Search

Abstract Background and purpose White matter hyperintensities in brain MRI are key indicators of various neurological conditions, and their accurate segmentation is essential for assessing disease progression. This study aims to evaluate the performance of a 3D convolutional neural network and a 3D Transformer-based model for white matter hyperintensities segmentation, focusing on their efficacy with limited datasets and similar computational resources. Materials and methods We implemented a convolution-based model (3D ResNet-50 U-Net with spatial and channel squeeze & excitation) and a Transformer-based model (3D Swin Transformer with a convolutional stem). The models were evaluated on two clinical datasets from Kaohsiung Chang Gung Memorial Hospital and National Center for High-Performance Computing. Four metrics were used for evaluation: Dice similarity coefficient, lesion segmentation, lesion F1-Score, and lesion sensitivity. Results The Transformer-based model, with appropriate adjustments, outperformed the well-established convolution-based model in foreground Dice similarity coefficient, lesion F1-Score, and sensitivity, demonstrating robust segmentation accuracy. DRLoc enhanced the Transformer’s performance, achieving comparable results on internal and benchmark datasets despite limited data availability. Conclusion With comparable computational overhead, a Transformer-based model can surpass a well-established convolution-based model in white matter hyperintensities segmentation on small datasets by capturing global context effectively, making them suitable for clinical applications where computational resources are constrained.

Background: Patients with carbon monoxide (CO) intoxication may develop ongoing neurological and psychiatric symptoms that ebb and flow, a condition often called delayed encephalopathy (DE). The association between morphologic changes in the brain and neuropsychological deficits in DE is poorly understood. Methods: Magnetic resonance imaging and neuropsychological tests were conducted on 11 CO patients with DE, 11 patients without DE, and 15 age-, sex-, and education-matched healthy subjects. Differences in gray matter volume (GMV) between the subgroups were assessed and further correlated with diminished cognitive functioning. Results: As a group, the patients had lower regional GMV compared to controls in the following regions: basal ganglia, left claustrum, right amygdala, left hippocampus, parietal lobes, and left frontal lobe. The reduced GMV in the bilateral basal ganglia, left post-central gyrus, and left hippocampus correlated with decreased perceptual organization and processing speed function. Those CO patients characterized by DE patients had a lower GMV in the left anterior cingulate and right amygdala, as well as lower levels of cognitive function, than the non-DE patients. Conclusions: Patients with CO intoxication in the chronic stage showed a worse cognitive and morphologic outcome, especially those with DE. This study provides additional evidence of gray matter structural abnormalities in the pathophysiology of DE in chronic CO intoxicated patients. [ABSTRACT FROM AUTHOR]