Management and modeling of balance disorders using decision support systems: the EMBALANCE project.

In this work, we present the concept, the methodological ideas and the architecture of the EMBALANCE platform. EMBALANCE platform extends existing but generic and currently uncoupled balance modeling activities, leading to a multi-scale and patient-specific balance Hypermodel, which is incorporated to a Decision Support System (DSS), towards the early diagnosis, prediction and the efficient treatment planning of balance disorders. Various data feed the intelligent system increasing the dimensionality and personalization of the system. Human Computer Interaction techniques are utilized in order to develop the required interfaces in a user-intuitive and efficient way, while interoperable web services enhance the accessibility and acceptance of the system. The platform will be validated using both retrospective as well as prospective experimental and clinical data. The final tool will be a powerful web-based platform provided to primary and secondary care physicians across specialties, levels of training and geographical boundaries, targeting wider clinical acceptance as well as the increased confidence in the developed DSS towards the early diagnostic evaluation, behaviour prediction and effective management planning of balance problems. Currently we focus and present the management and modeling of the balance disorders.

EDIT Software: A tool for the semi-automatic 3D reconstruction of bladder cancer and urinary bladder of animal models.

BACKGROUND AND OBJECTIVE: This study presents the EDIT software, a tool for the visualization of the urinary bladder anatomy in the 3D space and for its semi-automatic 3D reconstruction. METHODS: The inner bladder wall was computed by applying a Region of Interest (ROI) feedback-based active contour algorithm on the ultrasound images while the outer bladder wall was calculated by expanding the inner borders to approach the vascularization area on the photoacoustic images. The validation strategy of the proposed software was divided into two processes. Initially, the 3D automated reconstruction was performed on 6 phantom objects of different volume in order to compare the software computed volumes of the models with the true volumes of phantoms. Secondly, the in-vivo 3D reconstruction of the urinary bladder for 10 animals with orthotopic bladder cancer, which range in different stages of tumor progression was performed. RESULTS: The results showed that the minimum volume similarity of the proposed 3D reconstruction method applied on phantoms is 95.59%. It is noteworthy to mention that the EDIT software enables the user to reconstruct the 3D bladder wall with high precision, even if the bladder silhouette has been significantly deformed by the tumor. Indeed, by taking into account the dataset of the 2251 in-vivo ultrasound and photoacoustic images, the presented software performs segmentation with dice similarity 96.96% and 90.91% for the inner and the outer borders of the bladder wall, respectively. CONCLUSIONS: This study delivers the EDIT software, a novel software tool that uses ultrasound and photoacoustic images to extract different 3D components of the bladder.

Effect of modeling parameters on the frequency response of the middle ear by means of finite element analysis.

A 3D finite element model of the human middle ear was developed for the investigation of the modeling parameters' effect on the frequency response. In this study, we incorporated realistic reconstructed geometries from microCT imaging data. The geometric representation of the stapedial annular ligament provided additional damping and the Rayleigh parameter ß was adjusted to lower values in comparison to previous computational studies. The maximum displacement of the stapes footplate, equal to 0.168 µm, was observed at a frequency of 1050 Hz. The computational results were validated with experimental measurements. Good agreement is observed between our results and the experimental data and other finite element studies.

Identification of COPD patients' health status using an intelligent system in the CHRONIOUS wearable platform.

The CHRONIOUS system offers an integrated platform aiming at the effective management and real-time assessment of the health status of the patient suffering from chronic obstructive pulmonary disease (COPD). An intelligent system is developed for the analysis and the real-time evaluation of patient's condition. A hybrid classifier has been implemented on a personal digital assistant, combining a support vector machine, a random forest, and a rule-based system to provide a more advanced categorization scheme for the early and in real-time characterization of a COPD episode. This is followed by a severity estimation algorithm which classifies the identified pathological situation in different levels and triggers an alerting mechanism to provide an informative and instructive message/advice to the patient and the clinical supervisor. The system has been validated using data collected from 30 patients that have been annotated by experts indicating 1) the severity level of the current patient's health status, and 2) the COPD disease level of the recruited patients according to the GOLD guidelines. The achieved characterization accuracy has been found 94%.

Reconstruction of cochlea based on micro-CT and histological images of the human inner ear.

The study of the normal function and pathology of the inner ear has unique difficulties as it is inaccessible during life and, so, conventional techniques of pathologic studies such as biopsy and surgical excision are not feasible, without further impairing function. Mathematical modelling is therefore particularly attractive as a tool in researching the cochlea and its pathology. The first step towards efficient mathematical modelling is the reconstruction of an accurate three dimensional (3D) model of the cochlea that will be presented in this paper. The high quality of the histological images is being exploited in order to extract several sections of the cochlea that are not visible on the micro-CT (mCT) images (i.e., scala media, spiral ligament, and organ of Corti) as well as other important sections (i.e., basilar membrane, Reissner membrane, scala vestibule, and scala tympani). The reconstructed model is being projected in the centerline of the coiled cochlea, extracted from mCT images, and represented in the 3D space. The reconstruction activities are part of the SIFEM project, which will result in the delivery of an infrastructure, semantically interlinking various tools and libraries (i.e., segmentation, reconstruction, and visualization tools) with the clinical knowledge, which is represented by existing data, towards the delivery of a robust multiscale model of the inner ear.

Clinical validation of the CHRONIOUS wearable system in patients with chronic disease.

The CHRONIOUS system defines a powerful and easy to use framework which has been designed to provide services to clinicians and their patients suffering from chronic diseases. The system is composed of a wearable shirt that integrate several body sensors, a portable smart device and a central sub-system that is responsible for the long term storage of the collected patient's data. A multi-parametric expert system is developed for the analysis of the collected data using intelligent algorithms and complex techniques. Apart for the vital signals, dietary habits, drug intake, activity data, environmental and biochemical parameters are recorded. The CHRONIOUS platform is validated through clinical trials in several medical centers and patient's home environments recruiting patients suffering from Chronic Obstructive pulmonary disease (COPD) and Chronic Kidney Disease (CKD) diseases. The clinical trials contribute in improving the system's accuracy, while Pulmonologists and Nephrologists experts utilized the CHRONIOUS platform to evaluate its efficiency and performance. The results of the utilization of the system were very encouraging. The CHRONIOUS system has been proven to be a well-validated real-time patient monitoring and supervision platform, providing a useful tool for the clinician and the patient that would contribute to the more effective management of chronic diseases.

Computational assessment of the fractional flow reserve from intravascular ultrasound and coronary angiography data: a pilot study.

Cardiovascular disease is one of the primary causes of morbidity and mortality around the globe. Thus, the diagnosis of critical lesions in coronary arteries is of utmost importance in clinical practice. One useful and efficient method to assess the functional severity of one or multiple lesions in a coronary artery is the calculation of the fractional flow reserve (FFR). In the current work, we present a method which allows the calculation of the FFR value computationally, without the use of a pressure wire and the induction of hyperemia, using intravascular ultrasound (IVUS) and biplane angiography images for three-dimensional (3D) coronary artery reconstruction and measurements of the volumetric flow rate derived from angiographic sequences. The simulated FFR values were compared to the invasively measured FFR values in 7 cases, presenting high correlation (r=0.85) and good agreement (mean difference=0.002). FFR assessment without employing a pressure wire and the induction of hyperemia is feasible using 3D reconstructed coronary artery models from angiographic and IVUS data coupled with computational fluid dynamics.

Categorization of COPD patient's health level through the use of the CHRONIOUS wearable platform.

The Chronic Obstructive Pulmonary Disease (COPD) is a chronic disease that causes airflow blockage and breathing-related problems. As a Chronic disease it requires specific treatment plan and patient management for a long period of time. Critical factor in the process is the realization of frequent and precise diagnostic tests that describes the health status of the patient. The CHRONIOUS system provides the required easy-to-use wearable platform aiming at the successful management of COPD patients. Several signals and patient's data are stored by the utilization of an ergonomic jacket and through the patient's platform interface. Hybrid techniques based on supervised and unsupervised methodologies were applied for the analysis of the patient's situation. The categorization of health level of the patient to discrete levels is achieved in a continuous base. Useful outcomes in the form of message or advice are extracted appeared on patient's and clinician's devices denoting his health status.

Heterogeneous data fusion and intelligent techniques embedded in a mobile application for real-time chronic disease management.

CHRONIOUS system is an integrated platform aiming at the management of chronic disease patients. One of the most important components of the system is a Decision Support System (DSS) that has been developed in a Smart Device (SD). This component decides on patient's current health status by combining several data, which are acquired either by wearable sensors or manually inputted by the patient or retrieved from the specific database. In case no abnormal situation has been tracked, the DSS takes no action and remains deactivated until next abnormal situation pack of data are being acquired or next scheduled data being transmitted. The DSS that has been implemented is an integrated classification system with two parallel classifiers, combining an expert system (rule-based system) and a supervised classifier, such as Support Vector Machines (SVM), Random Forests, artificial Neural Networks (aNN like the Multi-Layer Perceptron), Decision Trees and Naïve Bayes. The above categorized system is useful for providing critical information about the health status of the patient.

CHRONIOUS: a wearable platform for monitoring and management of patients with chronic disease.

The CHRONIOUS system has been developed based on an open architecture design that consists of a set of subsystems which interact in order to provide all the needed services to the chronic disease patients. An advanced multi-parametric expert system is being implemented that fuses information effectively from various sources using intelligent techniques. Data are collected by sensors of a body network controlling vital signals while additional tools record dietary habits and plans, drug intake, environmental and biochemical parameters and activity data. The CHRONIOUS platform provides guidelines and standards for the future generations of "chronic disease management systems" and facilitates sophisticated monitoring tools. In addition, an ontological information retrieval system is being delivered satisfying the necessities for up-to-date clinical information of Chronic Obstructive pulmonary disease (COPD) and Chronic Kidney Disease (CKD). Moreover, support tools are being embedded in the system, such as the Mental Tools for the monitoring of patient mental health status. The integrated platform provides real-time patient monitoring and supervision, both indoors and outdoors and represents a generic platform for the management of various chronic diseases.

An intelligent system for classification of patients suffering from chronic diseases.

The CHRONIOUS system addresses a smart wearable platform, based on multi-parametric sensor data processing, for monitoring people suffering from chronic diseases in long-stay setting. Several signals are being recorded through wearable sensors and are stored together with additional information, entered by the patient. An Intelligent System, placed at a Smart Assistant Device, analyzes incoming data and facilitates data mining techniques resulting upon the severity of a health episode. Part of the Intelligent System is the Mental Support Tool, which calculates a Stress Index and classifies the mental condition and stress levels of the patient. An additional component aiming at the personalization of the Intelligent System's Decision is the Profiler which defines several patients profiles and facilitates clustering techniques in order to associate each patient's description with one of the predefined profiles.