This study investigated the characteristics of cognitive impairment in patients with white matter lesions (WMLs) caused by cerebral small vessel disease and the corresponding changes in WM microstructures. Diffusion tensor imaging (DTI) data of 50 patients with WMLs and 37 healthy controls were collected. Patients were divided into vascular cognitive impairment non-dementia and vascular dementia groups. Tract-based spatial statistics showed that patients with WMLs had significantly lower fractional anisotropy (FA) and higher mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) values throughout the WM areas but predominately in the forceps minor, forceps major (FMA), bilateral corticospinal tract, inferior fronto-occipital fasciculus, superior longitudinal fasciculus, inferior longitudinal fasciculus (ILF), and anterior thalamic radiation, compared to the control group. These fiber bundles were selected as regions of interest. There were significant differences in the FA, MD, AD, and RD values (p < 0.05) between groups. The DTI metrics of all fiber bundles significantly correlated with the Montreal Cognitive Assessment (p < 0.05), with the exception of the AD values of the FMA and ILF. Patients with WMLs showed changes in diffusion parameters in the main WM fiber bundles. Quantifiable changes in WM microstructure are the main pathological basis of cognitive impairment, and may serve as a biomarker of WMLs.

Cerebral stroke (CS) is a heterogeneous syndrome caused by multiple disease mechanisms. Ischemic stroke (IS) is a subtype of CS that causes a disruption of cerebral blood flow with subsequent tissue damage. Noncontrast computer tomography (NCCT) is one of the most important IS detection methods. It is difficult to select the features of IS CT within computational image analysis. In this paper, we propose AC-YOLOv5, which is an improved detection algorithm for IS. The algorithm amplifies the features of IS via an NCCT image based on adaptive local region contrast enhancement, which then detects the region of interest via YOLOv5, which is one of the best detection algorithms at present. The proposed algorithm was tested on two datasets, and seven control group experiments were added, including popular detection algorithms at present and other detection algorithms based on image enhancement. The experimental results show that the proposed algorithm has a high accuracy (94.1% and 91.7%) and recall (85.3% and 88.6%) rate; the recall result is especially notable. This proves the excellent performance of the accuracy, robustness, and generalizability of the algorithm.