A5076601989- AI in cancer detection
- Telemedicine and Telehealth Implementation
- Electronic Health Records Systems
- Medical Image Segmentation Techniques
- Cerebrovascular and Carotid Artery Diseases
- Cardiovascular Health and Disease Prevention
- Digital Radiography and Breast Imaging
- Artificial Intelligence in Healthcare and Education
- Machine Learning in Healthcare
- Colorectal Cancer Screening and Detection
- Healthcare Technology and Patient Monitoring
- Infrared Thermography in Medicine
- Mobile Health and mHealth Applications
- Sepsis Diagnosis and Treatment
- Healthcare Systems and Technology
- ECG Monitoring and Analysis
- Topic Modeling
- Digital Imaging for Blood Diseases
- Neural Networks and Applications
- Image Enhancement Techniques
- Health Literacy and Information Accessibility
- Environmental Monitoring and Data Management
- Big Data Technologies and Applications
- Ultrasound Imaging and Elastography
- Cardiac, Anesthesia and Surgical Outcomes
University of Cyprus
2009-2025
Electricity Authority of Cyprus (Cyprus)
2024
University of Patras
2024
Open University of Cyprus
2017
Chinese University of Hong Kong
2013
Applied Multilayers (United Kingdom)
2013
Academy of Athens
2007-2010
Biomedical Research Foundation of the Academy of Athens
2010
Abstract This article presents the design aspects and development processes to transform a general‐purpose mobile robotic platform into semi‐autonomous agricultural robot sprayer focusing on user interfaces for teleoperation. The hardware software modules that must be installed onto system are described, with particular emphasis human–robot interaction. Details of technology given interface aspects. Two laboratory experiments two studies in field evaluate usability provide evidence increased...
This study aims to address the critical issue of emergency department (ED) overcrowding, which negatively affects patient outcomes, wait times, and resource efficiency. Accurate prediction ED length stay (LOS) can streamline operations improve care delivery. We utilized MIMIC IV-ED dataset, comprising over 400,000 records, classify LOS into short (≤4.5 hours) long (>4.5 categories. Using machine learning models, including Gradient Boosting (GB), Random Forest (RF), Logistic Regression...
Access to health data for patients is hindered by a fragmented healthcare system and the absence of unified, patient-centric solutions. Additionally, there are no mechanics easy sharing medical records with providers, risking incomplete diagnoses. To further intensify problem, when seek care abroad, language barriers may prevent foreign doctors from understanding their data, complicating treatment. Our study presents development evaluation mobile application designed enable users access...
The paper presents the development of a computeraided diagnostic (CAD) system for early detection endometrial cancer.The proposed CAD supports reproducibility through texture feature standardization, standardized multifeature selection, and provides physicians with comparative distributions extracted features.The was validated using 516 regions interest (ROIs) from 52 subjects.The ROIs were equally distributed among normal abnormal cases.To support reproducibility, RGB images first gamma...
Endemic island species face heightened extinction risk from climate-driven shifts, yet standard models often underestimate threat levels for those like Quercus alnifolia, an iconic Cypriot oak with pre-adaptations to aridity. Through distribution modelling, we investigated the potential shifts in its under future climate and land-use change scenarios. Our approach uniquely combines dispersal constraints, detailed soil characteristics, hydrological factors, anticipated erosion data, offering...
This paper introduces a mobile framework designed to enhance citizen access and sharing of health data, aiming empower individuals with greater control over their personal information. Accessing health-related data is essential in everyday scenarios, from routine doctor visits or viewing your on own emergencies where swift can save lives. It addresses the challenges posed by fragmented nature healthcare services barriers language differences patient records. The utilizes EU eHealth Digital...
The objective of this work was to investigate a new sparse multiscale Amplitude Modulation - Frequency (AM-FM) analysis based on multiple Gabor filterbanks representations where component selection carried out using the elastic net regularization equation. AM-FM histogram features sets instantaneous amplitude, phase and magnitude frequency were computed from carotid plaque ultrasound images assess risk stroke. A total 100 (50 asymptomatic 50 symptomatic) analyzed following manual...
There is a huge need for open source software solutions in the healthcare domain, given flexibility, interoperability and resource savings characteristics they offer. In this context, paper presents development of three libraries - Specific Enablers (SEs) eHealth applications that were developed under European project titled "Future Internet Social Technological Alignment Research" (FI-STAR) funded Public Private Partnership" (FI-PPP) program. The SEs Electronic Health Record Application...
The aim of this paper is to present Cyprus' initiative for the design and implementation prototype integrated electronic health record at a national level that will establish foundations country's broader eHealth ecosystem. latter, requires an interdisciplinary approach scientific collaboration among various fields, including medicine, information communication technologies, management, finance, others. objective, system architecture, specify requirements in terms clinical content as well...
The objective of this work was the investigation multiscale Amplitude Modulation - Frequency (AM-FM) analysis based on Difference Gaussians (DoG) filterbanks representations in order to predict risk stroke by analysing carotid plaques ultrasound images individuals with asymptomatic stenosis. We computed instantaneous amplitude, phase and magnitude frequency extract histogram features each plaque region. Support Vectors Machine classifier implemented classify versus symptomatic plaques. A...
Breasts are composed of a mixture fibrous and glandular tissue as well adipose breast density describes the prevalence fibroglandular it appears on mammogram. Over past few years, evaluation reporting mammograms has received lot attention because impacts one's risk developing cancer but also capability detecting mammograms. In addition, mammography fails in identification almost half women with dense breasts. Different image analysis methods have been investigated for automatic...
In this study we present an integrated system for supporting the diagnosis of endometrial cancer. The consists electronic patient record that incoporates a hysteroscopy imaging CAD early detection is based on information collected from: appointments, info, reporting and pharmacy. ROI manual or semi-automated extraction, texture feature computation SVM C4.5 classification into normal/abnormal. highest percentage correct classifications score (%CC) classifier was 79% YCrCb color using SF+SGLDS...
The Electrocardiogram (ECG) is one of the most well studied medical signals. A large number ECG processing algorithms have being proposed over years covering areas noise filtering, automated diagnostic interpretation and coding. In this work, we propose a robust multi-channel encoder architecture, which operates on 12-channel data. utilizes highly efficient multi-linear patient specific models for inter-channel prediction MPEG-4 Audio Lossless Coding (ALS) architecture intra-channel results...
Quantitative color tissue analysis in endoscopy examinations requires standardization procedures to be applied, so as enable compatibility among computer aided diagnosis application from different labs. The objective of this study was examine the usefulness correction algorithms (thus facilitating standardization), evaluated on four cameras. following five were investigated: two gamma based (the classical and a modified one), three (2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML"...
This paper describes a proposal for national implementation creating platform exchanging health data within Cyprus and between other countries. The is based on combining both the International Patient Summary guidelines, as well European guidelines meeting requirements of using minimum dataset that needs to be communicated different systems countries, together with respective value sets rules. latter consists which was defined by eHealth Network most important relevant information needed...
The paper proposes the use of elastic net regression for reconstructing images from AM-FM components. Current reconstruction methods are based on Dominant Component Analysis (DCA), multi-scale DCA, and Channel (CCA). introduce a variation CCA that uses to minimize number channels used in reconstruction. new approach is validated using family Gabor filterbanks parameterized by an overlap index. results show component selection algorithm performs significantly better than multiscale DCA.
This paper presents a comprehensive mobile eHealth application that integrates teleconsultation functionality to deliver high-quality healthcare and telemedicine services. Patients can have virtual consultations with professionals from the convenience of their own homes providing real time The supports patient medical history, schedule teleconsultations module based on doctors' plan availability, but also secure environment exchange data such as, laboratory reports, imaging results. platform...
Artificial Intelligence (AI) advances in healthcare underpin timely and informed interventions that can elevate the quality of care for benefit citizen. This be especially beneficial Intensive Care Unit (ICU) patients. The goal this study is to develop an interoperable electronic health record (EHR) system, integrating reproducible AI-based algorithms ICU services, linked with medical data status visualizations, will allow professionals proceed more diagnosis targeted, personalized...
The use of multiscale AM-FM analysis systems has been recently demonstrated in a variety applications medical image analysis. In all these applications, fixed filter-bank is used as preprocessing step for estimating different components from scales. this paper, the first time, we introduce an adaptive, approach that searches optimal specification classification. We demonstrate example application hysteroscopy imaging, identification gynaecological cancer, where turns out to be circularly symmetric.