A5087972272- Medical Image Segmentation Techniques
- EEG and Brain-Computer Interfaces
- Functional Brain Connectivity Studies
- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Medical Imaging Techniques and Applications
- Advanced Radiotherapy Techniques
- Neural and Behavioral Psychology Studies
- Dental Radiography and Imaging
- Neural dynamics and brain function
- Image and Signal Denoising Methods
- Medical Imaging and Analysis
- Advanced MRI Techniques and Applications
- Image Retrieval and Classification Techniques
- Advanced Neuroimaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Retinal Imaging and Analysis
- Robotics and Sensor-Based Localization
- Advanced Image Fusion Techniques
- Computer Graphics and Visualization Techniques
- Advanced Image and Video Retrieval Techniques
- Neural Networks and Applications
- Brain Tumor Detection and Classification
- Sleep and Work-Related Fatigue
- Image and Object Detection Techniques
National Technical University of Athens
2016-2025
Institute of Communication and Computer Systems
2003-2025
National and Kapodistrian University of Athens
2003-2013
Academy of Athens
2013
Biomedical Research Foundation of the Academy of Athens
2013
University of Strathclyde
1992-2005
Eginition Hospital
2003
Weatherford College
2001
In this paper, a computer-aided diagnostic (CAD) system for the classification of hepatic lesions from computed tomography (CT) images is presented. Regions interest (ROIs) taken nonenhanced CT normal liver, cysts, hemangiomas, and hepatocellular carcinomas have been used as input to system. The proposed consists two modules: feature extraction modules. module calculates average gray level 48 texture characteristics, which are derived spatial gray-level co-occurrence matrices, obtained ROIs....
Retinal image registration is commonly required in order to combine the complementary information different retinal modalities. In this paper, a new automatic scheme register images presented and currently tested clinical environment. The considers suitability efficiency of transformation models function optimization techniques, following an initial preprocessing stage. Three models--affine, bilinear projective--as well as three techniques--downhill simplex method, simulated annealing...
Despite the apparent usefulness of efficient mental workload assessment in various real-world situations, underlying neural mechanism remains largely unknown, and studies are limited to well-controlled cognitive tasks using a 2D computer screen. In this paper, we investigated functional brain network alterations simulated flight experiment with three levels compared reorganization pattern between screen (2D) virtual reality (3D) interfaces. We constructed multiband networks...
Background/Objectives: Spasticity commonly occurs in individuals after experiencing a stroke, impairing their hand function and limiting activities of daily living (ADLs). In this paper, we introduce an exoskeletal aid, combined with set augmented reality (AR) games consisting the Rehabotics rehabilitation solution, designed for upper limb spasticity following stroke. Methods: Our study, involving 60 post-stroke patients (mean ± SD age: 70.97 4.89 years), demonstrates significant...
Abstract Introduction Recent studies related to assessing functional connectivity (FC) in resting‐state magnetic resonance imaging have revealed that the resulting patterns exhibit considerable fluctuations (dynamic FC [dFC]). A widely applied method for quantifying dFC is sliding window technique. According this method, data are divided into segments with same length (window size) and a correlation metric employed assess within these segments, whereby size often empirically chosen. Methods...
In the nascent field of neuroergonomics, mental workload assessment is one most important issues and has an apparent significance in real-world applications. Although prior research achieved efficient single-task classification, scatted studies on cross-task usually result unsatisfactory performance. Here, we introduce a data-driven analysis framework to overcome challenges regarding task-independent using fusion EEG spectral characteristics unveil common neural mechanisms underlying...
Background: Osteosarcoma is the most common primary malignancy of bone, being prevalent in childhood and adolescence. Despite recent progress diagnostic methods, histopathology remains gold standard for disease staging therapy decisions. Machine learning deep methods have shown potential evaluating classifying histopathological cross-sections. Methods: This study used publicly available images osteosarcoma cross-sections to analyze compare performance state-of-the-art neural networks...
A combined computational and experimental study of 3D-printed scaffolds made from hybrid nanocomposite materials for potential applications in bone tissue engineering is presented. Polycaprolactone (PCL) polylactic acid (PLA), enhanced with chitosan (CS) multiwalled carbon nanotubes (MWCNTs), were investigated respect their mechanical characteristics responses fluidic environments. novel scaffold geometry was designed, considering the requirements cellular proliferation properties. Specimens...
A hierarchical image fusion scheme is presented which preserves the details of input images regardless their scale. The technique demonstrated by fusing human brain derived from magnetic resonance (MR) and computed tomography (CT) scanners. Results are given to show that fused preserve a more complete representation anatomical pathological structures, providing information cannot be obtained processing at single
Mental workload has a major effect on the individual’s performance in most real-world tasks, which can lead to significant errors critical operations. On this premise, analysis and assessment of mental attain high research interest both fields Neuroergonomics Neuroscience. In work, we implemented an EEG experimental design consisting two distinct tasks (mental arithmetic task, n-back task), each with conditions complexity (low high) investigate task-related task-unrelated effects. Since is...
The detection of mental fatigue is an important issue in the nascent field neuroergonomics. Although machine learning approaches and especially deep designs have constantly demonstrated their efficiency to automatically detect critical features from raw data, computational resources for training predictions are usually very demanding. In this work, we propose a shallow convolutional neural network, with three layers, using electroencephalogram (EEG) data that can alleviate burden provide...
Tinnitus is a highly prevalent condition, affecting more than 1 in 7 adults the EU and causing negative effects on sufferers' quality of life. In this study, we utilised data collected within "UNITI" project, largest tinnitus-related research programme. Initially, extracted characteristics from both auditory brainstem response (ABR) middle latency (AMLR) signals, which were derived tinnitus patients. We then combined these features with patients' clinical data, integrated them to build...
This work introduces EffiSegNet, a novel segmentation framework leveraging transfer learning with pre-trained Convolutional Neural Network (CNN) classifier as its backbone. Deviating from traditional architectures symmetric U-shape, EffiSegNet simplifies the decoder and utilizes full-scale feature fusion to minimize computational cost number of parameters. We evaluated our model on gastrointestinal polyp task using publicly available Kvasir-SEG dataset, achieving state-of-the-art results....
The prediction of schizophrenia-related psychopathologic deficits is exceedingly important in the fields psychiatry and clinical practice. However, objective association brain structure alterations to illness symptoms challenging. Although, schizophrenia has been characterized as a dysconnectivity syndrome, evidence accounting for neuroanatomical network remain scarce. Moreover, absence generalized connectome biomarkers assessment progression further perplexes long-term symptom severity. In...
The delineation of parotid glands in head and neck (HN) carcinoma is critical to assess radiotherapy (RT) planning. Segmentation processes ensure precise target position treatment precision, facilitate monitoring anatomical changes, enable plan adaptation, enhance overall patient safety. In this context, artificial intelligence (AI) deep learning (DL) have proven exceedingly effective precisely outlining tumor tissues and, by extension, the organs at risk. This paper introduces a DL...
Abdominal aortic aneurysm (AAA) is a complex vascular condition associated with high mortality rates. Accurate abdominal aorta segmentation essential in medical imaging, facilitating diagnosis and treatment for range of cardiovascular diseases. In this regard, deep learning-based automated has shown significant promise the precise delineation aorta. However, comparisons across different models remain limited, most studies performing algorithmic training testing on same dataset. Furthermore,...
Background: This study investigates electrophysiological distinctions in auditory evoked potentials (AEPs) among individuals with chronic subjective tinnitus, a specific focus on the impact of treatment response and tinnitus localisation. Methods: Early AEPs, known as Auditory Brainstem Responses (ABR), middle termed Middle Latency (AMLR), were analysed patients across four clinical centers an attempt to verify increased neuronal activity, accordance current models. Our statistical analyses...