Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

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

Browse

Filters

2023 - 20252

Settings

Publisher: search.filters.publisher.IOP Publishing LtdWoS Q: search.filters.wosQuartile.Q1

Search Results

Now showing 1 - 2 of 2
  • 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: 23
    Citation - Scopus: 26
    Fish scale containing alginate dialdehyde-gelatin bioink for bone tissue engineering
    (IOP Publishing Ltd, 2023) Özenler, Aylin Kara; Distler, Thomas; Tıhmınlıoğlu, Funda; Boccaccini, Aldo R
    The development of biomaterial inks suitable for biofabrication and mimicking the physicochemical properties of the extracellular matrix is essential for the application of bioprinting technology in tissue engineering (TE). The use of animal-derived proteinous materials, such as jellyfish collagen, or fish scale (FS) gelatin (GEL), has become an important pillar in biomaterial ink design to increase the bioactivity of hydrogels. However, besides the extraction of proteinous structures, the use of structurally intact FS as an additive could increase biocompatibility and bioactivity of hydrogels due to its organic (collagen) and inorganic (hydroxyapatite) contents, while simultaneously enhancing mechanical strength in three-dimensional (3D) printing applications. To test this hypothesis, we present here a composite biomaterial ink composed of FS and alginate dialdehyde (ADA)-GEL for 3D bioprinting applications. We fabricate 3D cell-laden hydrogels using mouse pre-osteoblast MC3T3-E1 cells. We evaluate the physicochemical and mechanical properties of FS incorporated ADA-GEL biomaterial inks as well as the bioactivity and cytocompatibility of cell-laden hydrogels. Due to the distinctive collagen orientation of the FS, the compressive strength of the hydrogels significantly increased with increasing FS particle content. Addition of FS also provided a tool to tune hydrogel stiffness. FS particles were homogeneously incorporated into the hydrogels. Particle-matrix integration was confirmed via scanning electron microscopy. FS incorporation in the ADA-GEL matrix increased the osteogenic differentiation of MC3T3-E1 cells in comparison to pristine ADA-GEL, as FS incorporation led to increased ALP activity and osteocalcin secretion of MC3T3-E1 cells. Due to the significantly increased stiffness and supported osteoinductivity of the hydrogels, FS structure as a natural collagen and hydroxyapatite source contributed to the biomaterial ink properties for bone engineering applications. Our findings indicate that ADA-GEL/FS represents a new biomaterial ink formulation with great potential for 3D bioprinting, and FS is confirmed as a promising additive for bone TE applications.