Department of Computer Science
University of Cyprus


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.