Introduction: The aim of this study was to examine whether the patterns of diffusion-weighted imaging (DWI) abnormalities and quantitative regional apparent diffusion coefficient (ADC) values can predict the clinical outcome of comatose patients following cardiac arrest. Methods: Thirty-nine patients resuscitated from out-of-hospital cardiac arrest were prospectively investigated. Within five days of resuscitation, axial DWIs were obtained and ADC maps were generated using two 1.5-T magnetic resonance scanners. The neurological outcomes of the patients were assessed using the Glasgow Outcome Scale (GOS) score at three months after the cardiac arrest. The brain injuries were categorised into four patterns: normal, isolated cortical injury, isolated deep grey nuclei injury, and mixed injuries (cortex and deep grey nuclei). Twenty-three subjects with normal DWIs served as controls. The ADC and percent ADC values (the ADC percentage as compared to the control data from the corresponding region) were obtained in various regions of the brains. We analysed the differences between the favourable (GOS score 4 to 5) and unfavourable (GOS score 1 to 3) groups with regard to clinical data, the DWI abnormalities, and the ADC and percent ADC values. Results: The restricted diffusion abnormalities in the cerebral cortex, caudate nucleus, putamen and thalamus were significantly different between the favourable (n = 13) and unfavourable (n = 26) outcome groups. The cortical pattern of injury was seen in one patient (3%), the deep grey nuclei pattern in three patients (8%), the cortex and deep grey nuclei pattern in 21 patients (54%), and normal DWI findings in 14 patients (36%). The cortex and deep grey nuclei pattern was significantly associated with the unfavourable outcome (20 patients with unfavourable vs. 1 patient with favourable outcomes, P < 0.001). In the 22 patients with quantitative ADC analyses, severely reduced ADCs were noted in the unfavourable outcome group. The optimal cutoffs for the mean ADC and the percent ADC values determined by receiver operating characteristic (ROC) curve analysis in the cortex, caudate nucleus, putamen, and thalamus predicted the unfavourable outcome with sensitivities of 67 to 93% and a specificity of 100%. Conclusions: The patterns of brain injury in early diffusion-weighted imaging (DWI) (less than or equal to five days after resuscitation) and the quantitative measurement of regional ADC may be useful for predicting the clinical outcome of comatose patients after cardiac arrest.

Multi-label brain segmentation from brain magnetic resonance imaging (MRI) provides valuable structural information for most neurological analyses. Due to the complexity of the brain segmentation algorithm, it could delay the delivery of neuroimaging findings. Therefore, we introduce Split-Attention U-Net (SAU-Net), a convolutional neural network with skip pathways and a split-attention module that segments brain MRI scans. The proposed architecture employs split-attention blocks, skip pathways with pyramid levels, and evolving normalization layers. For efficient training, we performed pre-training and fine-tuning with the original and manually modified FreeSurfer labels, respectively. This learning strategy enables involvement of heterogeneous neuroimaging data in the training without the need for many manual annotations. Using nine evaluation datasets, we demonstrated that SAU-Net achieved better segmentation accuracy with better reliability that surpasses those of state-of-the-art methods. We believe that SAU-Net has excellent potential due to its robustness to neuroanatomical variability that would enable almost instantaneous access to accurate neuroimaging biomarkers and its swift processing runtime compared to other methods investigated.

Objective Alzheimer’s disease (AD) is the most common type of dementia and the prevalence rapidly increased as the elderly population increased worldwide. In the contemporary model of AD, it is regarded as a disease continuum involving preclinical stage to severe dementia. For accurate diagnosis and disease monitoring, objective index reflecting structural change of brain is needed to correctly assess a patient’s severity of neurodegeneration independent from the patient’s clinical symptoms. The main aim of this paper is to develop a random forest (RF) algorithm-based prediction model of AD using structural magnetic resonance imaging (MRI).Methods We evaluated diagnostic accuracy and performance of our RF based prediction model using newly developed brain segmentation method compared with the Freesurfer’s which is a commonly used segmentation software.Results Our RF model showed high diagnostic accuracy for differentiating healthy controls from AD and mild cognitive impairment (MCI) using structural MRI, patient characteristics, and cognitive function (HC vs. AD 93.5%, AUC 0.99; HC vs. MCI 80.8%, AUC 0.88). Moreover, segmentation processing time of our algorithm (<5 minutes) was much shorter than of Freesurfer’s (6–8 hours).Conclusion Our RF model might be an effective automatic brain segmentation tool which can be easily applied in real clinical practice.

MRI-visible perivascular spaces in the neonatal brain were associated with maturation and preterm birth but not with sex. Background Mounting evidence suggests that perivascular spaces (PVSs) visible at MRI reflect the function of the glymphatic system. Understanding PVS burden in neonates may guide research on early ...

Song KS, et al. Yonsei Med J. 1992 Jun;33(2):168-172. https://doi.org/10.3349/ymj.1992.33.2.168

Chung SR, et al. Korean J Radiol. 2021 Sep;22(9):1579-1586. https://doi.org/10.3348/kjr.2021.0230