors the suspicious regions that could contain tumoral masses. The procedure succeeds also in the case of very low contrast because it depends only on the orientation of the gradient vectors in the image but not on their amplitude.
    IEEE Transactions on Instrumentation and Measurement 11/2010; · 1.71 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Breast cancer is the most common cancer in women. Fortunately, in the last years, the percentage of recovery has become higher and higher. The reasons are multiple: prevention, better surgery techniques, better diagnoses. In order to improve diagnostic performance, many Computer Aided Diagnosis systems have been developed in the latest years, which help the radiologists to detect and classify lump-masses. These systems, however, do not yet consider the uncertainty associated to the measurements (the mammography), even if, from a metrological point of view, they should. In this paper, measurement uncertainty is considered through a fuzzy inference system for the classification of microcalcifications in digital mammography.
    Instrumentation and Measurement Technology Conference (I2MTC), 2010 IEEE; 06/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we consider uncertainty handling and propagation by means of random fuzzy variables (RFVs) through a computer-aided-diagnosis (CADx) system for the early diagnosis of breast cancer. In particular, the denoising and the contrast enhancement of microcalcifications is specifically addressed, providing a novel methodology for separating the foreground and the background in the image to selectively process them. The whole system is then assessed by metrological aspects. In this context, we assume that the uncertainty associated to each pixel of the image has both a random and a non-negligible systematic contribution. Consequently, a preliminary noise variance estimation is performed on the original image, and then, using suitable operators working on RFVs, the uncertainty propagation is evaluated through the whole system. Finally, we compare our results with those obtained by a Monte Carlo method.
    IEEE Transactions on Instrumentation and Measurement 02/2010; · 1.71 Impact Factor

Publication Stats

252 Citations
23.53 Total Impact Points

Institutions

  • 2012
    • Oslo University Hospital
      • Institute for Cancer Research
      Oslo, Oslo, Norway
  • 1997–2012
    • University of Rome Tor Vergata
      • Dipartimento di Ingegneria Civile e Ingegneria Informatica (DICII)
      Roma, Latium, Italy
  • 2006
    • Università Degli Studi Roma Tre
      • Department of Electronic Engineering
      Roma, Latium, Italy
  • 1995–2000
    • The American University of Rome
      Roma, Latium, Italy