Matteo Masotti

A novel featureless approach to mass detection in digital mammograms based on support vector machines

In this work, we present a novel approach to mass detection in digital mammograms. The great variability of the appearance of masses is the main obstacle to building a mass detection method. It is indeed demanding to characterize all the varieties of masses with a reduced set of features. Hence, in our approach we have chosen not to extract any feature, for the detection of the region of interest; in contrast, we exploit all the information available on the image. A multiresolution overcomplete wavelet representation is performed, in order to codify the image with redundancy of information. The vectors of the very-large space obtained are then provided to a first support vector machine (SVM) classifier. The detection task is considered here as a two-class pattern recognition problem: crops are classified as suspect or not, by using this SVM classifier. False candidates are eliminated with a second cascaded SVM. To further reduce the number of false positives, an ensemble of experts is applied: the final suspect regions are achieved by using a voting strategy. The sensitivity of the presented system is nearly 80% with a false-positive rate of 1.1 marks per image, estimated on images coming from the USF DDSM database.

Computer-aided detection of lung nodules via 3D fast radial transform, scale space representation, and Zernike MIP classification.

PURPOSE The authors presented a novel system for automated nodule detection in lung CT exams. METHODS The approach is based on (1) a lung tissue segmentation preprocessing step, composed of histogram thresholding, seeded region growing, and mathematical morphology; (2) a filtering step, whose aim is the preliminary detection of candidate nodules (via 3D fast radial filtering) and estimation of their geometrical features (via scale space analysis); and (3) a false positive reduction (FPR) step, comprising a heuristic FPR, which applies thresholds based on geometrical features, and a supervised FPR, which is based on support vector machines classification, which in turn, is enhanced by a feature extraction algorithm based on maximum intensity projection processing and Zernike moments. RESULTS The system was validated on 154 chest axial CT exams provided by the lung image database consortium public database. The authors obtained correct detection of 71% of nodules marked by all radiologists, with a false positive rate of 6.5 false positives per patient (FP/patient). A higher specificity of 2.5 FP/patient was reached with a sensitivity of 60%. An independent test on the ANODE09 competition database obtained an overall score of 0.310. CONCLUSIONS The system shows a novel approach to the problem of lung nodule detection in CT scans: It relies on filtering techniques, image transforms, and descriptors rather than region growing and nodule segmentation, and the results are comparable to those of other recent systems in literature and show little dependency on the different types of nodules, which is a good sign of robustness.

Texture classification using invariant ranklet features

A novel invariant texture classification method is proposed. Invariance to linear/non-linear monotonic gray-scale transformations is achieved by submitting the image under study to the ranklet transform, an image processing technique relying on the analysis of the relative rank of pixels rather than on their gray-scale value. Some texture features are then extracted from the ranklet images resulting from the application at different resolutions and orientations of the ranklet transform to the image. Invariance to 90^o-rotations is achieved by averaging, for each resolution, correspondent vertical, horizontal, and diagonal texture features. Finally, a texture class membership is assigned to the texture feature vector by using a support vector machine (SVM) classifier. Compared to three recent methods found in literature and having being evaluated on the same Brodatz and Vistex datasets, the proposed method performs better. Also, invariance to linear/non-linear monotonic gray-scale transformations and 90^o-rotations are evidenced by training the SVM classifier on texture feature vectors formed from the original images, then testing it on texture feature vectors formed from contrast-enhanced, gamma-corrected, histogram-equalized, and 90^o-rotated images.

TESTING THE PERFORMANCES OF DIFFERENT IMAGE REPRESENTATIONS FOR MASS CLASSIFICATION IN DIGITAL MAMMOGRAMS

The classification of tumoral masses and normal breast tissue is targeted. A mass detection algorithm which does not refer explicitly to shape, border, size, contrast or texture of mammographic suspicious regions is evaluated. In the present approach, classification features are embodied by the image representation used to encode suspicious regions. Classification is performed by means of a support vector machine (SVM) classifier. To investigate whether improvements can be achieved with respect to a previously proposed overcomplete wavelet image representation, a pixel and a discrete wavelet image representations are developed and tested. Evaluation is performed by extracting 6000 suspicious regions from the digital database for screening mammography (DDSM) collected by the University of South Florida (USF). More specifically, 1000 regions representing biopsy-proven tumoral masses (either benign or malignant) and 5000 regions representing normal breast tissue are extracted. Results demonstrate very high performance levels. The area Az under the receiver operating characteristic (ROC) curve reaches values of 0.973 +/- 0.002, 0.948 +/- 0.004 and 0.956 +/- 0.003 for the pixel, discrete wavelet and overcomplete wavelet image representations, respectively. In particular, the improvement in the Az value with the pixel image representation is statistically significant compared to that obtained with the discrete wavelet and overcomplete wavelet image representations (two-tailed p-value < 0.0001). Additionally, 90% true positive fraction (TPF) values are achieved with false positive fraction (FPF) values of 6%, 11% and 7%, respectively.

Application of Support Vector Machine to the classification of volcanic tremor at Etna, Italy

We applied an automatic pattern recognition technique, known as Support Vector Machine (SVM), to classify volcanic tremor data recorded during different states of activity at Etna volcano, Italy. The seismic signal was recorded at a station deployed 6 km southeast of the summit craters from 1 July to 15 August, 2001, a time span encompassing episodes of lava fountains and a 23 day-long effusive activity. Trained by a supervised learning algorithm, the classifier learned to recognize patterns belonging to four classes, i.e., pre-eruptive, lava fountains, eruptive, and post-eruptive. Training and test of the classifier were carried out using 425 spectrogram-based feature vectors. Following cross-validation with a random subsampling strategy, SVM correctly classified 94.7 ± 2.4% of the data. The performance was confirmed by a leave-one-out strategy, with 401 matches out of 425 patterns. Misclassifications highlighted intrinsic fuzziness of class memberships of the signals, particularly during transitional phases.

TREMOrEC: a software utility for automatic classification of volcanic tremor

We describe a stand-alone software utility named TREMOrEC, which carries out training and test of a Support Vector Machine (SVM) classifier. TREMOrEC is developed in Visual C++ and runs under Microsoft Windows operating systems. Ease of use and short time processing, along with the excellent performance of the SVM classifier, make this tool ideal for volcano monitoring. The development of TREMOrEC is motivated by the successful application of the SVM classifier to volcanic tremor data recorded at Mount Etna in 2001. In that application, spectrograms of volcanic tremor were divided according to their recording date into four classes associated with different states of activity, i.e., preeruptive, lava fountain, eruptive, or post-eruptive. During the training, SVM learned the a priori classification. The classifier’s performance was then evaluated on test sets not considered for training. The classification results matched the actual class membership with an error of less than 6%.

A ranklet-based CAD for digital mammography

A novel approach to the detection of masses and clustered microcalcification is presented. Lesion detection is considered as a two-class pattern recognition problem. In order to get an effective and stable representation, the detection scheme codifies the image by using a ranklet transform. The vectors of ranklet coefficients obtained are classified by means of an SVM classifier. Our approach has two main advantages. First it does not need any feature selected by the trainer. Second, it is quite stable, with respect to the image histogram. That allows us to tune the detection parameters in one database and use the trained CAD on other databases without needing any adjustment. In this paper, training is accomplished on images coming from different databases (both digitized and digital). Test results are calculated on images coming from a few FFDM Giotto Image MD clinical units. The sensitivity of our CAD system is about 85% with a false-positive rate of 0.5 marks per image.

THE CONSUMER BEHAVIOUR AND NEW BRAND MANAGEMENT POLICIES OF ORGANIC FOOD IN ITALY: THE CASE STUDY OF “VIVI VERDE COOP”

Due to economic growth, social, cultural and demographic changes lead to changes on food production patterns. Increased instruction levels, strong urbanization and consequent depopulation of rural areas, increased number of working women, increased wealth of families, growth and differentiation of food demand led to deep innovations in consumers priorities and choices. It means that consumption behaviors are now more focused on food safety (search for secure, healthy and even biological food) rather than food security (the problem of food scarcity no longer affects the developed countries). Food producers and distributors, in particular large scale distribution, gradually adapted their strategies to meet the emerging consumers’ preferences. In this paper we analyze the brand management strategy “ViviVerde” pursued by Coop and, also we perfom an analysis of the demand elasticity of the food products sold with the ViviVerde label (eggs, milk, fresh cheese, pasta, fruit juices) from de period of January 2010 to May 2012 in the Italian Province of Bologna. The conclusions are that economic performance of a line of products of the ViviVerde Coop, that clearly pursues the Corporate Social Responsibility objectives, is positive and increasing. It demonstrates that those kinds of brand management strategies can be successful.

La linea commerciale Vivi Verde Coop: andamenti, diffusione e prospettive future

Social, cultural and demographic changes due to economic growth lead to changes on food production patterns. Increased instruction levels, strong urbanization and consequent depopulation of rural areas, increased number of working women, increased wealth of families, growth and differentiation of food demand led to deep innovations in consumers priorities and choices: consumption behaviors are now more focused on food safety (search for secure, healthy and even biological food) rather than food security (the problem of food scarcity no longer affects the developed countries). Food producers and distributors, in particular large scale distribution, gradually adapted their strategies to meet the emerging consumers’ preferences. In this paper we analyze the brand management strategy ViviVerde” pursued by Coop and, with an analysis of the demand elasticity of the food products sold with the ViviVerde label (eggs, milk, fresh cheese, pasta, fruit juices) from January 2010 to May 2012.