SMART BEAR: A large scale pilot supporting the independent living of the seniors in a smart environment.

SMART BEAR is a multinational European research project implementing an innovative, secure and privacy-preserving platform with market available wearable and medical devices, along with smart home sensors. The solution will target the elderly population who suffer from Hearing Loss, Cardio Vascular Diseases, Cognitive Impairments, Mental Health Issues and Balance Disorders. The platform will be tested and validated in five large scale pilots, in six different countries and 5100 individuals, providing evidenced-based interventions on lifestyle, medical significant risk factors, and chronic disease management. The present work demonstrates the initial requirements collection and analysis, along with the architecture and the Decision Support System, which will provide the evidence on the recommendations to the individuals.

HOLOBALANCE: An Augmented Reality virtual trainer solution forbalance training and fall prevention.

Balance disorders affect a large number of older people, leading to falls. To promote independence, self-care and the quality of living of the long-lived population, an innovative solution is devoped to act as a virtual trainer for people that suffer from vestibular dysfunction related balance disorders. Our solution offers a virtual balance therapy, supported by Information and Communication Technology devices, to monitor user's activity during the day and provide real time feedback for the correct execution of physiotherapy exercises. Wearable sensors are utilized to monitor user activity, while during the execution of exercises, cameras are used to track the body of the user. An Augmented Reality headset is used to project the virtual trainer's 3D avatar in front of the user, providing real time guidance for the correct execution of the exercises.

Mining balance disorders' data for the development of diagnostic decision support systems.

In this work we present the methodology for the development of the EMBalance diagnostic Decision Support System (DSS) for balance disorders. Medical data from patients with balance disorders have been analysed using data mining techniques for the development of the diagnostic DSS. The proposed methodology uses various data, ranging from demographic characteristics to clinical examination, auditory and vestibular tests, in order to provide an accurate diagnosis. The system aims to provide decision support for general practitioners (GPs) and experts in the diagnosis of balance disorders as well as to provide recommendations for the appropriate information and data to be requested at each step of the diagnostic process. Detailed results are provided for the diagnosis of 12 balance disorders, both for GPs and experts. Overall, the reported accuracy ranges from 59.3 to 89.8% for GPs and from 74.3 to 92.1% for experts.

Monitoring of compliance on an individual treatment through mobile innovations.

The present work examines the potential of smartphone usage for offering health services to elderly patients. The purpose of this work is the design, development, and implementation of a telemedicine application. This application aims to improve the monitoring mode and increase patient adherence to the instructions assigned by the medical staff. It consists of three parts: the doctor's application (Web Application), the patient's application (Android Application) and the Web Server of the platform, where the database is stored necessary for the smooth operation of the platform. Also the Web Server hosts the doctor's Web Application. The Web Application is based on web front-end technologies, providing the medical personnel with a variety of features and useful actions. These actions and capabilities are mainly relevant to the assignment of instructions to patients and the monitoring of their health progress. The Android Application has been implemented and validated for the Android-based mobile devices operating system and consists of a handy and user-friendly environment, equipped with the right tools so that the patient has the ability to update the system on the progress of his/her health by storing the appropriate measurements. Both applications also provide customization capabilities in regards to the patients' and doctors' profile.

ART-ML: a new markup language for modelling and representation of biological processes in cardiovascular diseases.

BACKGROUND: With an ever increasing number of biological models available on the internet, a standardized modelling framework is required to allow information to be accessed and visualized. OBJECTIVE: In this paper we propose a novel Extensible Markup Language (XML) based format called ART-ML that aims at supporting the interoperability and the reuse of models of geometry, blood flow, plaque progression and stent modelling, exported by any cardiovascular disease modelling software. ART-ML has been developed and tested using ARTool. ARTool is a platform for the automatic processing of various image modalities of coronary and carotid arteries. METHODS: The images and their content are fused to develop morphological models of the arteries in 3D representations. All the above described procedures integrate disparate data formats, protocols and tools. ART-ML proposes a representation way, expanding ARTool, for interpretability of the individual resources, creating a standard unified model for the description of data and, consequently, a format for their exchange and representation that is machine independent. More specifically, ARTool platform incorporates efficient algorithms which are able to perform blood flow simulations and atherosclerotic plaque evolution modelling. Integration of data layers between different modules within ARTool are based upon the interchange of information included in the ART-ML model repository. ART-ML provides a markup representation that enables the representation and management of embedded models within the cardiovascular disease modelling platform, the storage and interchange of well-defined information. RESULTS: The corresponding ART-ML model incorporates all relevant information regarding geometry, blood flow, plaque progression and stent modelling procedures. All created models are stored in a model repository database which is accessible to the research community using efficient web interfaces, enabling the interoperability of any cardiovascular disease modelling software models. CONCLUSIONS: ART-ML can be used as a reference ML model in multiscale simulations of plaque formation and progression, incorporating all scales of the biological processes.

Evaluating the effect of various background correction methods regarding noise reduction, in two-channel microarray data.

In this work, two novel background correction (BC) methods, along with several commonly used ones, are evaluated regarding noise reduction in eleven two-channel self-versus-self (SVS) hybridizations. The evaluation of each BC method is investigated under the use of four statistical criteria combined into a single measure, the polygon area measure. Overall, our proposed BC approaches perform very well in terms of the proposed measure for most of the cases and provide an improved effect regarding technical noise reduction.

Elastic models: a comparative study applied to retinal images.

In this work various methods of parametric elastic models are compared, namely the classical snake, the gradient vector field snake (GVF snake) and the topology-adaptive snake (t-snake), as well as the method of self-affine mapping system as an alternative to elastic models. We also give a brief overview of the methods used. The self-affine mapping system is implemented using an adapting scheme and minimum distance as optimization criterion, which is more suitable for weak edges detection. All methods are applied to glaucomatic retinal images with the purpose of segmenting the optical disk. The methods are compared in terms of segmentation accuracy and speed, as these are derived from cross-correlation coefficients between real and algorithm extracted contours and segmentation time, respectively. As a result, the method of self-affine mapping system presents adequate segmentation time and segmentation accuracy, and significant independence from initialization.

ISWLS: novel algorithm for image reconstruction in PET.

The purpose of this study is to introduce a novel empirical iterative algorithm for medical image reconstruction, under the short name ISWLS (image space weighted least squares), which is expected to have image space reconstruction algorithm (ISRA) properties in noise manipulation and weighted least-squares (WLS) acceleration of the reconstruction process. We used phantom data from a prototype small-animal positron emission tomography system and the methods presented here are applied to 2-D sinograms. Further, we assess the performance of the new algorithm by comparing it to the simultaneous version of algebraic reconstruction technique (ART), simultaneous algebraic reconstruction technique (SART), to expectation maximization maximum likelihood (EM-ML), ISRA, and WLS. All algorithms are compared in terms of cross-correlation coefficient, reconstruction time, and contrast-to-noise ratios (CNRs). As it turns out, ISWLS presents higher CNRs than EM-ML, ISRA, and SART for objects of different sizes. Also, ISWLS shows similar performance to WLS during the first iterations but it has better noise manipulation. Finally, ordered subsets ISWLS (OS-ISWLS), the OS version of ISWLS, shows its best performance between the first six-nine iterations. Its behavior seems to be a compromise between OS-ISRA and OS-WLS.

Advanced image fusion algorithms for Gamma Knife treatment planning. Evaluation and proposal for clinical use.

Image fusion is a process of combining information from multiple sensors. It is a useful tool implemented in the treatment planning programme of Gamma Knife Radiosurgery. In this paper we evaluate advanced image fusion algorithms for Matlab platform and head images. We develop nine level grayscale image fusion methods: average, principal component analysis (PCA), discrete wavelet transform (DWT) and Laplacian, filter - subtract - decimate (FSD), contrast, gradient, morphological pyramid and a shift invariant discrete wavelet transform (SIDWT) method in Matlab platform. We test these methods qualitatively and quantitatively. The quantitative criteria we use are the Root Mean Square Error (RMSE), the Mutual Information (MI), the Standard Deviation (STD), the Entropy (H), the Difference Entropy (DH) and the Cross Entropy (CEN). The qualitative are: natural appearance, brilliance contrast, presence of complementary features and enhancement of common features. Finally we make clinically useful suggestions.

Secure and efficient health data management through multiple watermarking on medical images.

The landscape of healthcare delivery and medical data management has significantly changed over the last years, as a result of the significant advancements in information and communication technologies. Complementary and/or alternative solutions are needed to meet the new challenges, especially regarding security of the widely distributed sensitive medical information. Digital watermarking is a recently established research area with many applications; nevertheless, the potential of this technology to contribute value-added services to medical information management systems has only recently started to be realized by the research community. The paper presents a review of research efforts in the area of medical-oriented watermarking and proposes a wavelet-based multiple watermarking scheme; this scheme aims to address critical health information management issues, including origin and data authentication, protection of sensitive data, and image archiving and retrieval. In accordance with the strict limitations applying to medical images, the scheme allows the definition of a region of interest (ROI) whose diagnostic value is protected, since the only additional information embedded therein aims at integrity control. The robustness of the method is enhanced through a form of hybrid coding, which includes repetitive embedding of BCH encoded watermarks. The experimental results on different medical imaging modalities demonstrate the efficiency and transparency of the watermarking scheme.

Classification algorithms for microcalcifications in mammograms (Review).

Early detection is the key to improve breast cancer prognosis. The only proven effective method of breast cancer early detection is mammography. An early sign of 30-50% of breast cancer is the appearance of clusters of fine, granular microcalcifications and 60-80% of breast carcinomas reveal microcalcification clusters upon histological examination. The high correlation between the appearance of the microcalcification clusters and diseases, proves that computer aided diagnosis (CAD) systems for automated classification of microcalcification clusters will be very useful and helpful for breast cancer control. The fuzzy nature of microcalcification, the low contrast and the low ability of distinguishing them from their surroundings make automated characterization of them extremely difficult. In this study, we give an overview of the currently available literature on characterization of malignant and benign microcalcifications. We compare and evaluate some of the classification algorithms on microcalcifications in mammograms used in various CAD systems, which are separated into categories according to the method in use. Neural networks are used in applications where only a few decisions are required concerning an amount of data. The k-nearest neighbour classifier distinguishes unknown patterns based on the similarity to known samples and the decision tree approach is much simpler than neural networks and does not need extensive knowledge of the probability distribution of the features.

Texture-based classification of hysteroscopy images of the endometrium.

The objective of this study was to classify hysteroscopy images of the endometrium based on texture analysis for the early detection of gynaecological cancer. A total of 418 regions of interest (ROIs) were extracted (209 normal and 209 abnormal) from 40 subjects. Images were gamma corrected and were converted to gray scale. The following texture features were extracted: (i) statistical features, (ii) spatial gray level dependence matrices (SGLDM), and (iii) gray level difference statistics (GLDS). The PNN and SVM neural network classifiers were also investigated for classifying normal and abnormal ROIs. Results show that there is significant difference (using Wilcoxon rank sum test at a=0.05) between the texture features of normal and abnormal ROIs for both the gamma corrected and uncorrected images. Abnormal ROIs had lower gray scale median and homogeneity values, and higher entropy and contrast values when compared to the normal ROIs. The highest percentage of correct classifications score was 77% and was achieved for the SVM models trained with the SF and GLDS features. Concluding, texture features provide useful information differentiating between normal and abnormal ROIs of the endometrium.

An integrated computer supported acquisition, handling, and characterization system for pigmented skin lesions in dermatological images.

This paper describes an integrated prototype computer-based system for the characterization of skin digital images. The first stage includes an image acquisition arrangement designed for capturing skin images, under reproducible conditions. The system processes the captured images and performs unsupervised image segmentation and image registration utilizing an efficient algorithm based on the log-polar transform of the images' Fourier spectrum. Border- and color-based features, extracted from the digital images of skin lesions, were used to construct a classification module for the recognition of malignant melanoma versus dysplastic nevus. Different methods, drawn from the fields of artificial intelligence (neural networks) and statistical modeling (discriminant analysis), were used in order to find the best classification rules and to compare the results of different approaches to the problem.

Multiple digital watermarking applied to medical imaging.

Beyond its already established wide range of applications, digital watermarking has recently started to gain a foothold in the healthcare sector. The paper discusses the potential of multiple watermarking to address a number of health information management issues, such as protection of sensitive data, origin and data authentication, image archiving and retrieval. A wavelet-based multiple watermarking scheme focusing on these medical-oriented applications is presented; the scheme allows the physician to define a Region of Interest, whose diagnostic value is explicitly protected throughout the embedding process, since the only additional information inserted therein is for the purpose of integrity control. The rest part of the image casts multiple watermarks conveying the physician's digital signature, patient's sensitive data, and keywords allowing image retrieval. In order to increase data robustness, a form of hybrid coding is applied, which includes repetitive embedding of BCH encoded watermarks.

Energy-efficient MAC Protocol for Patient Personal Area Networks.

The formulation of a Personal Area Network (PAN), consisting of a wireless infrastructure of medical sensors, attached to patient's body, and a supervising device carried by them, lays the path for continuous and real-time monitoring of vital signs without discomforting the person in question. This infrastructure enhances the context of remote healthcare services by supporting flexible acquisition of crucial vital signs, while at the same time it provides more convenience to the patient. Aiming at the exploitation of the inherent features and requirements of wireless medical sensor networks, in this paper we focus on the main design guidelines of a low power Medium Access Control (MAC) protocol, designated to support a patient PAN. The proposed protocol intends to improve energy efficiency in such applications and thus is oriented towards the prevention of main energy wastage sources, such as collision, idle listening and power outspending.

Healthcare services towards individualised wellness (i-wellness).

Information technology applications in medicine are rapidly expanding, and new methods and solutions are evolving since they are considered pivotal in the success of preventive medicine. In this paper two different concepts will be presented, the PANACEIA-iTV and the e-Vital concept. PANACEIA-iTV is a home care service provision system based on interactive TV technology and supported by the IST programme of the European Commission. The e-Vital service, supported by the eTEN programme of the European Commission, regards an integrated homecare and telemonitoring service chain aimed at large sensitive parts of the European population, the "at-risk" citizens. Both concepts developed a generic, flexible and adaptable framework for the combination of heterogeneous information sources and the creation of the individualised wellness (i-wellness) profile for prognostic purposes and early intervention.

A Communication Platform for Tele-monitoring and Tele-management of Type 1 Diabetes.

Type 1 diabetes mellitus is a chronic disease characterized by blood glucose levels out of normal range due to inability of insulin production. This dysfunction leads to many short- and long-term complications. In this paper, a system for tele-monitoring and tele-management of Type 1 diabetes patients is proposed, aiming at reducing the risk of diabetes complications and improving quality of life. The system integrates Wireless Personal Area Networks (WPAN), mobile infrastructure, and Internet technology along with commercially available and novel glucose measurement devices, advanced modeling techniques, and tools for the intelligent processing of the available diabetes patients information. The integration of the above technologies enables intensive monitoring of blood glucose levels, treatment optimisation, continuous medical care, and improvement of quality of life for Type 1 diabetes patients, without restrictions in everyday life activities.

Integrating legacy medical data sensors in a wireless network infrastucture.

In the process of developing a wireless networking solution to provide effective field-deployable communications and telemetry support for rescuers during major natural disasters, we are faced with the task of interfacing the multitude of medical and other legacy data collection sensors to the network grid. In this paper, we detail a number of solutions, with particular attention given to the issue of data security. The chosen implementation allows for sensor control and management from remote network locations, while the sensors can wirelessly transmit their data to nearby network nodes securely, utilizing the latest commercially available cryptography solutions. Initial testing validates the design choices, while the network-enabled sensors are being integrated in the overall wireless network security framework.

The effect of color correction of endoscopy images for quantitative analysis in endometrium.

The objective of this study was to develop a standardized protocol for the capturing and analysis of endoscopy digital images for subsequent use in a Computer Aided Diagnosis (CAD) system in gynaecological cancer. Images were captured at optimum illumination and focus at 720x576 pixels using 24 bits color in the following cases: (i) for a variety of testing targets from a color palette with known color distribution, (ii) different viewing angles and distances from calf endometrium, and (iii) images from the human endometrium. Images were then gamma corrected and their classification performance was compared against that of nonqamma corrected images. No significant difference in texture features was found between the close up and panoramic views, and between angles, either before or after gamma correction. There was significant difference in certain texture features between normal and abnormal endometrium, both before and after gamma correction. Our findings suggest that proper color correction can significantly impact CAD system performance, and we recommend its application prior to quantitative texture analysis in gynaecological endoscopy.

Design of an interoperability framework in a regional healthcare system.

The integration of information systems represents one of the most urgent priorities of a regional healthcare authority in order to meet its clinical, organizational and managerial needs. Current practice shows that the most promising approach to achieve a regional healthcare information system (RHIS) is to use a health level 7 (HL7) message-based communication system implemented by an asynchronous common communication infrastructure between healthcare sites. The RHIS is a complete and integrated information system at a regional level that comprises all types of healthcare levels, that includes interoperability issues, that covers most of the needed components, and that is able to work efficiently in a secure wide area network to ensure data privacy and confidentiality. Another important feature of the proposed solution is that it creates an interoperability framework that can be replicated from one healthcare institution to another. In that sense, common interoperability messages can be used to interconnect heterogeneous information systems. In response to this strategy, more than 10 different consortiums have submitted proposals to the Greek government and the proposed interoperability' framework seems to be widely accepted as a solution to enhance information and communication technologies developments in the healthcare sector in Greece.