Search

Coeliac disease (CD) is a permanent inflammatory disease of the small intestine characterized by the destruction of the mucous membrane of this intestinal tract. Coeliac disease represents the most frequent food intolerance and affects about 1% of the population, but it is severely underdiagnosed. Currently available guidelines require CD-specific serology and atrophic histology in duodenal biopsy samples to diagnose CD in adults. In paediatric CD, but recently in adults also, non-invasive diagnostic strategies have become increasingly popular. In order to increase the rates of correct diagnosis of the disease without the use of biopsy, researchers have recently been using approaches based on artificial intelligence techniques. In this work, we present a Clinical Decision Support System (CDSS)system for supporting CD diagnosis, developed in the context of the Italy-Malta cross-border project ITAMA. The implemented CDSS has been based on a neural-network-based fuzzy classifier. The system was developed and tested using a Virtual Database and a Real Database acquired during the ITAMA project. Analysis on 10,000 virtual patients shows that the system achieved an accuracy of 99% and a sensitivity of 99%. On 19,415 real patients, of which 109 with a confirmed diagnosis of coeliac disease, the system achieved 99.6% accuracy, 85.7% sensitivity, 99.6% specificity and 96% precision. Such results show that the developed system can be used effectively to support the diagnosis of the CD by reducing the appeal to invasive techniques such as biopsy.

Purpose: Many semi-automated and fully-automated approaches have been proposed in literature to improve the objectivity of the estimation of conjunctival hyperemia, based on image processing analysis of eyes’ photographs. The purpose is to improve its evaluation using faster fully-automated systems and independent by the human subjectivity. Methods: In this work, we introduce a fully-automated analysis of the redness grading scales able to completely automatize the clinical procedure, starting from the acquired image to the redness estimation. In particular, we introduce a neural network model for the conjunctival segmentation followed by an image processing pipeline for the vessels network segmentation. From these steps, we extract some features already known in literature and whose correlation with the conjunctival redness has already been proved. Lastly, we implemented a predictive model for the conjunctival hyperemia using these features. Results: In this work, we used a dataset of images acquired during clinical practice.We trained a neural network model for the conjunctival segmentation, obtaining an average accuracy of 0.94 and a corresponding IoU score of 0.88 on a test set of images. The set of features extracted on these ROIs is able to correctly predict the Efron scale values with a Spearman’s correlation coefficient of 0.701 on a set of not previously used samples. Conclusions: The robustness of our pipeline confirms its possible usage in a clinical practice as a viable decision support system for the ophthalmologists.

We have developed a method for the detection of clusters of microcalcifications in digital mammograms. Here, we present a genetic algorithm used to optimize the choice of the parameters in the detection scheme. The optimization has allowed the improvement of the performance, the detailed study of the influence of the various parameters on the performance and an accurate investigation of the behavior of the detection method on unknown cases. We reach a sensitivity of 96.2% with 0.7 false positive clusters per image on the Nijmegen database; we are also able to identify the most significant parameters. In addition, we have examined the feasibility of a distributed genetic algorithm implemented on a non-dedicated Cluster Of Workstations. We get very good results both in terms of quality and efficiency.

Nodule growth as observed in computed tomography (CT) scans acquired at different times is the primary feature to malignancy of indeterminate small lung nodules. In this paper, we propose the estimation of nodule size through a scale-space representation which needs no segmentation and has high intra- and inter-operator reproducibility. Lung nodules usually appear in CT images as blob-like patterns and can be analyzed in the scale-space by Laplacian of Gaussian ( LoG ) kernels. For each nodular pattern the LoG scale-space signature was computed and the related characteristic scale adopted as measurement of nodule size. Both in vitro and in vivo validation of LoG characteristic scale were carried out. In vitro validation was done by 40 nondeformable phantoms and 10 deformable phantoms. A close relationship between the characteristic scale and the equivalent diameter, i.e., the diameter of the sphere having the same volume of nodules, (Pearson correlation coefficient was 0.99) and, for nodules undergoing little deformations (obtained at constant volume), small variability of the characteristic scale was observed. The in vivo validation was performed on low and standard-dose CT scans collected from the ITALUNG screening trial (86 nodules) and from the LIDC public data set (89 solid nodules and 40 part-solid nodules or ground-glass opacities). The Pearson correlation coefficient between characteristic scale and equivalent diameter was 0.83-0.93 for ITALUNG and 0.68-0.83 for LIDC data set. Intra- and inter-operator reproducibility of characteristic scale was excellent: on a set of 40 lung nodules of ITALUNG data, two radiologists produced identical results in repeated measurements. The scan-rescan variability of the characteristic scale was also investigated on 86 two-year-stable solid lung nodules (each one observed, on average, in four CT scans) identified in the ITALUNG screening trial: a coefficient of repeatability of about 0.9 mm was observed. Experimental evidence supports the clinical use of the LoG characteristic scale to measure nodule size in CT imaging.

Our working group has started a project aiming at the development of analysis algorithms devoted to images produced by two-dimensional electrophoresis (2-DE) for general applications in the field of proteomics. General analysis problems have been addressed, with the ultimate goal of the maximization of the "automation level" of the analysis procedure, without reducing the accuracy now reachable only with manual intervention. For this purpose, the working group is analyzing 2-DE images that a real ready stored or that will be produced by means of the instrumentation and the know-how of the biologists participating to the project. It's obvious that the "key" for the project success is primarily the availability of many images produced by different groups, but especially their "comparability", and their significant "clinical contextualization". For these reasons, the group has started the implementation of federation of heterogeneous biobanks of images founded on open registry/repository for P2P architecture (ebXML RR), on images stored with standard metadata for their comparability (EFMI MIP) (A. Horsch et al., 2005), and on standard electronic documents for their clinical contextualization (HL7 CDA) (G. Mercurio and A. Rossi Mori). This paper summarizes the concepts of the initiative, describes its current state and presents an overview of related work.

Aim of this study was to analyse diffusion tensor imaging (DTI) datasets in order to identify damaged areas or disorders of the brain in a semi-automatic way. For this purpose, a software tool has been developed: it takes in input the fractional anisotropy (FA) map of a (damaged) brain and, after several steps involving the comparison between the two brain hemispheres, it gives back, as output, a binary mask with a ROI (Region of Interest) that shows the probably damaged area. In the same way, starting from the MR image without diffusion weighting (b0), we find another ROI that we compare with the one previously detected from the FA map. Then we overlay these ROIs onto both the FA map and the image without diffusion weighting, trying to quantify how well the ROIs cover the pathological tissue. This procedure was repeated on a few patients (healthy and pathological ones). The algorithm worked well, showing as a preliminary result that FA maps allow a neater detection of the pathological tissue if compared to MR images without diffusion weighting.

Proteomics is the science that studies the proteome, that is the proteic expression of the genome. Cell proteome is extremely complex, and is composed of several thousand proteins. Two-dimensional polyacrylamide gel electrophoresis (2D-PAGE) is widely used as a standard method to separate and display proteins in a tissue or compound with a theoretical resolution of 104 proteins simultaneously. This technique combines the resolution power of isoelectrofocalization (IEF), which distinguishes proteins by their isoelectric point (pI), with SDS-PAGE (sodium dodecyl sulphate PAGE), in which proteins are separated according to their weight and molecular size. Our group is developing software algorithms for the automatic analysis of images obtained by 2D-PAGE gel optical scanning; our aim is the reduction of human intervention in the analysis process, currently quite slow, operator-dependent, and prone to errors. In our approach, image noise is first reduced, in order to limit false positives and protein missing. Proteins appear as dark spots on a light background, so the next step is local minima search. Then, the watershed transform is applied, which partitions the gel image into basins: each basin contains a single (recognized) minimum, but can possibly include more than one protein spot if less-deep minima are masked by the main one. At this point, we perform a registration between the work image and an atlas image (already analyzed by a biologist), and map the atlas spot positions to the work image. Each basin is then used as a region of interest (ROI) in which the shape of the spot (or spots) is fit to a model through a χ2-minimization procedure. The coordinates of the transformed spots are used as the fit initialization parameters.

We propose a method for automatic lung juxtapleural nodule detection in thorax CT images, to be used as a Computer Assisted Detection (CAD) tool by radiologists. It is based on the calculation and automatic analysis of local curvature on the lung surface as extracted from high-resolution CT scans, and exploits uniformization to a sphere (e.g. through conformal mapping) to allow a global view of the lung surface, with marking of high curvature regions which can be suspected of being pleural nodules. Schematically, the tool works as follows. First, lung binary masks are extracted from the image by 3D segmentation of the CT scan. On these masks, pleural nodules appear as small surface concavities of the mask surface. After patching the entrance of vessels into the parenchyma in the hilus pulmonis, the lung frontier 'Sigma' is a smooth genus-0 surface. This surface is triangulated and is then uniformized to a sphere 'Sigma-prime' . In this parameterization a suitable function Psi of the mean and the Gaussian curvatures can be calculated over Sigma. Function Psi is displayed as a colour variation onto both Sigma and Sigma-prime, so marking regions that represent high-curvature concavities. A threshold on Psi is then applied and regions of interest (ROIs), containing little concavities with a low radius of curvature (such as pleural nodules), are detected. ROIs are then examined and classified; techniques such as spherical wavelets are available on the sphere, which will be used to distinguish between false and true positives, helping in diagnosing pleural nodules.

Compressed images are usually used in biomedical data transmission and storage. They play an significant role in diagnostic and interventional radiology since they can contain data from different (separately) biomedical instrumental techniques: MRI, angiography, CT, etc.. In this context, an appropriate methodology of removing artifact has a primary importance in order to improve signal-to-noise ratio. In this paper we propose a quick methodology of helping radiologists and clinicians in assessing particular diagnosis. The suggested methodology is based on Hough transform to be compared, in terms of efficiency, with other ones related to blocking artifact evaluation.

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.

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 remote image analysis and interactive online diagnosis, with a relevant reduction of the delays presently associated with the diagnosis in the screening programs. The MAGIC-5 project develops algorithms for the analysis of mammographies for breast cancer detection, Computed- Tomography (CT) images for lung cancer detection and Positron Emission Tomography (PET) images for the early diagnosis of Alzheimer Disease (AD). A Virtual Organization (VO) has been deployed, so that authorized users can share data and resources and implement the following use cases: screening, tele-training and tele-diagnosis for mammograms and lung CT scans, statistical diagnosis by comparison of candidates to a distributed data-set of negative PET scans for the diagnosis of the AD. A small-scale prototype of the required Grid functionality was already implemented for the analysis of digitized mammograms.

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 image's 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

In the traditional way of learning from examples of objects the classifiers are built in a feature space. However, alternative ways can be found by constructing decision rules on dissimilarity (distance) representations. In such a recognition process a new object is described by its distances to (a subset of) die training samples. The use of the dissimilarities is especially of interest when features are difficult to obtain or when they have a little discriminative power. Purpose of this work is the development of an automatic classification system which could be useful for radiologists in the investigation of breast cancer. The software has been designed in the framework of the MAGIC-5 collaboration. In the automatic classification system the suspicious regions with high probability to include a lesion are extracted from the image as regions of interest (ROIs). Each ROI is characterized by some features extracted from co-occurrence matrix containing spatial statistics information on ROI pixel gray tones. A dissimilarity representation of diese features is made before me classification. A feed-forward neural network is employed to distinguish pathological records, from non-pathological ones by the new features. The results obtained in terms of sensitivity (percentage of pathological ROIs correctly classified) and specificity (percentage of non-pathological ROIs correcdy classified) will be presented.

In the present paper we discuss a new approach for the detection of microcalcification clusters, based on neural networks and developed as part of the MAGIC-5 project, an INFN-funded program which aims at the development and implementation of CAD algorithms in a GRID-based distributed environment. The proposed approach has as its roots the desire to maximize the rejection of background during the analytical pre-processing stage, in order to train and test the neural network with as clean as possible a sample and therefore maximize its performance. The algorithm is composed of three modules: the image pre-processing, the feature extraction component and the Backpropagation Neural Network module. The First module comprises the use of several algorithms: H-Dome Transformation, Masking, Binarisation of grayscale images, Connected Components Labeling; for the classification, initially 27 features are extracted from the output image, features that are statistically analyzed and reduced to 17, which are used as input to the Backpropagation Neural Network. The algorithm was trained (tested) on 139 (139) images respectively, containing 149 (152) true clusters and 146 (415) false

In this paper, we investigate the performance of a Computer Aided Diagnosis (CAD) system for the detection of clustered microcalcifications in mammograms. Our detection algorithm consists of the combination of two different methods. The first, based on difference-image techniques and gaussianity statistical tests, finds out the most obvious signals. The second, is able to discover more subtle microcalcifications by exploiting a multiresolution analysis by means of the wavelet transform. We can separately tune the two methods, so that each one of them is able to detect signals with similar features. By combining signals coming out from the two parts through a logical OR operation, we can discover microcalcifications with different characteristics. Our algorithm yields a sensitivity of 91.4% with 0.4 false positive cluster per image on the 40 images of the Nijmegen database.

The MAGIC-5 Project aims at developing Computer Aided Detection (CAD) software for Medical Applications on distributed databases by means of GRID Services. The use of automated systems for analyzing medical images has been demonstrated to improve the radiologist 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 remote image analysis and interactive online diagnosis, with a relevant reduction of the delays presently associated to the diagnosis in screening programs. The MAGIC-5 project develops algorithms for the analysis of mammographies for breast cancer detection, Computed-Tomography (CT) images for lung cancer detection and Positron Emission Tomography (PET) imaging for the early diagnosis of the Alzheimer Disease (AD). We plan to configure a Virtual Organization (VO), so that authorized users can share data and resources and implement the following use cases: screening, tele-training and tele-diagnosis for mammograms and lung CT scans; statistical diagnosis by comparison of candidates to a distributed data-set of negative PET scans for the diagnosis of the Alzheimer Disease. A smallscale prototype of the required GRID functionality was already implemented for the analysis of digitized mammograms.