WoS İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.14627/6

Browse

Filters

20262

Settings

Language: search.filters.language.enSubject: search.filters.subject.Ischemic Stroke

Search Results

Now showing 1 - 2 of 2
  • Article
    Gba-Net: A Gated Bottleneck and Attention-Driven Architecture for Robust Ischemic Stroke Segmentation across Ct and Dwi
    (Baku State Univ, Inst Applied Mathematics, 2026) Pacal, I.; Ganie, S.M.
    Automated ischemic stroke segmentation remains difficult because non-contrast Computed Tomography (CT) is low contrast and noisy, whereas Diffusion Weighted Imaging (DWI) shows heterogeneous lesions. Conventional U-Net models rely on local receptive fields and unselective skip fusion, limiting global context and noise control. We propose GBA-Net, a UNet variant that combines a high-capacity gated Convolutional Neural Network (CNN) bottleneck for long range dependencies with convolutional block attention modules that refine multiscale features before decoder fusion. The bottleneck helps interpret subtle CT hypo densities and link scattered infarcts in DWI, while attention suppresses CT noise and filters high intensity mimics, improving boundary delineation. We evaluated GBA-Net on ISLES 2024 and TEKNOFEST 2021 and compared it with nine baselines including UNet, UNet++, DeepLabV3+, and Seg-Former. GBA-Net achieved Dice 0.7376 and 0.7140 and the best average ASSD of 4.73 pixels on CT.
  • Article
    Effect of Inspiratory Muscle Training on Diaphragm Function and Activity Performance in Subacute Ischemic Stroke Patients: A Single-Blind Randomized-Controlled Trial
    (SAGE Publications Inc., 2026) Akçay S.; Akyol D.K.; Erkut Ü.; Karagözoğlu Coşkunsu D.; Kunduracilar Z.; Bajrami A.; Dinç Yavaş A.; Kunduracilar, Zuhal; Coskunsu, Dilber Karagozoglu; Bajrami, Arsida; Akçay, Sümeyye; Akyol, Dudu Kübra; Erkut, Ümit; Karagözoğlu Coşkunsu, Dilber; Yavas, Arzu Dinc; Dinç Yavaş, Arzu
    Background: Respiratory dysfunction is common after stroke and may negatively affect functional recovery. Inspiratory muscle training (IMT) has been proposed to enhance diaphragmatic function and activity performance in this population. Objective: To investigate the effects of IMT on diaphragm function and activity performance in patients with subacute ischemic stroke. Methods: In this randomized controlled, single-blind trial, 26 patients with subacute ischemic stroke (>1 month post-onset) were randomly allocated to an intervention group (IG, n = 13) or control group (CG, n = 13). Both groups received standard neurorehabilitation, aerobic training, and the Active Cycle of Breathing Technique (ACBT). The IG additionally underwent IMT, 5 days per week for 6 weeks (30 sessions). Assessments included maximal inspiratory and expiratory pressures (MIP, MEP), diaphragmatic thickness (Ti, Te) and excursion via ultrasonography, 6-minute walk test (6MWT), and Canadian Occupational Performance Measure (COPM). Results: Twenty-two participants completed the study (IG = 11; CG = 11). Significant within-group improvements were observed in both groups for MIP, MEP, Ti, TF, excursion, 6MWT, and COPM scores (P < .05). Between-group analyses showed significantly greater improvements in the IG for ΔMIP (P < .001), ΔMEP (P = .003), affected-side ΔTi (P = .007), ΔTF (P = .008), and Δexcursion (P = .005). No significant differences were found for 6MWT and COPM (P > .05). Conclusions: IMT effectively improves respiratory muscle strength, diaphragmatic thickness, and excursion in subacute ischemic stroke and may be a valuable addition to post-stroke rehabilitation programs. Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT06210516. © The Author(s) 2026