Search

Accurate segmentation of chronic stroke lesions from mono‐spectral magnetic resonance imaging scans (e.g., T1‐weighted images) is a difficult task due to the arbitrary shape, complex texture, variable size and intensities, and varied locations of the lesions. Due to this inherent spatial heterogeneity, existing machine learning methods have shown moderate performance for chronic lesion delineation. In this study, we introduced: (1) a method that integrates transformers' deformable feature attention mechanism with convolutional deep learning architecture to improve the accuracy and generalizability of stroke lesion segmentation, and (2) an ecological data augmentation technique based on inserting real lesions into intact brain regions. Our combination of these two approaches resulted in a significant increase in segmentation performance, with a Dice index of 0.82 (±0.39), outperforming the existing methods trained and tested on the same Anatomical Tracings of Lesions After Stroke (ATLAS) 2022 dataset. Our method performed relatively well even for cases with small stroke lesions. We validated the robustness of our method through an ablation study and by testing it on new unseen brain scans from the Ischemic Stroke Lesion Segmentation (ISLES) 2015 dataset. Overall, our proposed approach of transformers with ecological data augmentation offers a robust way to delineate chronic stroke lesions with clinically relevant accuracy. Our method can be extended to other challenging tasks that require automated detection and segmentation of diverse brain abnormalities from clinical scans. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The current study aimed to evaluate the effects of action observation on the walking ability and oscillatory brain activity of chronic stroke patients. Fourteen chronic stroke patients were allocated randomly to the action observation (AO) or sham observation (SO) groups. Both groups received 12 sessions of intervention. Each session composed of 12 min of observational training, which depicted exercises for the experimental group but nature pictures for the sham group and 40 min of occupational therapy, which was the same for the both groups. Walking ability was assessed by a motion analysis system and brain activity was monitored using quantitative electroencephalography (QEEG) before and after the intervention. Brain asymmetry at alpha frequency, the percentage of stance phase, and step length showed significant changes in the AO group. Only the change in global alpha power was significantly correlated with the change in velocity after the intervention in AO group. Despite more improvements in walking and brain activity of patients in the AO group, our study failed to show significant correlations between the brain activity changes and functional improvements after the intervention, which might be mainly due to the small sample size in our study. Trial registration: IRCT20181014041333N1 [ABSTRACT FROM AUTHOR]

Background and Aim: Stroke is a leading cause of permanent disability in developing nations. Motor impairment in stroke contributes to limitations in activities of daily life, participation in community, and overall quality of life. Recovery following stroke is challenged by poor lower-limb muscle performance interfering with balance, gait, and functional tasks. Objective: The objective of this study was to investigate the effect of Russian current over the quadriceps muscle in 10-m walk performance and Brunnstrom stages of lower-extremity recovery in chronic stroke survivors. Materials and Methods: The Institutional Review Board approval was obtained for this pilot study, and a total of 36 chronic stroke survivors were recruited from the outpatient department of Alva's College of Physiotherapy and Research Center, Moodubidire, Karnataka. Consent was obtained from the voluntary participants, and they were randomly assigned to one of the two groups; intervention and the control groups. Participants in the intervention group received Russian current over the quadriceps muscle in addition to the conventional rehabilitation, whereas the control group participants received only conventional rehabilitation. The study duration was 6 weeks. The outcomes measured were 10-m walk test and Brunnstrom stages of lower-extremity recovery. Results: Statistical analysis was performed with SPSS statistical software. The Kolmogorov–Smirnov test was performed for normality. The paired t-test, within-group analysis, demonstrated a significant increase in the 10-m walk test (P < 002) and Brunnstrom stage of lower extremity (P < 0.043) for the intervention group. The independent t-test demonstrated a highly significant (P = 0.001) value for the intervention group than the control group. Conclusion: Statistical results conclude that Russian current is effective in improving 10-m walk performance and Brunnstrom stages of motor recovery of lower limb in chronic stroke survivors.