Magnetic resonance imaging plays a crucial role in the diagnosis and management of ischemic stroke. Accurate segmentation of stroke lesions holds significant clinical value in assisting the formulation of individualized interventional treatment plans and objectively assessing patient prognosis. To address the challenges of blurred and irregularly shaped ischemic stroke lesions with random locations, this study proposes a prior knowledge-guided and multi-level edge feature fusion shifted window Transformer-based U-Net with encoder representations (PMSwin UNETR). First, based on the distribution characteristics of stroke lesions, a lesion distribution probability map is generated to guide the segmentation network in focusing on areas prone to lesions. Second, a multi-level edge feature extraction module is employed to enrich edge features. Finally, a soft-clDice loss function is introduced to directly learn lesion boundaries, enhancing edge segmentation accuracy. The effectiveness of PMSwin UNETR was validated using the 2022 Ischemic Stroke Lesion Segmentation Challenge (ISLES2022) dataset, with results showing Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and recall rates of 82.43%, 3.768 8, and 82.45%, respectively, outperforming other mainstream segmentation algorithms. This study demonstrates that the proposed PMSwin UNETR model effectively improves ischemic stroke lesion segmentation, providing important references and application value for precise clinical diagnosis and intelligent medical imaging research in stroke.
Objective To understand the current situation of the care burden of primary caregiver of patients with oral diquat poisoning, analyze its influencing factors, and analyze the mediating effect of psychological resilience in social support and care burden, so as to provide a theoretical basis for further clinical intervention. Methods The primary caregivers of patients with oral diquat poisoning who received treatment at Qilu Hospital of Shandong University between October 2019 and October 2021 were selected. The general information questionnaire, Zarit Burden Interview (ZBI), Connor-davidson Resilience Scale (CD-RISC), and Social Support Revalued Scale (SSRS) were used to investigate the primary caregivers of patients with oral diquat poisoning. The influencing factors of the care burden on primary caregivers were analyzed. Results A total of 218 patients and their primary caregivers were included. The age of the primary caregivers, whether they were an only child, physical condition, educational level, economic income, daily care time, patient’s condition, and patient’s urinary concentration of diquat were the influencing factors of ZBI. The SSRS score of the primary caregiver was 26.97±10.21, the CD-RISC score was 56.95±26.64, and the ZBI score was 52.95±16.06. The burden of care was negatively correlated with social support (r=?0.369, P<0.05), the burden of care was negatively correlated with psychological resilience (r=?0.467, P<0.05), and social support was positively correlated with psychological resilience (r=0.288, P<0.05). The role of psychological resilience in the influence of social support and care burden was partly mediated, accounting for 41.905%. Conclusions The level of social support and psychological resilience of the primary caregivers is low, and the burden of care is heavy. Psychological resilience plays an intermediary role in the social support and care burden of the primary caregivers of patients with oral diquat poisoning. Clinical staff can carry out targeted intervention to improve the level of social support and psychological resilience and reduce the care burden.
