Cerebral small-vessel disease at high altitude: A comparison of patients from plateau and plain.

Background and purpose: Cerebral small-vessel disease (CSVD) is prevalent worldwide and one of the major causes of stroke and dementia. For patients with CSVD at high altitude, a special environmental status, limited information is known about their clinical phenotype and specific neuroimaging change. We investigated the clinical and neuroimaging features of patients residing at high altitude by comparing with those in the plain, trying to explore the impact of high altitude environment on CSVD. Methods: Two cohorts of CSVD patients from the Tibet Autonomous Region and Beijing were recruited retrospectively. In addition to the collection of clinical diagnoses, demographic information and traditional vascular risk factors, the presence, location, and severity of lacunes and white matter hyperintensities were assessed by manual counting and using age-related white matter changes (ARWMC) rating scale. Differences between the two groups and influence of long-term residing in the plateau were analyzed. Results: A total of 169 patients in Tibet (high altitude) and 310 patients in Beijing (low altitude) were enrolled. Fewer patients in high altitude group were found with acute cerebrovascular events and concomitant traditional vascular risk factors. The median (quartiles) ARWMC score was 10 (4, 15) in high altitude group and 6 (3, 12) in low altitude group. Less lacunes were detected in high altitude group [0 (0, 4)] than in low altitude group [2 (0, 5)]. In both groups, most lesions located in the subcortical (especially frontal) and basal ganglia regions. Logistic regressions showed that age, hypertension, family history of stroke, and plateau resident were independently associated with severe white matter hyperintensities, while plateau resident was negatively correlated with lacunes. Conclusion: Patients of CSVD residing at high altitude showed more severe WMH but less acute cerebrovascular events and lacunes in neuroimaging, comparing to patients residing at low altitude. Our findings suggest potential biphasic effect of high altitude on the occurrence and progression of CSVD.

SMBFT: A Modified Fuzzy c-Means Algorithm for Superpixel Generation.

Most traditional superpixel segmentation methods used binary logic to generate superpixels for natural images. When these methods are used for images with significantly fuzzy characteristics, the boundary pixels sometimes cannot be correctly classified. In order to solve this problem, this paper proposes a Superpixel Method Based on Fuzzy Theory (SMBFT), which uses fuzzy theory as a guide and traditional fuzzy c-means clustering algorithm as a baseline. This method can make full use of the advantage of the fuzzy clustering algorithm in dealing with the images with the fuzzy characteristics. Boundary pixels which have higher uncertainties can be correctly classified with maximum probability. The superpixel has homogeneous pixels. Meanwhile, the paper also uses the surrounding neighborhood pixels to constrain the spatial information, which effectively alleviates the negative effects of noise. The paper tests on the images from Berkeley database and brain MR images from the Brain web. In addition, this paper proposes a comprehensive criterion to measure the weights of two kinds of criterions in choosing superpixel methods for color images. An evaluation criterion for medical image data sets employs the internal entropy of superpixels which is inspired by the concept of entropy in the information theory. The experimental results show that this method has superiorities than traditional methods both on natural images and medical images.

A new multistage medical segmentation method based on superpixel and fuzzy clustering.

The medical image segmentation is the key approach of image processing for brain MRI images. However, due to the visual complex appearance of image structures and the imaging characteristic, it is still challenging to automatically segment brain MRI image. A new multi-stage segmentation method based on superpixel and fuzzy clustering (MSFCM) is proposed to achieve the good brain MRI segmentation results. The MSFCM utilizes the superpixels as the clustering objects instead of pixels, and it can increase the clustering granularity and overcome the influence of noise and bias effectively. In the first stage, the MRI image is parsed into several atomic areas, namely, superpixels, and a further parsing step is adopted for the areas with bigger gray variance over setting threshold. Subsequently, designed fuzzy clustering is carried out to the fuzzy membership of each superpixel, and an iterative broadcast method based on the Butterworth function is used to redefine their classifications. Finally, the segmented image is achieved by merging the superpixels which have the same classification label. The simulated brain database from BrainWeb site is used in the experiments, and the experimental results demonstrate that MSFCM method outperforms the traditional FCM algorithm in terms of segmentation accuracy and stability for MRI image.