Eleftherios Kontopodis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Eleftherios Kontopodis has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Ioannis Kakkos
Biomedical Engineering Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, 15773 Athens, Greece
4 shared publications Efrosini Papadaki
Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology‑Hellas, 70013 Heraklion, Greece
3 shared publications- George K. Matsopoulos
Biomedical Engineering Laboratory, Institute of Communication and Computer Systems of the National Technical University of Athens, 15773 Athens, Greece
3 shared publications Georgios Z. Papadakis
Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology‑Hellas, 70013 Heraklion, Greece
3 shared publications- Ioannis Vezakis
Biomedical Engineering Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, 15773 Athens, Greece
3 shared publications - Errikos-Chaim Ventouras
Department of Biomedical Engineering, University of West Attica, 12243 Athens, Greece
2 shared publications
Latest Publications
- Open Access
- 29 April 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (9) , 4345
Geometric Radiomic Analysis of Hip Joint Space for Automatic Detection of Developmental Dysplasia of the Hip in Infants
Developmental dysplasia of the hip (DDH) is a common musculoskeletal disorder in infancy, and early detection is essential for optimal clinical outcomes. Radiographic assessment is traditionally based on angular measurements, which may be limited by variability in landmark identification and do not fully capture the complex morphology of the hip joint. In this study, we investigate whether geometric features derived from the hip joint articulation space can be used to differentiate between normal and dysplastic hips in infant radiographs. Pelvic X-ray images from infants (mean age 4.5 ± 0.83 months) were analyzed, and custom segmentation masks were developed to isolate the joint space region. A total of 99 geometric and radiomic features were extracted and evaluated using statistical analysis and supervised machine learning methods. Multiple features demonstrated strong discriminative power between normal and DDH (p < 0.001), with shape and spatial distribution characteristics showing the highest relevance. Classification models achieved an F1-score of approximately 80% on the full dataset. Notably, patient age was identified as a significant confounding factor, and analysis on an age-matched subset improved classification performance to 94% accuracy and 93% recall. These findings suggest that geometric characterization of the hip joint space provides a promising and interpretable framework for DDH detection. The results also highlight the importance of age-stratified analysis in pediatric imaging. Further validation on larger and more diverse datasets is required to assess clinical applicability.
- 29 April 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (9) , 4345
Open AccessGeometric Radiomic Analysis of Hip Joint Space for Automatic Detection of Developmental Dysplasia of the Hip in Infants
Developmental dysplasia of the hip (DDH) is a common musculoskeletal disorder in infancy, and early detection is essential for optimal clinical outcomes. Radiographic assessment is traditionally based on angular measurements, which may be limited by variability in landmark identification and do not fully capture the complex morphology of the hip joint. In this study, we investigate whether geometric features derived from the hip joint articulation space can be used to differentiate between normal and dysplastic hips in infant radiographs. Pelvic X-ray images from infants (mean age 4.5 ± 0.83 months) were analyzed, and custom segmentation masks were developed to isolate the joint space region. A total of 99 geometric and radiomic features were extracted and evaluated using statistical analysis and supervised machine learning methods. Multiple features demonstrated strong discriminative power between normal and DDH (p < 0.001), with shape and spatial distribution characteristics showing the highest relevance. Classification models achieved an F1-score of approximately 80% on the full dataset. Notably, patient age was identified as a significant confounding factor, and analysis on an age-matched subset improved classification performance to 94% accuracy and 93% recall. These findings suggest that geometric characterization of the hip joint space provides a promising and interpretable framework for DDH detection. The results also highlight the importance of age-stratified analysis in pediatric imaging. Further validation on larger and more diverse datasets is required to assess clinical applicability.
- Open Access
- 1 April 2026
- Published by National Documentation Centre (EKT) in Technical Annals
- Vol. 2 (4)
Evaluating Multimodal EEG Features for Motor Imagery Classification Using MLP Models
Motor imagery (MI) electroencephalography (EEG) provides a non-invasive approach for decoding movement-related neural activity and supporting brain–computer interface applications. This study evaluated the discriminative contribution of multiple EEG feature types for classifying lower-limb MI and non-MI conditions. As such, EEG data were recorded during a visually guided MI paradigm and different feature types (including event related potentials, power spectral density, correlation-based brain network, and energy-based features) were extracted and combined into a unified feature space. Four feature subsets containing the top 120, 180, 240, and 300 features were evaluated using a multilayer perceptron (MLP) classifier within a Leave-One-Subject-Out cross-validation framework. The best performance was achieved with 240 selected features, yielding an accuracy of 0.79 and an F1-score of 0.782. This optimal subset was dominated by ERP features, followed by correlation-based features, while PSD and energy features contributed marginally. These findings suggest that combining multiple EEG feature types can improve the characterization of MI-related neural activity, but their contributions are not equivalent, thus requiring systematic feature selection for the development of more reliable EEG-based MI classification models.
- 1 April 2026
- Published by National Documentation Centre (EKT) in Technical Annals
- Vol. 2 (4)
Open AccessEvaluating Multimodal EEG Features for Motor Imagery Classification Using MLP Models
Motor imagery (MI) electroencephalography (EEG) provides a non-invasive approach for decoding movement-related neural activity and supporting brain–computer interface applications. This study evaluated the discriminative contribution of multiple EEG feature types for classifying lower-limb MI and non-MI conditions. As such, EEG data were recorded during a visually guided MI paradigm and different feature types (including event related potentials, power spectral density, correlation-based brain network, and energy-based features) were extracted and combined into a unified feature space. Four feature subsets containing the top 120, 180, 240, and 300 features were evaluated using a multilayer perceptron (MLP) classifier within a Leave-One-Subject-Out cross-validation framework. The best performance was achieved with 240 selected features, yielding an accuracy of 0.79 and an F1-score of 0.782. This optimal subset was dominated by ERP features, followed by correlation-based features, while PSD and energy features contributed marginally. These findings suggest that combining multiple EEG feature types can improve the characterization of MI-related neural activity, but their contributions are not equivalent, thus requiring systematic feature selection for the development of more reliable EEG-based MI classification models.
- Open Access
- 24 November 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (23) , 12458
DTI-Based Structural Connectome Analysis of SCLC Patients After Chemotherapy via Machine Learning
Small-cell lung cancer (SCLC) is an aggressive malignancy that exhibits high prevalence for brain metastases. Furthermore, chemotherapy and metastasis-preventive approaches are also linked to neurotoxicity, further aggravating cognitive impairment. Despite evidence supporting structural and functional brain alterations in SCLC, the application of machine learning (ML) to new connectivity biomarkers has remained unexplored. This study is—to the best of our knowledge—the first to apply ML to structural brain connectomics in SCLC, using diffusion tensor imaging (DTI) to identify features discriminating between post-chemotherapy SCLC patients and healthy controls. Specifically, we constructed structural networks via deterministic tractography, applying an adapted feature reduction technique to identify the most informative connections without selection bias. This process isolated 16 connections involving 26 brain regions, predominantly in the frontal, temporal, and parietal lobes, showcasing primarily intra-hemispheric and left-lateralized alterations. Our optimal model leveraged a Gaussian Support Vector Machine (SVM), achieving a weighted accuracy of 0.92, a sensitivity of 0.93, a specificity of 0.91, and an area under the curve of 0.94. The selected feature subset retained high performance when tested with other classifiers, confirming its robustness. Our findings differ from prior studies based on statistically derived features, highlighting the ML-driven connectomics’ potential in uncovering DTI-derived SCLC patterns, offering interpretable insights for neuroimaging-based diagnostics.
- 24 November 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (23) , 12458
Open AccessDTI-Based Structural Connectome Analysis of SCLC Patients After Chemotherapy via Machine Learning
Small-cell lung cancer (SCLC) is an aggressive malignancy that exhibits high prevalence for brain metastases. Furthermore, chemotherapy and metastasis-preventive approaches are also linked to neurotoxicity, further aggravating cognitive impairment. Despite evidence supporting structural and functional brain alterations in SCLC, the application of machine learning (ML) to new connectivity biomarkers has remained unexplored. This study is—to the best of our knowledge—the first to apply ML to structural brain connectomics in SCLC, using diffusion tensor imaging (DTI) to identify features discriminating between post-chemotherapy SCLC patients and healthy controls. Specifically, we constructed structural networks via deterministic tractography, applying an adapted feature reduction technique to identify the most informative connections without selection bias. This process isolated 16 connections involving 26 brain regions, predominantly in the frontal, temporal, and parietal lobes, showcasing primarily intra-hemispheric and left-lateralized alterations. Our optimal model leveraged a Gaussian Support Vector Machine (SVM), achieving a weighted accuracy of 0.92, a sensitivity of 0.93, a specificity of 0.91, and an area under the curve of 0.94. The selected feature subset retained high performance when tested with other classifiers, confirming its robustness. Our findings differ from prior studies based on statistically derived features, highlighting the ML-driven connectomics’ potential in uncovering DTI-derived SCLC patterns, offering interpretable insights for neuroimaging-based diagnostics.
- Open Access
EEG-Based Assessment of Cognitive Resilience via Interpretable Machine Learning Models
Background: Cognitive resilience is a critical factor in high-performance environments such as military operations, where sustained stress can impair attention and decision-making. In the present study, we utilized EEG and machine learning to assess cognitive resilience in elite military personnel. Methods: For this purpose, EEG signals were recorded from elite military personnel during stress-inducing attention-related and emotional tasks. The EEG signals were segmented into two temporal windows corresponding to the initial stress response (baseline) and the adaptive/recovery phase, extracting power spectral density features across delta, theta, alpha, beta, and gamma bands. Different machine learning models (Decision Tree, Random Forest, AdaBoost, XGBoost) were trained to classify temporal phases. Results: XGBoost achieved the highest accuracy (0.95), while Shapley Additive Explanations (SHAP) analysis identified delta and alpha bands (particularly in frontal and parietal regions) as key features associated with adaptive mental states. Conclusions: Our findings indicate that resilience-related neural responses can be successfully distinguished and that interpretable AI frameworks can be used for monitoring cognitive adaptation in high-stress environments.
Open AccessEEG-Based Assessment of Cognitive Resilience via Interpretable Machine Learning Models
Background: Cognitive resilience is a critical factor in high-performance environments such as military operations, where sustained stress can impair attention and decision-making. In the present study, we utilized EEG and machine learning to assess cognitive resilience in elite military personnel. Methods: For this purpose, EEG signals were recorded from elite military personnel during stress-inducing attention-related and emotional tasks. The EEG signals were segmented into two temporal windows corresponding to the initial stress response (baseline) and the adaptive/recovery phase, extracting power spectral density features across delta, theta, alpha, beta, and gamma bands. Different machine learning models (Decision Tree, Random Forest, AdaBoost, XGBoost) were trained to classify temporal phases. Results: XGBoost achieved the highest accuracy (0.95), while Shapley Additive Explanations (SHAP) analysis identified delta and alpha bands (particularly in frontal and parietal regions) as key features associated with adaptive mental states. Conclusions: Our findings indicate that resilience-related neural responses can be successfully distinguished and that interpretable AI frameworks can be used for monitoring cognitive adaptation in high-stress environments.
- Open Access
- 9 August 2021
- Published by Spandidos Publications in Experimental and Therapeutic Medicine
- Vol. 22 (4) , 1-17
Emerging deep learning techniques using magnetic resonance imaging data applied in multiple sclerosis and clinical isolated syndrome patients (Review)
Computer‑aided diagnosis systems aim to assist clinicians in the early identification of abnormal signs in order to optimize the interpretation of medical images and increase diagnostic precision. Multiple sclerosis (MS) and clinically isolated syndrome (CIS) are chronic inflammatory, demyelinating diseases affecting the central nervous system. Recent advances in deep learning (DL) techniques have led to novel computational paradigms in MS and CIS imaging designed for automatic segmentation and detection of areas of interest and automatic classification of anatomic structures, as well as optimization of neuroimaging protocols. To this end, there are several publications presenting artificial intelligence‑based predictive models aiming to increase diagnostic accuracy and to facilitate optimal clinical management in patients diagnosed with MS and/or CIS. The current study presents a thorough review covering DL techniques that have been applied in MS and CIS during recent years, shedding light on their current advances and limitations.
- 9 August 2021
- Published by Spandidos Publications in Experimental and Therapeutic Medicine
- Vol. 22 (4) , 1-17
Open AccessEmerging deep learning techniques using magnetic resonance imaging data applied in multiple sclerosis and clinical isolated syndrome patients (Review)
Computer‑aided diagnosis systems aim to assist clinicians in the early identification of abnormal signs in order to optimize the interpretation of medical images and increase diagnostic precision. Multiple sclerosis (MS) and clinically isolated syndrome (CIS) are chronic inflammatory, demyelinating diseases affecting the central nervous system. Recent advances in deep learning (DL) techniques have led to novel computational paradigms in MS and CIS imaging designed for automatic segmentation and detection of areas of interest and automatic classification of anatomic structures, as well as optimization of neuroimaging protocols. To this end, there are several publications presenting artificial intelligence‑based predictive models aiming to increase diagnostic accuracy and to facilitate optimal clinical management in patients diagnosed with MS and/or CIS. The current study presents a thorough review covering DL techniques that have been applied in MS and CIS during recent years, shedding light on their current advances and limitations.
- Open Access
- 1 January 2020
- Published by Walter de Gruyter GmbH in Open Medicine
- Vol. 15 (1) , 520-530
Extended perfusion protocol for MS lesion quantification
This study aims to examine a time-extended dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) protocol and report a comparative study with three different pharmacokinetic (PK) models, for accurate determination of subtle blood-brain barrier (BBB) disruption in patients with multiple sclerosis (MS). This time-extended DCE-MRI perfusion protocol, called Snaps, was applied on 24 active demyelinating lesions of 12 MS patients. Statistical analysis was performed for both protocols through three different PK models. The Snaps protocol achieved triple the window time of perfusion observation by extending the magnetic resonance acquisition time by less than 2 min on average for all patients. In addition, the statistical analysis in terms of adj-R-2 goodness of fit demonstrated that the Snaps protocol outperformed the conventional DCE-MRI protocol by detecting 49% more pixels on average. The exclusive pixels identified from the Snaps protocol lie in the low k(trans) range, potentially reflecting areas with subtle BBB disruption. Finally, the extended Tofts model was found to have the highest fitting accuracy for both analyzed protocols. The previously proposed time-extended DCE protocol, called Snaps, provides additional temporal perfusion information at the expense of a minimal extension of the conventional DCE acquisition time.
- 1 January 2020
- Published by Walter de Gruyter GmbH in Open Medicine
- Vol. 15 (1) , 520-530
Open AccessExtended perfusion protocol for MS lesion quantification
This study aims to examine a time-extended dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) protocol and report a comparative study with three different pharmacokinetic (PK) models, for accurate determination of subtle blood-brain barrier (BBB) disruption in patients with multiple sclerosis (MS). This time-extended DCE-MRI perfusion protocol, called Snaps, was applied on 24 active demyelinating lesions of 12 MS patients. Statistical analysis was performed for both protocols through three different PK models. The Snaps protocol achieved triple the window time of perfusion observation by extending the magnetic resonance acquisition time by less than 2 min on average for all patients. In addition, the statistical analysis in terms of adj-R-2 goodness of fit demonstrated that the Snaps protocol outperformed the conventional DCE-MRI protocol by detecting 49% more pixels on average. The exclusive pixels identified from the Snaps protocol lie in the low k(trans) range, potentially reflecting areas with subtle BBB disruption. Finally, the extended Tofts model was found to have the highest fitting accuracy for both analyzed protocols. The previously proposed time-extended DCE protocol, called Snaps, provides additional temporal perfusion information at the expense of a minimal extension of the conventional DCE acquisition time.
- 31 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 23 (5) , 1834-1843
Investigating the Role of Model-Based and Model-Free Imaging Biomarkers as Early Predictors of Neoadjuvant Breast Cancer Therapy Outcome
Imaging biomarkers (IBs) play a critical role in the clinical management of breast cancer (BRCA) patients throughout the cancer continuum for screening, diagnosis, and therapy assessment, especially in the neoadjuvant setting. However, certain model-based IBs suffer from significant variability due to the complex workflows involved in their computation, whereas model-free IBs have not been properly studied regarding clinical outcome. In this study, IBs from 35 BRCA patients who received neoadjuvant chemotherapy (NAC) were extracted from dynamic contrast-enhanced MR imaging (DCE-MRI) data with two different approaches, a model-free approach based on pattern recognition (PR), and a model-based one using pharmacokinetic compartmental modeling. Our analysis found that both model-free and model-based biomarkers can predict pathological complete response (pCR) after the first cycle of NAC. Overall, eight biomarkers predicted the treatment response after the first cycle of NAC, with statistical significance (p-value < 0.05), and three at the baseline. The best pCR predictors at first follow-up, achieving high AUC and sensitivity and specificity more than 50%, were the hypoxic component with threshold 2 (AUC 90.4%) from the PR method, and the median value of k ep (AUC 73.4%) from the model-based approach. Moreover, the 80 th percentile of ve achieved the highest pCR prediction at baseline with AUC 78.5%. The results suggest that the model-free DCE-MRI IBs could be a more robust alternative to complex, model-based ones such as k ep and favor the hypothesis that the PR image-derived hypoxic image component captures actual tumor hypoxia information able to predict BRCA NAC outcome.
- 31 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 23 (5) , 1834-1843
Investigating the Role of Model-Based and Model-Free Imaging Biomarkers as Early Predictors of Neoadjuvant Breast Cancer Therapy Outcome
Imaging biomarkers (IBs) play a critical role in the clinical management of breast cancer (BRCA) patients throughout the cancer continuum for screening, diagnosis, and therapy assessment, especially in the neoadjuvant setting. However, certain model-based IBs suffer from significant variability due to the complex workflows involved in their computation, whereas model-free IBs have not been properly studied regarding clinical outcome. In this study, IBs from 35 BRCA patients who received neoadjuvant chemotherapy (NAC) were extracted from dynamic contrast-enhanced MR imaging (DCE-MRI) data with two different approaches, a model-free approach based on pattern recognition (PR), and a model-based one using pharmacokinetic compartmental modeling. Our analysis found that both model-free and model-based biomarkers can predict pathological complete response (pCR) after the first cycle of NAC. Overall, eight biomarkers predicted the treatment response after the first cycle of NAC, with statistical significance (p-value < 0.05), and three at the baseline. The best pCR predictors at first follow-up, achieving high AUC and sensitivity and specificity more than 50%, were the hypoxic component with threshold 2 (AUC 90.4%) from the PR method, and the median value of k ep (AUC 73.4%) from the model-based approach. Moreover, the 80 th percentile of ve achieved the highest pCR prediction at baseline with AUC 78.5%. The results suggest that the model-free DCE-MRI IBs could be a more robust alternative to complex, model-based ones such as k ep and favor the hypothesis that the PR image-derived hypoxic image component captures actual tumor hypoxia information able to predict BRCA NAC outcome.