A clustering based method for collagen proportional area extraction in liver biopsy images.

Collagen Proportional Area (CPA) extraction using digital image analysis (DIA) in liver biopsies provides an effective way to estimate the liver disease staging. CPA represents accurately fibrosis expansion in liver tissue. This paper presents an automated clustering-based method for fibrosis detection and CPA computation. Initially, a k-means based approach is employed to detect the liver tissue and eliminate the background. Next, the method decides about the adequacy of current biopsy, according to the size of liver tissue. Biopsies which contain small and segmented specimens must be repeated. Since the tissue has been detected, fibrosis areas are also found in the tissue. Finally, CPA is computed. For the evaluation of the proposed method 25 images are employed and the percentage errors of CPA are computed for each image. In the majority of the cases, small variation of CPA is computed, comparing to the expert's annotation.

PERFORM: a system for monitoring, assessment and management of patients with Parkinson's disease.

In this paper, we describe the PERFORM system for the continuous remote monitoring and management of Parkinson's disease (PD) patients. The PERFORM system is an intelligent closed-loop system that seamlessly integrates a wide range of wearable sensors constantly monitoring several motor signals of the PD patients. Data acquired are pre-processed by advanced knowledge processing methods, integrated by fusion algorithms to allow health professionals to remotely monitor the overall status of the patients, adjust medication schedules and personalize treatment. The information collected by the sensors (accelerometers and gyroscopes) is processed by several classifiers. As a result, it is possible to evaluate and quantify the PD motor symptoms related to end of dose deterioration (tremor, bradykinesia, freezing of gait (FoG)) as well as those related to over-dose concentration (Levodopa-induced dyskinesia (LID)). Based on this information, together with information derived from tests performed with a virtual reality glove and information about the medication and food intake, a patient specific profile can be built. In addition, the patient specific profile with his evaluation during the last week and last month, is compared to understand whether his status is stable, improving or worsening. Based on that, the system analyses whether a medication change is needed--always under medical supervision--and in this case, information about the medication change proposal is sent to the patient. The performance of the system has been evaluated in real life conditions, the accuracy and acceptability of the system by the PD patients and healthcare professionals has been tested, and a comparison with the standard routine clinical evaluation done by the PD patients' physician has been carried out. The PERFORM system is used by the PD patients and in a simple and safe non-invasive way for long-term record of their motor status, thus offering to the clinician a precise, long-term and objective view of patient's motor status and drug/food intake. Thus, with the PERFORM system the clinician can remotely receive precise information for the PD patient's status on previous days and define the optimal therapeutical treatment.

Modeling and simulation of speed selection on left ventricular assist devices.

The control problem for LVADs is to set pump speed such that cardiac output and pressure perfusion are within acceptable physiological ranges. However, current technology of LVADs cannot provide for a closed-loop control scheme that can make adjustments based on the patient's level of activity. In this context, the SensorART Speed Selection Module (SSM) integrates various hardware and software components in order to improve the quality of the patients' treatment and the workflow of the specialists. It enables specialists to better understand the patient-device interactions, and improve their knowledge. The SensorART SSM includes two tools of the Specialist Decision Support System (SDSS); namely the Suction Detection Tool and the Speed Selection Tool. A VAD Heart Simulation Platform (VHSP) is also part of the system. The VHSP enables specialists to simulate the behavior of a patient׳s circulatory system, using different LVAD types and functional parameters. The SDSS is a web-based application that offers specialists with a plethora of tools for monitoring, designing the best therapy plan, analyzing data, extracting new knowledge and making informative decisions. In this paper, two of these tools, the Suction Detection Tool and Speed Selection Tool are presented. The former allows the analysis of the simulations sessions from the VHSP and the identification of issues related to suction phenomenon with high accuracy 93%. The latter provides the specialists with a powerful support in their attempt to effectively plan the treatment strategy. It allows them to draw conclusions about the most appropriate pump speed settings. Preliminary assessments connecting the Suction Detection Tool to the VHSP are presented in this paper.

Adverse event prediction in patients with left ventricular assist devices.

This work presents the Treatment Tool, which is a component of the Specialist's Decision Support Framework (SDSS) of the SensorART platform. The SensorART platform focuses on the management of heart failure (HF) patients, which are treated with implantable, left ventricular assist devices (LVADs). SDSS supports the specialists on various decisions regarding patients with LVADs including decisions on the best treatment strategy, suggestion of the most appropriate candidates for LVAD weaning, configuration of the pump speed settings, while also provides data analysis tools for new knowledge extraction. The Treatment Tool is a web-based component and its functionality includes the calculation of several acknowledged risk scores along with the adverse events appearance prediction for treatment assessment.

Knowledge Editor and execution engine development for optimal ventricular assist device weaning.

In this work, the weaning module of the SensorART specialist decision support system (SDSS) is presented. SensorART focuses on the treatment of patients suffering from end-stage heart failure (HF). The use of a ventricular assist device (VAD) is the main treatment for HF patients. However in certain cases, myocardial function recovers and VADs can be explanted after the patient is weaned. In that framework an efficient module is developed responsible for the selection of the most suitable candidates for VAD weaning. In this study we describe all technical specifications concerning its two main sub-modules of the weaning module, of the Clinical Knowledge Editor and the Knowledge Execution Engine.

Automated knowledge-based fuzzy models generation for weaning of patients receiving ventricular assist device (VAD) therapy.

The SensorART project focus on the management of heart failure (HF) patients which are treated with implantable ventricular assist devices (VADs). This work presents the way that crisp models are transformed into fuzzy in the weaning module, which is one of the core modules of the specialist's decision support system (DSS) in SensorART. The weaning module is a DSS that supports the medical expert on the weaning and remove VAD from the patient decision. Weaning module has been developed following a "mixture of experts" philosophy, with the experts being fuzzy knowledge-based models, automatically generated from initial crisp knowledge-based set of rules and criteria for weaning.

An intelligent Decision Support System for the treatment of patients receiving ventricular assist device (VAD) support.

The scope of this paper is to present the Specialist's Decision Support System (SDSS), part of the overall Decision Support Framework that is developed under the SensorART platform. The SensorART platform focuses on the management and remote treatment of patients suffering from end-stage heart failure. The SDSS assists specialists on designing the best treatment plan for their patients before and after VAD implantation, analyzing patients' data, extracting new knowledge, and making informative decisions. It creates a hallmark in the field, supporting medical and VAD experts through the different phases of VAD therapy.

Detection of fetal heart rate through 3-D phase space analysis from multivariate abdominal recordings.

A novel three-stage methodology for the detection of fetal heart rate (fHR) from multivariate abdominal ECG recordings is introduced. In the first stage, the maternal R-peaks and fiducial points (maternal QRS onset and offset) are detected, using band-pass filtering and phase space analysis. The maternal fiducial points are used to eliminate the maternal QRS complexes from the abdominal ECG recordings. In the second stage, two denoising procedures are applied to enhance the fetal QRS complexes. The phase space characteristics are employed to identify fetal heart beats not overlapping with the maternal QRSs, which are eliminated in the first stage. The extraction of the fHR is accomplished in the third stage, using a histogram-based technique in order to identify the location of the fetal heart beats that overlap with the maternal QRSs. The methodology is evaluated on simulated multichannel ECG signals, generated by a recently proposed model with various SNRs, and on real signals, recorded from pregnant women in various weeks during gestation. In both cases, the obtained results indicate high performance; in the simulated ECGs, the accuracy ranges from 72.78% to 98.61%, depending on the employed SNR, while in the real recordings, the average accuracy is 95.45%. The proposed methodology is advantageous since it copes with the existence of noise from various sources while it is applicable in multichannel abdominal recordings.

An automated methodology for fetal heart rate extraction from the abdominal electrocardiogram.

This paper introduces an automated methodology for the extraction of fetal heart rate from cutaneous potential abdominal electrocardiogram (abdECG) recordings. A three-stage methodology is proposed. Having the initial recording, which consists of a small number of abdECG leads in the first stage, the maternal R-peaks and fiducial points (QRS onset and offset) are detected using time-frequency (t-f) analysis and medical knowledge. Then, the maternal QRS complexes are eliminated. In the second stage, the positions of the candidate fetal R-peaks are located using complex wavelets and matching theory techniques. In the third stage, the fetal R-peaks, which overlap with the maternal QRS complexes (eliminated in the first stage) are found using two approaches: a heuristic algorithm technique and a histogram-based technique. The fetal R-peaks detected are used to calculate the fetal heart rate. The methodology is validated using a dataset of eight short and ten long-duration recordings, obtained between the 20th and the 41st week of gestation, and the obtained accuracy is 97.47%. The proposed methodology is advantageous, since it is based on the analysis of few abdominal leads in contrast to other proposed methods, which need a large number of leads.

Maternal and fetal heart rate extraction from abdominal recordings using multi-scale principal components analysis.

A three-stage methodology for the extraction of maternal and fetal heart rate using abdominal ECG leads, is presented. In the first stage, the maternal R-peaks and fiducial points (maternal QRS onset and offset) are detected, using multiscale principal components analysis (MSPCA) and the Smoothed Nonlinear Energy Operator (SNEO). Maternal fiducial points are used to eliminate the maternal QRS complexes from the abdominal ECG recordings. In the second stage, again MSPCA and SNEO are employed in order to detect the fetal heart beats that do not overlap with the maternal QRSs (eliminated from the first stage). The extraction of the fetal heart rate is accomplished in the last stage, using a histogram based technique in order to identify the positions of the fetal heart beats that overlap with the maternal QRSs. Real signals, recorded from different pregnant women and different weeks of gestation, are used for the evaluation of the proposed methodology and the obtained results indicate high performance (accuracy 95%).