Department of Computer Science
University of Cyprus

The Smart, Ubiquitous, and Participatory Technologies for Healthcare Innovation Multidisciplinary Research Group is part of the RISE CoE. The MRG focuses on smart, citizen-centred eHealth and mHealth interventions, leveraging mixed reality technologies, edge computing diagnostics, and big healthcare data analytics, underpinning P4 medicine (predictive, preventive, personalised and participatory). Basic and applied research efforts are directed towards:

  • Empowering patients to become co-managers of their own health facilitating smart home interventions including mHealth and gaming applications for rehabilitation, chronic disease management, and healthy ageing, building on augmented and mixed reality personalised applications, capitalizing near real-time cloud-based EHR data, and encompassing gamification strategies, unobtrusive edge diagnostics using miniaturized system-on-chip IoT biosensors, and social robotics interactions.
  • Point-of-care diagnostics bringing specialized care to remote populations, emergency and disaster incidents, leveraging portable image and video acquisition and processing devices, along with physiological parameters sensors, equipped with advanced analytical capabilities, relying on big and deep learning technologies including machine and statistical learning and inference, computer vision, etc.
  • Smart, context-aware (big) healthcare data visualization strategies for different healthcare stakeholders in medical research, education, and care provision, as well as surgical activity and object detection for minimally invasive surgery and robotic-assisted guided interventions, medical training using interactive processes and evidence-based rendered intelligence, and smart 3D visualizations for informed diagnosis, treatment planning, and in-silico modelling.

For more information please visit RISE website.

The computational biology contributions focus on the development of optimized algorithmic approaches that utilize high performance computing (HPC) resources in order to analyze high dimensional medical data. Specifically, a system has been developed that through implementing new and utilizing existing web service accessible cloud computing HPC systems is capable of performing epistasis (interaction) testing in high dimensional genome wide association scans (GWAS). This research was performed in collaboration with one of the pharmaceutical industry leaders that enabled the use of state of the art HPC systems and also provided access to some of the largest GWAS datasets available. An analytical pipeline that performs both traditional and exploratory analytical techniques was also implemented for GWAS data. Finally a lot of work has been performed on analyzing GWAS data in combination with many other types of biomarkers, such as protein expression levels in blood to discover associations of genetic markers to biomarkers.

The chemoinformatics team focuses on specific problems found in the small molecule discovery process, primarily in drug discovery. Current research includes small molecule design (de novo design), QSAR modeling (as well as inverse-QSAR), and Virtual Screening. A new initiative focuses on the application of advanced chemoinformatics methods for the development of chemoprevention agents in close cooperation with experts in EU (Germany and Cyprus) and the US. In recent years the team has taken a leading role in the introduction of multi-objective optimization methods in chemoinformatics and has proposed such algorithms for de novo drug design among others.

A parametric pattern recognition (PPR) algorithm for the identification of similar motor unit action potentials (MUAPS) (recorded with needle electrodes) based on time-domain features that can be very easily monitored and understood by the neurophysiologist. The PPR algorithm was made commercially available through the Excel EMG model, from CADWELL Labs, USA. Furthermore, a new algorithm for the identification of similar MUAPS based on the self-organizing feature maps algorithm that gave higher recognition accuracy was developed. MUAP features were then extracted in the time-domain, frequency-domain, and time-scale domains, and a multi-feature/multi-classifier diagnostic system for the diagnosis of neuromuscular disorders was proposed based on statistical, neural network and genetics based machine learning models. More recent work focused on multi-scale (entropy based wavelet analysis and Amplitude Modulation – Frequency Modulation (AM-FM)) surface EMG (SEMG) analysis recorded from the biceps brachii muscle of subjects suffering from neuromuscular disorders. This work is carried out in collaboration with the Department of Clinical Neurophysiology of the Cyprus Institute of Neurology and Genetics (CING).

One of the first integrated eEmergency systems funded by 3 EU projects has been developed. The system allows the transmission of vital biosignals (3 or 12 lead ECG, oxygen saturation, heart rate, blood pressure, temperature, and respiration) and images or videos of the patient. The transmission was originally performed through GSM, and more recently via GPRS, or UMTS mobile networks. The system was piloted in 4 EU countries (Sweden, Italy, Greece, and Cyprus). This system has recently been updated to support the wireless transmission of diagnostic quality ultrasound medical video in emergency cases based on error resilient techniques included in H.264/AVC (MPEG4-Part 10).


An integrated modular neural network multi-feature/multi-classifier diagnostic system, including image normalization, despeckle filtering, plaque segmentation, texture and morphological feature extraction, and neural network classification has been developed for differentiating between asymptomatic and symptomatic plaques in ultrasound imaging of the carotid for the assessment of the risk of stroke. This is the only carotid plaque diagnostic system that covers all image processing steps from acquisition to diagnosis. The image normalization and texture feature extraction modules of this system are used in several cardiovascular clinics in North America, Europe, and Asia, including Columbia University, McGill University, Imperial College, Tromso University, and others. Moreover, an automated system for segmenting and computing the texture of the intima and media layer thickness of the common carotid artery as prognostic indicators for atherosclerosis versus the intima media thickness has recently been proposed. The adoption of these techniques represents a shift of emphasis from the standard practice of visual assessment of the plaque images to a normalized, re-producible, and quantitative approach based on a medical image-analysis methodology. This research work is carried out in collaboration with the Cardiovascular Disease Education and Research Trust.


This study introduces the use of classical texture analysis, and multiscale amplitude modulation–frequency modulation (AM–FM) texture analysis of multiple sclerosis (MS) using magnetic resonance (MR) images from brain. Clinically, there is interest in identifying potential associations between lesion texture and disease progression, and in relating texture features with relevant clinical indexes, such as the expanded disability status scale (EDSS). This longitudinal study explores the application of 2-D AM–FM analysis of brain white matter MS lesions to quantify and monitor disease load. To this end, MS lesions and normal-appearing white matter (NAWM)from MS patients, as well as normal white matter (NWM) from healthy volunteers, were segmented on transverse T2-weighted images obtained from serial brain MR imaging (MRI) scans (0 and 6–12 months). The instantaneous amplitude (IA), the magnitude of the instantaneous frequency (IF), and the IF angle were extracted from each segmented region at different scales. The findings suggest that AM–FM characteristics succeed in differentiating: between NWM and lesions; between NAWMand lesions; and between NWM and NAWM. A support vector machine (SVM) classifier succeeded in differentiating between patients that, two years after the initial MRI scan, acquired an EDSS ≤ 2 from those with EDSS > 2. This research work is carried out in collaboration with the Cyprus Institute of Neurology and Genetics (CING), and Medical Diagnostic Center “Ayios Therissos”.


A standardised protocol for the analysis of endoscopy images in gynaecological cancer has been proposed enabling the differentiation between normal and abnormal endometrium, cervix, and ovary tissue. Given that there is no standardised methodology for the interpretation of endoscopy images in gynaecology; our proposed standardised protocol is at presently discussed for consideration by the European Society for Gynaecological Endosopy (ESGE) and the European Academy of Gynaecological Cancer (EAGC). Recent work focuses on the hysteroscopy video analysis of the endometrium based on Amplitude Modulation – Frequency Modulation (AM-FM) models for differentiating between normal and abnormal tissue.


A computer-aided detection system for tissue cell nuclei in histological sections is introduced and validated as part of the Biopsy Analysis Support System (BASS). Cell nuclei are selectively stained with monoclonal antibodies, such as the antiestrogen receptor antibodies, which are widely applied as part of assessing patient prognosis in breast cancer. The detection system uses a receptive field filter to enhance negatively and positively stained cell nuclei and a squashing function to label each pixel value as belonging to the background or a nucleus. In this study, the detection system assessed all biopsies in an automated fashion. Detection and classification of individual nuclei as well as biopsy grading performance was shown to be promising as compared to that of two experts. One major advantage of BASS stems from the fact that the system simulates the assessment procedures routinely employed by human experts; thus it can be used as an additional independent expert. Moreover, the system allows the efficient accumulation of data from large numbers of nuclei in a short time span. Therefore, the potential for accurate quantitative assessments is increased and a platform for more standardized evaluations is provided.

In the context of the development of innovative computational intelligence based medical systems, two systems were developed. The first one, investigates the classification capacity of a new adaptive neural network architecture based on dissimilar neurons in medical data sets, whereas, the second one investigates the effectiveness of video coding based on visual attention and region of interest.