2002
Journal article
Restricted
Computational complexity analysis of a 3D neural network approach to volume matching
Di Bona S, Niemann H, Salvetti O, Wolf M
Automatic registration of digital images is an important support in the medical field for physicians and surgeons. In fact, comparison of anatomical scan is a fundamental procedure for disease prediction, lesions quantification or for evaluating the results of a therapy. A new proposed approach implements three-dimensional neural networks to match, and hence to register, volumetric data sets of the brain in order to evaluate the differences between two volumes. The high computational complexity of this approach has been improved by implementing a more efficient method to train the networks.Source: PATTERN RECOGNITION, vol. 12 (issue 1), pp. 63-69
Di Bona S, Niemann H, Salvetti O, Wolf M
Automatic registration of digital images is an important support in the medical field for physicians and surgeons. In fact, comparison of anatomical scan is a fundamental procedure for disease prediction, lesions quantification or for evaluating the results of a therapy. A new proposed approach implements three-dimensional neural networks to match, and hence to register, volumetric data sets of the brain in order to evaluate the differences between two volumes. The high computational complexity of this approach has been improved by implementing a more efficient method to train the networks.Source: PATTERN RECOGNITION, vol. 12 (issue 1), pp. 63-69
2003
Journal article
Restricted
A simulation model for analyzing brain structures deformations
Di Bona S, Lutzemberger L, Salvetti O
Recent developments of medical software applications,from the simulation to the planning of surgical operations,have revealed the need for modelling human tissues and organs, not only from a geometric point of viewbut also from a physical one, i.e. soft tissues, rigid body, viscoelasticity, etc. This has given rise to the term 'deformable objects', which refers to objects with a morphology, a physical and a mechanical behaviour of their own and that reflects their natural properties. In this paper, we propose a model, based upon physical laws, suitable for the realistic manipulation of geometric reconstructions of volumetric data taken from MR and CT scans. In particular, a physically based model of the brain is presented that is able to simulate the evolution of different nature pathological intra-cranial phenomena such as haemorrhages, neoplasm, haematoma, etc and to describe the consequences that are caused by their volume expansions and the influences they have on the anatomical and neuro-functional structures of the brain.Source: PHYSICS IN MEDICINE AND BIOLOGY, vol. 48, pp. 4001-4002
Di Bona S, Lutzemberger L, Salvetti O
Recent developments of medical software applications,from the simulation to the planning of surgical operations,have revealed the need for modelling human tissues and organs, not only from a geometric point of viewbut also from a physical one, i.e. soft tissues, rigid body, viscoelasticity, etc. This has given rise to the term 'deformable objects', which refers to objects with a morphology, a physical and a mechanical behaviour of their own and that reflects their natural properties. In this paper, we propose a model, based upon physical laws, suitable for the realistic manipulation of geometric reconstructions of volumetric data taken from MR and CT scans. In particular, a physically based model of the brain is presented that is able to simulate the evolution of different nature pathological intra-cranial phenomena such as haemorrhages, neoplasm, haematoma, etc and to describe the consequences that are caused by their volume expansions and the influences they have on the anatomical and neuro-functional structures of the brain.Source: PHYSICS IN MEDICINE AND BIOLOGY, vol. 48, pp. 4001-4002
2007
Contribution to book
Restricted
Semi-automatic semantic tagging of 3D images from pancreas cells
Little S, Salvetti O, Perner P
Detailed, consistent semantic annotation of large collections of multimedia data is difficult and time-consuming. In domains such as eScience, digital curation and industrial monitoring, fine-grained high-quality labeling of regions enables advanced semantic querying, analysis and aggregation and supports collaborative research. Manual annotation is inefficient and too subjective to be a viable solution. Automatic solutions are often highly domain or application specific, require large volumes of annotated training corpi and, if using a 'black box' approach, add little to the overall scientific knowledge. This article evaluates the use of simple artificial neural networks to semantically annotate micrographs and discusses the generic process chain necessary for semi-automatic semantic annotation of images.
Little S, Salvetti O, Perner P
Detailed, consistent semantic annotation of large collections of multimedia data is difficult and time-consuming. In domains such as eScience, digital curation and industrial monitoring, fine-grained high-quality labeling of regions enables advanced semantic querying, analysis and aggregation and supports collaborative research. Manual annotation is inefficient and too subjective to be a viable solution. Automatic solutions are often highly domain or application specific, require large volumes of annotated training corpi and, if using a 'black box' approach, add little to the overall scientific knowledge. This article evaluates the use of simple artificial neural networks to semantically annotate micrographs and discusses the generic process chain necessary for semi-automatic semantic annotation of images.
See at:
CNR IRIS 
| CNR IRIS | www.springerlink.com
2007
Book
Restricted
Preface - Advances in mass data analysis of signals and images in medicine, biotechnology and chemistry
Perner P, Salvetti O
The automatic analysis of images and signals in medicine, biotechnology, and chemistry is a challenging and demanding field. Signal-producing procedures by microscopes, spectrometers, and other sensors have found their way into wide fields of medicine, biotechnology, economy, and environmental analysis. With this arises the problem of the automatic mass analysis of signal information. Signal-interpreting systems which generate automatically the desired target statements from the signals are therefore of compelling necessity. The continuation of mass analyses on the basis of classical procedures leads to investments of proportions that are not feasible. New procedures and system architectures are therefore required. The scope of the International Conference on Mass Data Analysis of Images and Signals in Medicine, Biotechnology and Chemistry MDA (www.mda-signals.de) is to bring together researchers, practitioners, and industry people who are dealing with mass analysis of images and signals to present and discuss recent research in these fields.Source: LECTURE NOTES IN COMPUTER SCIENCE, vol. 4826
Perner P, Salvetti O
The automatic analysis of images and signals in medicine, biotechnology, and chemistry is a challenging and demanding field. Signal-producing procedures by microscopes, spectrometers, and other sensors have found their way into wide fields of medicine, biotechnology, economy, and environmental analysis. With this arises the problem of the automatic mass analysis of signal information. Signal-interpreting systems which generate automatically the desired target statements from the signals are therefore of compelling necessity. The continuation of mass analyses on the basis of classical procedures leads to investments of proportions that are not feasible. New procedures and system architectures are therefore required. The scope of the International Conference on Mass Data Analysis of Images and Signals in Medicine, Biotechnology and Chemistry MDA (www.mda-signals.de) is to bring together researchers, practitioners, and industry people who are dealing with mass analysis of images and signals to present and discuss recent research in these fields.Source: LECTURE NOTES IN COMPUTER SCIENCE, vol. 4826
2008
Conference article
Restricted
Evaluation of feature subset selection, feature weighting, and prototype selection for biomedical applications
Little S, Salvetti O, Perner P
Many medical diagnosis applications are characterized by datasets that contain under-represented classes due to the fact that the disease appears more rarely than the normal case. In such a situation classifiers that generalize over the data such as decision trees and Naïve Bayesian are not the proper choice as classification methods. Case-based classifiers that can work on the samples seen so far are more appropriate for such a task. We propose to calculate the contingency table and class specific evaluation measures despite the overall accuracy for evaluation purposes of classifiers for these specific data characteristics. We evaluate the different options of our case-based classifier and compare the performance to decision trees and Naïve Bayesian. Finally, we give an outlook for further work.
Little S, Salvetti O, Perner P
Many medical diagnosis applications are characterized by datasets that contain under-represented classes due to the fact that the disease appears more rarely than the normal case. In such a situation classifiers that generalize over the data such as decision trees and Naïve Bayesian are not the proper choice as classification methods. Case-based classifiers that can work on the samples seen so far are more appropriate for such a task. We propose to calculate the contingency table and class specific evaluation measures despite the overall accuracy for evaluation purposes of classifiers for these specific data characteristics. We evaluate the different options of our case-based classifier and compare the performance to decision trees and Naïve Bayesian. Finally, we give an outlook for further work.
See at:
CNR IRIS | CNR IRIS | www.springerlink.com
2008
Book
Open Access
Advances in Mass Data Analysis of Images and Signals in Medicine, Biotechnology, Chemistry and Food Industry
Perner P, Salvetti O
The automatic analysis of signals and images together with the characterization and elaboration of their representation features is still a challenging activity in many relevant scientific and hi-tech fields such as medicine, biotechnology, and chemistry. Multidimensional and multisource signal processing can generate a number of information patterns which can be useful to increase the knowledge of several domains for solving complex problems. Furthermore, advanced signal and image manipulation allows relating specific application problems into pattern recognition problems, often implying also the development of KDD and other computational intelligence procedures. Nevertheless, the amount of data produced by sensors and equipments used in biomedicine, biotechnology and chemistry is usually quite huge and structured, thus strongly pushing the need of investigating advanced models and efficient computational algorithms for automating mass analysis procedures. Accordingly, signal and image understanding approaches able to generate automatically expected outputs become more and more essential, including novel conceptual approaches and system architectures. The purpose of this third edition of the International Conference on Mass Data Analysis of Signals and Images in Medicine, Biotechnology, Chemistry and Food Industry (MDA 2008; www.mda-signals.de) was to present the broad and growing scientific evidence linking mass data analysis with challenging problems in medicine, biotechnology and chemistry. Scientific and engineering experts convened at the workshop to present the current understanding of image and signal processing and interpretation methods useful for facing various medical and biological problems and exploring the applicability and effectiveness of advanced techniques as solutions. The primary goal of the conference was to disseminate this knowledge to a multidisciplinary community and encourage cooperative proactive collaboration in all the interested fields. We were pleased to see that the idea of the conference was taken up by a growing number of researchers and that we could start to bundle the activities in this area. We appreciate the help and understanding of the editorial staff at Springer, and in particular Alfred Hofmann, who supported the publication of these proceedings in the LNAI series. Last, but not least, we wish to thank all the speakers and participants who contributed to the success of the conference. The next International Conferences on Mass Data Analysis of Signals and Images (www.mda-signals.de) will be held in July 2009. We are looking forward to your submissions.
Perner P, Salvetti O
The automatic analysis of signals and images together with the characterization and elaboration of their representation features is still a challenging activity in many relevant scientific and hi-tech fields such as medicine, biotechnology, and chemistry. Multidimensional and multisource signal processing can generate a number of information patterns which can be useful to increase the knowledge of several domains for solving complex problems. Furthermore, advanced signal and image manipulation allows relating specific application problems into pattern recognition problems, often implying also the development of KDD and other computational intelligence procedures. Nevertheless, the amount of data produced by sensors and equipments used in biomedicine, biotechnology and chemistry is usually quite huge and structured, thus strongly pushing the need of investigating advanced models and efficient computational algorithms for automating mass analysis procedures. Accordingly, signal and image understanding approaches able to generate automatically expected outputs become more and more essential, including novel conceptual approaches and system architectures. The purpose of this third edition of the International Conference on Mass Data Analysis of Signals and Images in Medicine, Biotechnology, Chemistry and Food Industry (MDA 2008; www.mda-signals.de) was to present the broad and growing scientific evidence linking mass data analysis with challenging problems in medicine, biotechnology and chemistry. Scientific and engineering experts convened at the workshop to present the current understanding of image and signal processing and interpretation methods useful for facing various medical and biological problems and exploring the applicability and effectiveness of advanced techniques as solutions. The primary goal of the conference was to disseminate this knowledge to a multidisciplinary community and encourage cooperative proactive collaboration in all the interested fields. We were pleased to see that the idea of the conference was taken up by a growing number of researchers and that we could start to bundle the activities in this area. We appreciate the help and understanding of the editorial staff at Springer, and in particular Alfred Hofmann, who supported the publication of these proceedings in the LNAI series. Last, but not least, we wish to thank all the speakers and participants who contributed to the success of the conference. The next International Conferences on Mass Data Analysis of Signals and Images (www.mda-signals.de) will be held in July 2009. We are looking forward to your submissions.
See at:
CNR IRIS 
| link.springer.com | CNR IRIS
2008
Book
Open Access
Human-Activity Analysis in Multimedia Data
Salvetti O, Cetin E A, Pauwels E
Many important applications in multimedia revolve around the detection of humans and the interpretation of their behavior. These include surveillance and intrusion detection, video conferencing applications, assisted living applications, and automatic analysis of sports videos, broadcasts, and movies, to name just a few. Success in these tasks often requires the integration of various sensor or data modalities such as video, audio, motion, and accompanying text, and typically hinges on a host of machine-learning methodologies to handle the inherent variability and complexity of the ensuing features. The computational efficiency of the resulting algorithms is critical since the amount of data to be processed in multimedia applications is typically large, and in real-time systems, speed is of the essence. There have been several recent special issues dealing with the dection of humans and the analysis of their activity relying solely on video footage. In this special issue, we have tried to provide a platform to contributions that make use of a broader spectrum of multimedia information, complementing video with audio or text information as well as other types of sensor signals, whenever available. The first group of papers in the special issue addresses the joint use of audio and video data. The paperSource: EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING (ONLINE)
Salvetti O, Cetin E A, Pauwels E
Many important applications in multimedia revolve around the detection of humans and the interpretation of their behavior. These include surveillance and intrusion detection, video conferencing applications, assisted living applications, and automatic analysis of sports videos, broadcasts, and movies, to name just a few. Success in these tasks often requires the integration of various sensor or data modalities such as video, audio, motion, and accompanying text, and typically hinges on a host of machine-learning methodologies to handle the inherent variability and complexity of the ensuing features. The computational efficiency of the resulting algorithms is critical since the amount of data to be processed in multimedia applications is typically large, and in real-time systems, speed is of the essence. There have been several recent special issues dealing with the dection of humans and the analysis of their activity relying solely on video footage. In this special issue, we have tried to provide a platform to contributions that make use of a broader spectrum of multimedia information, complementing video with audio or text information as well as other types of sensor signals, whenever available. The first group of papers in the special issue addresses the joint use of audio and video data. The paperSource: EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING (ONLINE)
See at:
CNR IRIS | link.springer.com | CNR IRIS
2010
Book
Restricted
Advanced Infrared Technology and Applications
Abbozzo Ronchi L, Carlomagno G M, Corsi C, Grinzato E, Pippi I, Salvetti O
This special issue of the Journal of Modern Optics contains extended versions of selected papers accepted and presented at the 10th International Workshop on Advanced Infrared Technology and Applications held on 8-11 September 2009 at the Astronomy and Space Science Department of the University of Florence, Italy. The workshop - an event in a biennial series of meetings that started in 1991, and organised by Fondazione 'Giorgio Ronchi' (Florence), the Institutes of Information Science and Technologies 'Alessandro Faedo' (Pisa), Construction Technologies (Padova), Applied Physics 'Nello Carrara' (Florence) of the Italian National Research Council and the CREO Consortium, L'Aquila - constitutes a forum for bringing together academic and industrial researchers to exchange knowledge, ideas and experiences in the field of infrared (IR) science and technology. The main topics of the workshop included, in particular, advanced technology and materials, smart and fibre-optic sensors, aerospace and industrial applications, astronomy and earth monitoring, nondestructive tests and evaluation, systems for cultural heritage, near-, mid-, and long-wavelength systems, and image processing and data analysis. This special issue includes 17 papers that discuss scientific and technological aspects related to a few of these areas.Source: JOURNAL OF MODERN OPTICS (PRINT), pp. 1661-1662
DOI: 10.1080/09500340.2010.527708
Metrics:
Abbozzo Ronchi L, Carlomagno G M, Corsi C, Grinzato E, Pippi I, Salvetti O
This special issue of the Journal of Modern Optics contains extended versions of selected papers accepted and presented at the 10th International Workshop on Advanced Infrared Technology and Applications held on 8-11 September 2009 at the Astronomy and Space Science Department of the University of Florence, Italy. The workshop - an event in a biennial series of meetings that started in 1991, and organised by Fondazione 'Giorgio Ronchi' (Florence), the Institutes of Information Science and Technologies 'Alessandro Faedo' (Pisa), Construction Technologies (Padova), Applied Physics 'Nello Carrara' (Florence) of the Italian National Research Council and the CREO Consortium, L'Aquila - constitutes a forum for bringing together academic and industrial researchers to exchange knowledge, ideas and experiences in the field of infrared (IR) science and technology. The main topics of the workshop included, in particular, advanced technology and materials, smart and fibre-optic sensors, aerospace and industrial applications, astronomy and earth monitoring, nondestructive tests and evaluation, systems for cultural heritage, near-, mid-, and long-wavelength systems, and image processing and data analysis. This special issue includes 17 papers that discuss scientific and technological aspects related to a few of these areas.Source: JOURNAL OF MODERN OPTICS (PRINT), pp. 1661-1662
DOI: 10.1080/09500340.2010.527708
Metrics:
2002
Journal article
Restricted
A web site for the "Giorgio Ronchi" foundation
Galligani A, Salvetti O
This paper describes the main aspects of the Web Site designed and realized for the "Giorgio Ronchi" Foundation at the lnstitute of· lnfornation Processing of the Italian National Research Council,, in Pisa. The site is accessible remotely via network, allows connecting on-line the Foundation Library and it offers an actual and efficient instrument for giving worldwide knowledge about the Foundation and its activity.Source: ATTI DELLA FONDAZIONE GIORGIO RONCHI, vol. LVII (issue 2), pp. 195-208
Galligani A, Salvetti O
This paper describes the main aspects of the Web Site designed and realized for the "Giorgio Ronchi" Foundation at the lnstitute of· lnfornation Processing of the Italian National Research Council,, in Pisa. The site is accessible remotely via network, allows connecting on-line the Foundation Library and it offers an actual and efficient instrument for giving worldwide knowledge about the Foundation and its activity.Source: ATTI DELLA FONDAZIONE GIORGIO RONCHI, vol. LVII (issue 2), pp. 195-208
2002
Journal article
Restricted
A Web-based resource discovery facility for a Geo-Data Server
Galligani A, Salvetti O
This article deals with the design of a resource discovery system, based on a Web interface, for searching and downloading data stored in a Geo-Data Server. The main features of the Geo-Data Server are the design of a cartographic and image database, following international standards, a relational catalogue, containing meta-information on the archived data, and a high-level interface to access the system. The Geo-Data Server implements a distributed system where data are appropriately organised for remote consultation.
Galligani A, Salvetti O
This article deals with the design of a resource discovery system, based on a Web interface, for searching and downloading data stored in a Geo-Data Server. The main features of the Geo-Data Server are the design of a cartographic and image database, following international standards, a relational catalogue, containing meta-information on the archived data, and a high-level interface to access the system. The Geo-Data Server implements a distributed system where data are appropriately organised for remote consultation.
2003
Journal article
Restricted
A multilevel neural approach to dynamic scene analysis
Di Bona S, Salvetti O
A neural network architecture is presented for monitoring events coded in image time sequences. The image sequence defines the sampling of high frequency phenomena where only morphological aspects of the scene are taken into account. In particular a model for implementing a hierarchical neural network architecture is proposed. Preliminary results are shown in the study of the oscillation states in the flame front of the power plant gas combustors.Source: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 13, pp. 86-89
Di Bona S, Salvetti O
A neural network architecture is presented for monitoring events coded in image time sequences. The image sequence defines the sampling of high frequency phenomena where only morphological aspects of the scene are taken into account. In particular a model for implementing a hierarchical neural network architecture is proposed. Preliminary results are shown in the study of the oscillation states in the flame front of the power plant gas combustors.Source: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 13, pp. 86-89
2003
Journal article
Restricted
Automatic monitoring of states evolution in dinamic scene supervision
Di Bona S, Salvetti O
A neural network model is presented for monitoring events coded in image sequences. The image sequences define the sampling of high frequency space/time changeable phenomena where both the morphological and densitometric aspects of the scene are taken into account. In this frame, a model for implementing a multilevel neural network architecture is proposed. This model is tested in the field of power production for monitoring the combustion instability degree in power plant gas combustors. The main goal of this study is both to provide a support for preventing the oscillation states in the combustor's flame front and to characterise the instability itself. The work has been developed within a collaboration with ENEL Production and Research S.p.A. (Italian National Department for Electric Power), that supplied the study cases and the technical support for conducting the experiments. The preliminary results obtained show the effectiveness of the approach proposed.Source: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 13, pp. 495-504
Di Bona S, Salvetti O
A neural network model is presented for monitoring events coded in image sequences. The image sequences define the sampling of high frequency space/time changeable phenomena where both the morphological and densitometric aspects of the scene are taken into account. In this frame, a model for implementing a multilevel neural network architecture is proposed. This model is tested in the field of power production for monitoring the combustion instability degree in power plant gas combustors. The main goal of this study is both to provide a support for preventing the oscillation states in the combustor's flame front and to characterise the instability itself. The work has been developed within a collaboration with ENEL Production and Research S.p.A. (Italian National Department for Electric Power), that supplied the study cases and the technical support for conducting the experiments. The preliminary results obtained show the effectiveness of the approach proposed.Source: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 13, pp. 495-504
2002
Journal article
Metadata Only Access
Neural Method for three-dimensional image matching
Di Bona S, Salvetti O
This paper presents the "Volume-Matcher 3D" project, an approach for a data-driven comparison and registration of three-dimensional (3D) images. The approach is based on a neural network model derived from self-organizing maps and extended in order to match a full 3D data set of a "source volume" with the 3D data set of a "target volume." The method developed has been tested on real cases of interest in medical imaging. The results have been evaluated on the basis of both an objective mathematical function and visual analysis performed by an expert. The software was implemented on a high performance PC using AVS/Express(TM). © 2002 SPIE and IS&TSource: JOURNAL OF ELECTRONIC IMAGING, vol. 11 (issue 4), pp. 497-506
Di Bona S, Salvetti O
This paper presents the "Volume-Matcher 3D" project, an approach for a data-driven comparison and registration of three-dimensional (3D) images. The approach is based on a neural network model derived from self-organizing maps and extended in order to match a full 3D data set of a "source volume" with the 3D data set of a "target volume." The method developed has been tested on real cases of interest in medical imaging. The results have been evaluated on the basis of both an objective mathematical function and visual analysis performed by an expert. The software was implemented on a high performance PC using AVS/Express(TM). © 2002 SPIE and IS&TSource: JOURNAL OF ELECTRONIC IMAGING, vol. 11 (issue 4), pp. 497-506
See at:
CNR IRIS
2005
Journal article
Restricted
Integration of two approaches to medical image analysis for diagnostic purposes
Di Bona S, Gurevich I, Koryabkina I, Nefyodov A, Salvetti O
This paper presents the results of the research activity performed in the field of medical image analysis within a joint study between the Institute of Information Science and Technologies of the Italian National Research Council (ISTI-CNR) and the Scientific Council 'Cybernetics' of the Russian Academy of Sciences (SCC-RAS). The studies carried out concern the analysis and classification of neuro (ISTI-CNR) and hematological (SCC-RAS) images. The comparison and integration of the approaches adopted by the two research groups have been fostered as an important activity to mutually improve the significant results obtained up to now by both ISTI-CNR and SCC-RAS in the field of medical imaging.Source: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 15-2 (issue 2), pp. 539-542
Di Bona S, Gurevich I, Koryabkina I, Nefyodov A, Salvetti O
This paper presents the results of the research activity performed in the field of medical image analysis within a joint study between the Institute of Information Science and Technologies of the Italian National Research Council (ISTI-CNR) and the Scientific Council 'Cybernetics' of the Russian Academy of Sciences (SCC-RAS). The studies carried out concern the analysis and classification of neuro (ISTI-CNR) and hematological (SCC-RAS) images. The comparison and integration of the approaches adopted by the two research groups have been fostered as an important activity to mutually improve the significant results obtained up to now by both ISTI-CNR and SCC-RAS in the field of medical imaging.Source: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 15-2 (issue 2), pp. 539-542
See at:
CNR IRIS | CNR IRIS | puma.isti.cnr.it
2006
Journal article
Restricted
HEARTFAID: a knowledge based platform for supporting the clinical management of elderly patients with heart failure
Conforti D, Costanzo D, Lagani V, Perticone F, Parati G, Kaweckajaszcz K, Marsh A, Biniaris C, Stratakis M, Fontanelli R, Guerri D, Salvetti O, Tsiknakis M, Chiarugi F, Gamberger D, Valentini M
Chronic heart failure is a major health problem in many developed countries with strong social and economic effects due to its prevalence and morbidity. These effects occur particularly in the elderly who have frequent hospital admissions and utilise significant medical resources. Studies and data have demonstrated that evidence-based heart failure management programs utilising appropriate integration of inpatient and outpatient clinical services, have the potential to prevent and reduce hospital admissions, improve clinical status and reduce healthcare costs. HEARTFAID is a research and development project aimed at creating and validating an innovative knowledge-based platform to improve the early diagnosis and effective management of heart failure. The core of the platform is formalisation of pre-existing clinical knowledge and the discovery of new elicited knowledge. HEARTFAID has been designed to improve the processes of diagnosis, prognosis and therapy by providing the following services: Electronic health records for easy and ubiquitous access to heterogeneous patient data Integrated services for healthcare professionals, including patient telemonitoring, signal and image processing, alert and alarm systems Clinical decision support, based on pattern recognition in historical data, knowledge discovery analysis and inference from patients' clinical data.Source: THE JOURNAL ON INFORMATION TECHNOLOGY IN HEALTHCARE, vol. 4, pp. 283-300
Conforti D, Costanzo D, Lagani V, Perticone F, Parati G, Kaweckajaszcz K, Marsh A, Biniaris C, Stratakis M, Fontanelli R, Guerri D, Salvetti O, Tsiknakis M, Chiarugi F, Gamberger D, Valentini M
Chronic heart failure is a major health problem in many developed countries with strong social and economic effects due to its prevalence and morbidity. These effects occur particularly in the elderly who have frequent hospital admissions and utilise significant medical resources. Studies and data have demonstrated that evidence-based heart failure management programs utilising appropriate integration of inpatient and outpatient clinical services, have the potential to prevent and reduce hospital admissions, improve clinical status and reduce healthcare costs. HEARTFAID is a research and development project aimed at creating and validating an innovative knowledge-based platform to improve the early diagnosis and effective management of heart failure. The core of the platform is formalisation of pre-existing clinical knowledge and the discovery of new elicited knowledge. HEARTFAID has been designed to improve the processes of diagnosis, prognosis and therapy by providing the following services: Electronic health records for easy and ubiquitous access to heterogeneous patient data Integrated services for healthcare professionals, including patient telemonitoring, signal and image processing, alert and alarm systems Clinical decision support, based on pattern recognition in historical data, knowledge discovery analysis and inference from patients' clinical data.Source: THE JOURNAL ON INFORMATION TECHNOLOGY IN HEALTHCARE, vol. 4, pp. 283-300
2006
Journal article
Restricted
Elements of the information technology of cytological specimen analysis: taxonomy and factor analysis
Gurevich I, Harazishvili D, Salvetti O, Trykova A, Vorob'Ev I
The automated software systemSource: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 16, pp. 113-115
Gurevich I, Harazishvili D, Salvetti O, Trykova A, Vorob'Ev I
The automated software systemSource: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 16, pp. 113-115
See at:
CNR IRIS | CNR IRIS | springerlink.metapress.com
2007
Journal article
Restricted
A new measure on intuitionistic fuzzy set using Hausdorff metric and its application to edge detection
Tamalika C, Swades D, Salvetti O
Intuitionistic fuzzy set (IFS) proposed by Attanassov has gained much importance to the researchers for its application in various fields such as pattern recognition. It takes into account the membership, non-membership function also another term hesitation degree. Hesitation degree is the lack of knowledge in assigning the membership function. In particular, the similarity measure between IFSs has increased its interest and several algorithms have been developed. In this paper a new method for measuring the distance between two intuitionistic fuzzy sets based on Hausdorff metric is proposed. The distance measure is the intuitionistic fuzzy divergence using Hausdorff metric. Our proposed method has been applied in image processing in detecting the edges of different kinds of practical images, demonstrating to be a tool for processing monochrome images.
Tamalika C, Swades D, Salvetti O
Intuitionistic fuzzy set (IFS) proposed by Attanassov has gained much importance to the researchers for its application in various fields such as pattern recognition. It takes into account the membership, non-membership function also another term hesitation degree. Hesitation degree is the lack of knowledge in assigning the membership function. In particular, the similarity measure between IFSs has increased its interest and several algorithms have been developed. In this paper a new method for measuring the distance between two intuitionistic fuzzy sets based on Hausdorff metric is proposed. The distance measure is the intuitionistic fuzzy divergence using Hausdorff metric. Our proposed method has been applied in image processing in detecting the edges of different kinds of practical images, demonstrating to be a tool for processing monochrome images.
2008
Journal article
Restricted
Descriptive approach to medical image mining. An algorithmic scheme for analysis of cytological specimens
Gurevich I B, Yashina V, Koryabkina I, Niemann H, Salvetti O
The present paper is devoted the development and formal representation of a descriptive model for an information technology to automate the morphological analysis of cytologic preparations (a tumor of the lymphatic system). The theoretical basis of the model is a descriptive approach to image analysis and understanding and its main mathematical tools. Practical application of the algebraic tools of the descriptive approach is demonstrated, and the algorithmic scheme of the technology is described in the language of descriptive image algebras.Source: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 18 (issue 4), pp. 542-562
Gurevich I B, Yashina V, Koryabkina I, Niemann H, Salvetti O
The present paper is devoted the development and formal representation of a descriptive model for an information technology to automate the morphological analysis of cytologic preparations (a tumor of the lymphatic system). The theoretical basis of the model is a descriptive approach to image analysis and understanding and its main mathematical tools. Practical application of the algebraic tools of the descriptive approach is demonstrated, and the algorithmic scheme of the technology is described in the language of descriptive image algebras.Source: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 18 (issue 4), pp. 542-562
See at:
CNR IRIS | CNR IRIS | www.springerlink.com
2004
Conference article
Restricted
Integration of two approaches to medical image analysis for diagnostic purposes
Di Bona S, Gurevich I, Koryabkina I, Nefyodov A, Salvetti O
This paper presents the results of the research activity performed in the field of medical image analysis within a joint study between the Institute of Information Science and Technologies of the Italian National Research Council (ISTI-CNR) and the Scientific Council 'Cybernetics' of the Russian Academy of Sciences (SCC-RAS). The studies carried out concern the analysis and classification of neuro (ISTI-CNR) and hematological (SCC-RAS) images. The comparison and integration of the approaches adopted by the two research groups have been fostered as an important activity to mutually improve the significant results obtained up to now by both ISTI-CNR and SCC-RAS in the field of medical imaging.
Di Bona S, Gurevich I, Koryabkina I, Nefyodov A, Salvetti O
This paper presents the results of the research activity performed in the field of medical image analysis within a joint study between the Institute of Information Science and Technologies of the Italian National Research Council (ISTI-CNR) and the Scientific Council 'Cybernetics' of the Russian Academy of Sciences (SCC-RAS). The studies carried out concern the analysis and classification of neuro (ISTI-CNR) and hematological (SCC-RAS) images. The comparison and integration of the approaches adopted by the two research groups have been fostered as an important activity to mutually improve the significant results obtained up to now by both ISTI-CNR and SCC-RAS in the field of medical imaging.
2004
Conference article
Restricted
The elements of information technology for cytological specimen image analysis: taxonomy and factor analysis
Vorobjev Ia, Gurevich I, Mekhedov Is, Nefyodov A, Salvetti O, Trykova Aa, Harazishvili Dv
The investigations are described concerning design of automated systems of hematopoietic tumors diagnostics. The elements of information technology for automation of diagnostic analysis of cytological specimen, such as taxonomy and factor analysis are considered. The results of testing the stability of the used methods for the larger size of learning sample are given. The usefulness of the proposed methods for discriminating patients with different types of tumor is empirically justified.
Vorobjev Ia, Gurevich I, Mekhedov Is, Nefyodov A, Salvetti O, Trykova Aa, Harazishvili Dv
The investigations are described concerning design of automated systems of hematopoietic tumors diagnostics. The elements of information technology for automation of diagnostic analysis of cytological specimen, such as taxonomy and factor analysis are considered. The results of testing the stability of the used methods for the larger size of learning sample are given. The usefulness of the proposed methods for discriminating patients with different types of tumor is empirically justified.