Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Filters

2010 - 201932020 - 20252

Settings

Subject: search.filters.subject.Electroencephalography

Search Results

Now showing 1 - 5 of 5
  • Article
    Vision-Language Model Approach for Few-Shot Learning of Attention Deficit Hyperactivity Disorder Using EEG Connectivity-Based Featured Images
    (IOP Publishing Ltd, 2025) Catal, Mehmet Sergen; Gumus, Abdurrahman; Karabiber Cura, Ozlem; Aydin, Ocan; Zubeyir Unlu, Mehmet
    Traditional medical diagnosis approaches have predominantly relied on single-modality analysis, limiting clinicians to interpreting isolated data streams such as images or time series. The integration of vision language models (VLMs) into neurophysiological analysis represents a paradigm shift toward multimodal diagnostic frameworks, enabling clinicians to interact with diagnosis models through diverse modalities including text, audio, visual inputs, etc. This multimodal interaction capability extends beyond conventional label-based classification, offering clinicians flexibility in diagnostic reasoning and decision-making processes. Building on this foundation, this study explores the application of VLMs to electroencephalography (EEG)-based attention deficit hyperactivity disorder (ADHD) classification, addressing a gap in neurophysiological diagnostics. The proposed framework applies VLM-based few-shot ADHD classification by converting raw EEG data into EEG connectivity-based featured images compatible with contrastive language-image pre-training's (CLIP) image encoder. The adaptor-based CLIP approach (Tip-Adapter and Tip-Adapter-F) for few-shot learning improves CLIP's zero-shot classification performance, achieving 78.73% accuracy with 1-shot and 98.30% accuracy with 128-shot using the RN50x16 backbone. Experiments investigate prompt engineering effects, backbone architectures of CLIP, patient-based classification, and combinations of EEG connectivity features. Comparative analysis is performed with two datasets to evaluate the approach between different data sources. Through the adaptation of pre-trained VLMs to neurophysiological data, this technique demonstrates the potential for multimodal diagnostic frameworks that enable flexible clinician-model interactions beyond conventional label-based classification systems. The approach achieves effective ADHD classification with minimal training data while establishing foundations for applying VLMs in clinical neuroscience, where diverse modality interactions through text, visual, and audio inputs can enhance diagnostic workflows. The code is publicly available on GitHub to facilitate further research in the field: https://github.com/miralab-ai/vlm-few-shot-eeg.
  • Article
    Citation - WoS: 2
    Citation - Scopus: 2
    Temporal Electroencephalography Features Unveiled Via Olfactory Stimulus as Biomarkers for Mild Alzheimer's Disease
    (Elsevier Sci Ltd, 2025) Olcay, Bilal Orkan; Pehlivan, Murat; Karacali, Bilge
    Aim: Our primary aim is to capture and use the timings of the characteristic brain responses to olfactory stimulation for mild Alzheimer's disease diagnosis purposes. Proposed method: Our method identifies the timings of short-lived signal segments where characteristic distances between pre- and post-stimulus relative spectral energies are attained for each EEG channel and frequency band. These timings and timing-derived features were subsequently used in a leave-one-subject-out cross-validation scenario to assess the diagnostic performance of our framework. We evaluated seven distinct statistical distance measures to determine the most effective one for characterizing the neurological conditions of the subjects. Results: The average cross-validation performance shows that our framework achieved 87.50% diagnosis performance. The frequently used features were mainly derived from the delta and alpha activity of the prefrontal region (Fp1) and the beta activity of the parietal region (Pz), which agree with the current findings of olfaction biophysics. Comparison with existing methods: We compared the performance of our method with that of four existing methods in the literature. Our method outperformed these four methods. Moreover, our method elicited the highest accuracy when the clinical olfactory score (UPSIT) was included as a feature. Conclusions: Our analysis framework reveals a significant alteration of the timing organization of the brain that emerged upon olfactory stimulation in Alzheimer's patients. The timings of characteristic response and the features calculated via these timings contribute to Alzheimer's disease diagnosis performance remarkably. The perspective proposed here may facilitate early diagnosis, thereby facilitating the exploration of novel therapeutic and treatment strategies.
  • Conference Object
    Citation - Scopus: 3
    Entropik Kümeleme Kullanılarak Beyin Aktivitesi Karakterizasyonu
    (IEEE, 2017) Olcay, Bilal Orkan; Karacali, Bilge; Ozgoren, Murat; Guducu, Cagda
    In this study, two novel entropy and mutual information based algorithms have been proposed to characterize the stimulus specific brain activity. In the first method, inter channel mutual information of electroencephalography signals has been calculated and the channels that exhibit synchronized behaivour during stimulus. In the second method, the responsiveness of the individual channels has been characterized in an entropic manner and then, the channels which demonstrates stimulus specific entropic behavior have been obtained. The performance of the proposed methods has been simulated on a real dataset obtained from Dokuz Eylul University Brain Biophysics laboratory. The results demonstrate that different regions of the brain exhibit a coherent activity during stimulus.
  • Article
    Citation - WoS: 24
    Citation - Scopus: 24
    Mice Doubly-Deficient in Lysosomal Hexosaminidase a and Neuraminidase 4 Show Epileptic Crises and Rapid Neuronal Loss
    (Public Library of Science, 2010) Seyrantepe, Volkan; Lema, Pablo; Caqueret, Aurore; Dridi, Larbi; Hadj, Samar Bel; Carpentier, Stephane; Boucher, Francine; Levade, Thierry; Carmant, Lionel; Gravel, Roy A.; Hamel, Edith; Vachon, Pascal; Di Cristo, Graziella; Michaud, Jacques L.; Morales, Carlos R.; Pshezhetsky, Alexey V.
    Tay-Sachs disease is a severe lysosomal disorder caused by mutations in the HexA gene coding for the a-subunit of lysosomal β-hexosaminidase A, which converts GM2 to GM3 ganglioside. Hexa-/- mice, depleted of b-hexosaminidase A, remain asymptomatic to 1 year of age, because they catabolise GM2 ganglioside via a lysosomal sialidase into glycolipid GA2, which is further processed by β-hexosaminidase B to lactosyl-ceramide, thereby bypassing the β-hexosaminidase A defect. Since this bypass is not effective in humans, infantile Tay-Sachs disease is fatal in the first years of life. Previously, we identified a novel ganglioside metabolizing sialidase, Neu4, abundantly expressed in mouse brain neurons. Now we demonstrate that mice with targeted disruption of both Neu4 and Hexa genes (Neu4-/-;Hexa-/-) show epileptic seizures with 40% penetrance correlating with polyspike discharges on the cortical electrodes of the electroencephalogram. Single knockout Hexa-/- or Neu4-/- siblings do not show such symptoms. Further, double-knockout but not single-knockout mice have multiple degenerating neurons in the cortex and hippocampus and multiple layers of cortical neurons accumulating GM2 ganglioside. Together, our data suggest that the Neu4 block exacerbates the disease in Hexa-/- mice, indicating that Neu4 is a modifier gene in the mouse model of Tay-Sachs disease, reducing the disease severity through the metabolic bypass. However, while disease severity in the double mutant is increased, it is not profound suggesting that Neu4 is not the only sialidase contributing to the metabolic bypass in Hexa-/- mice.
  • Article
    Citation - WoS: 15
    Citation - Scopus: 17
    Quasi-Supervised Learning for Biomedical Data Analysis
    (Elsevier Ltd., 2010) Karaçalı, Bilge
    We present a novel formulation for pattern recognition in biomedical data. We adopt a binary recognition scenario where a control dataset contains samples of one class only, while a mixed dataset contains an unlabeled collection of samples from both classes. The mixed dataset samples that belong to the second class are identified by estimating posterior probabilities of samples for being in the control or the mixed datasets. Experiments on synthetic data established a better detection performance against possible alternatives. The fitness of the method in biomedical data analysis was further demonstrated on real multi-color flow cytometry and multi-channel electroencephalography data. © 2010 Elsevier Ltd. All rights reserved.