Lin Shi

Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks

Cerebral microbleeds (CMBs) are small haemorrhages nearby blood vessels. They have been recognized as important diagnostic biomarkers for many cerebrovascular diseases and cognitive dysfunctions. In current clinical routine, CMBs are manually labelled by radiologists but this procedure is laborious, time-consuming, and error prone. In this paper, we propose a novel automatic method to detect CMBs from magnetic resonance (MR) images by exploiting the 3D convolutional neural network (CNN). Compared with previous methods that employed either low-level hand-crafted descriptors or 2D CNNs, our method can take full advantage of spatial contextual information in MR volumes to extract more representative high-level features for CMBs, and hence achieve a much better detection accuracy. To further improve the detection performance while reducing the computational cost, we propose a cascaded framework under 3D CNNs for the task of CMB detection. We first exploit a 3D fully convolutional network (FCN) strategy to retrieve the candidates with high probabilities of being CMBs, and then apply a well-trained 3D CNN discrimination model to distinguish CMBs from hard mimics. Compared with traditional sliding window strategy, the proposed 3D FCN strategy can remove massive redundant computations and dramatically speed up the detection process. We constructed a large dataset with 320 volumetric MR scans and performed extensive experiments to validate the proposed method, which achieved a high sensitivity of 93.16% with an average number of 2.74 false positives per subject, outperforming previous methods using low-level descriptors or 2D CNNs by a significant margin. The proposed method, in principle, can be adapted to other biomarker detection tasks from volumetric medical data.

Volume-Based Morphometry of Brain MR Images in Adolescent Idiopathic Scoliosis and Healthy Control Subjects

BACKGROUND AND PURPOSE: Adolescent idiopathic scoliosis (AIS) is a spinal deformity with unknown cause. Previous studies have suggested that subclinical neurologic abnormalities are associated with AIS. The objective of this prospective study was to characterize systematically neuroanatomic changes in patients with left thoracic AIS vs right thoracic AIS and healthy control subjects by using volume-based morphometry. MATERIALS AND METHODS: Our current study involved 9 girls with left thoracic AIS and 20 girls with right thoracic AIS vs 11 and 17 matched female control subjects, respectively. Voxel-based morphometry (VBM), deformation-based morphometry (DBM), and tensor-based morphometry (TBM) were used to analyze the MR images aligned with a specific brain template of local adolescent girls. The statistical t test was used in VBM and TBM, and the Hotelling T2 test was applied in DBM. RESULTS: Using VBM, we found statistically significant differences (P < .05) in the white matter attenuation of the genu of the corpus callosum and left internal capsule (left thoracic AIS < control subjects). In contrast, no significant differences were observed between patients with right thoracic AIS and control subjects. CONCLUSIONS: White matter attenuation in the corpus callosum and left internal capsule, responsible for interhemispheric communication and conduit of the corticothalamic projectional fibers, respectively, were found to be significantly lower in left thoracic AIS compared with control subjects; however, this was not the case in right thoracic AIS. Confirmation of the findings is required in future research, which needs to evaluate the relationship of white matter abnormality to curve laterality, pathogenesis, and prognosis in patients with AIS, with biologic significance and possible therapeutic correction.

Automated quantification of white matter lesion in magnetic resonance imaging of patients with acute infarction.

PURPOSE It has been reported that increased white matter lesions (WML) is one of the risk factors for stroke. To quantify WML objectively with the presence of acute infarcts, we proposed an automated segmentation scheme to locate WMLs in combined T1-weighted MRI, fluid attenuation inversion recovery (FLAIR) and diffusion weighted imaging (DWI). MATERIALS AND METHODS The proposed method detects WMLs by a coarse-to-fine mathematical morphology method. It has been evaluated quantitatively and qualitatively using voxel-based, volume-based, score-based, and atlas-based approaches on MRI data of 91 subjects with acute infarction. RESULT The proposed WML detection algorithm yields average sensitivity, positive predictive value and similarity index of 0.803, 0.818, and 0.836, respectively. Experimental results demonstrated that the segmentation from the proposed method is in high agreement with that from manual segmentation (intraclass correlation coefficient=0.9892), and with a good correlation with visual scores (R=0.8442, p<0.0001).

Excellent side-to-side symmetry in glenoid size and shape

ObjectiveIn quantifying glenoid bone loss and as a means to determine initial glenoid size, the abnormal glenoid is often compared with the contralateral normal glenoid. The assumption is that good symmetry exists between both glenoid surfaces with regard to size and shape. The purpose of this study is to critically analyze the structural symmetry of both glenoids in an objective and quantitative manner to ascertain the degree of symmetry present.Materials and methodsThe study cohort comprised 60 subjects (35 males and 25 females) with no shoulder pathology or injury. Each glenoid surface was extracted from the whole scapular model constructed from CT data using a 3D curvature-based incremental watershed algorithm. Glenoid morphometric analysis was carried out based on the 2D contour of the glenoid projected on the principal plane.ResultsThere was no side-to-side difference in glenoid length (p = 0.53), width (p = 0.42), area (p = 0.36), or circumference (p = 0.73). All glenoid dimensions were larger in males than females (p < 0.05). Point-wise curvature analysis showed no significant shape difference between both glenoids (all p > 0.1). Regression analysis revealed a positive correlation (R2 = 0.3–0.5) between increasing age and increasing glenoid size.ConclusionsIn normal subjects, both glenoids are highly symmetric in shape and size. This study provides objective and quantitative justification for using the normal counterlateral glenoid as a reference standard for initial glenoid shape in patients with unilateral glenoid bone loss.

Automatic detection of arterial input function in dynamic contrast enhanced MRI based on affinity propagation clustering.

To automatically and robustly detect the arterial input function (AIF) with high detection accuracy and low computational cost in dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI).

Variation in Anisotropy and Diffusivity along the Medulla Oblongata and the Whole Spinal Cord in Adolescent Idiopathic Scoliosis: A Pilot Study Using Diffusion Tensor Imaging

BACKGROUND AND PURPOSE: Disturbed somatosensory evoked potentials have been demonstrated in patients with adolescent idiopathic scoliosis (but this functional delay was found to originate above the C5–6 level, while the lower cord level was unaffected). Together with MR imaging observation of tonsillar ectopia and a relatively tethered cord, we hypothesized that there is disturbed mean diffusivity integrity along the spinal cord. In this study, advanced DTI was used to evaluate whether there was underlying decreased WM integrity within the brain stem and spinal cord in adolescent idiopathic scoliosis and any relationship to cerebellar tonsillar ectopia. Clinical impact on balance testing was also correlated. MATERIALS AND METHODS: Thirteen girls with adolescent idiopathic scoliosis with right thoracic curves were compared with 13 age-matched healthy girls. DTI of the brain and whole spinal cord was performed. ROIs were manually defined for the medulla oblongata and along each intervertebral segment of the cord. Mean values of fractional anisotropy and mean diffusivity were computed at the defined regions. Between-group comparisons were performed by 1-way ANOVA. RESULTS: Significantly decreased fractional anisotropy values and increased mean diffusivity values were found at the medulla oblongata and C1–2, C2–3, C3–4, and C4–5 segments in patients with adolescent idiopathic scoliosis compared with healthy subjects. No significant difference was found in the lower cord levels. Significant correlation was found between the tonsillar level and fractional anisotropy value at the C4–5 level in patients with adolescent idiopathic scoliosis only. CONCLUSIONS: The findings from this study are in agreement with previous findings showing abnormal somatosensory evoked potential readings occurring only above the C5–6 level in patients with adolescent idiopathic scoliosis; these findings might partially explain the pathophysiology of the neural pathway involved.

Construction of brain atlases based on a multi-center MRI dataset of 2020 Chinese adults

Despite the known morphological differences (e.g., brain shape and size) in the brains of populations of different origins (e.g., age and race), the Chinese brain atlas is less studied. In the current study, we developed a statistical brain atlas based on a multi-center high quality magnetic resonance imaging (MRI) dataset of 2020 Chinese adults (18–76 years old). We constructed 12 Chinese brain atlas from the age 20 year to the age 75 at a 5 years interval. New Chinese brain standard space, coordinates, and brain area labels were further defined. The new Chinese brain atlas was validated in brain registration and segmentation. It was found that, as contrast to the MNI152 template, the proposed Chinese atlas showed higher accuracy in hippocampus segmentation and relatively smaller shape deformations during registration. These results indicate that a population-specific time varying brain atlas may be more appropriate for studies involving Chinese populations.

Intensity and sulci landmark combined brain atlas construction for Chinese pediatric population

Constructing an atlas from a population of brain images is of vital importance to medical image analysis. Especially in neuroscience study, creating a brain atlas is useful for intra‐ and inter‐population comparison. Research on brain atlas construction has attracted great attention in recent years, but the research on pediatric population is still limited, mainly due to the limited availability and the relatively low quality of pediatric magnetic resonance brain images. This article is targeted at creating a high quality representative brain atlas for Chinese pediatric population. To achieve this goal, we have designed a set of preprocessing procedures to improve the image quality and developed an intensity and sulci landmark combined groupwise registration method to align the population of images for atlas construction. As demonstrated in experiments, the newly constructed atlas can better represent the size and shape of brains of Chinese pediatric population, and show better performance in Chinese pediatric brain image analysis compared with other standard atlases. Hum Brain Mapp 35:3880–3892, 2014.

Adaptive Distance Metric Learning for Diffusion Tensor Image Segmentation

High quality segmentation of diffusion tensor images (DTI) is of key interest in biomedical research and clinical application. In previous studies, most efforts have been made to construct predefined metrics for different DTI segmentation tasks. These methods require adequate prior knowledge and tuning parameters. To overcome these disadvantages, we proposed to automatically learn an adaptive distance metric by a graph based semi-supervised learning model for DTI segmentation. An original discriminative distance vector was first formulated by combining both geometry and orientation distances derived from diffusion tensors. The kernel metric over the original distance and labels of all voxels were then simultaneously optimized in a graph based semi-supervised learning approach. Finally, the optimization task was efficiently solved with an iterative gradient descent method to achieve the optimal solution. With our approach, an adaptive distance metric could be available for each specific segmentation task. Experiments on synthetic and real brain DTI datasets were performed to demonstrate the effectiveness and robustness of the proposed distance metric learning approach. The performance of our approach was compared with three classical metrics in the graph based semi-supervised learning framework.

Abnormal Organization of White Matter Network in Patients with No Dementia after Ischemic Stroke

Structural changes after ischemic stroke could affect information communication extensively in the brain network. It is likely that the defects in the white matter (WM) network play a key role in information interchange. In this study, we used graph theoretical analysis to examine potential organization alteration in the WM network architecture derived from diffusion tensor images from subjects with no dementia and experienced stroke in the past 5.4–14.8 months (N = 47, Mini-Mental Screening Examination, MMSE range 18–30), compared with a normal control group with 44 age and gender-matched healthy volunteers (MMSE range 26–30). Region-wise connectivity was derived from fiber connection density of 90 different cortical and subcortical parcellations across the whole brain. Both normal controls and patients with chronic stroke exhibited efficient small-world properties in their WM structural networks. Compared with normal controls, topological efficiency was basically unaltered in the patients with chronic stroke, as reflected by unchanged local and global clustering coefficient, characteristic path length, and regional efficiency. No significant difference in hub distribution was found between normal control and patient groups. Patients with chronic stroke, however, were found to have reduced betweenness centrality and predominantly located in the orbitofrontal cortex, whereas increased betweenness centrality and vulnerability were observed in parietal-occipital cortex. The National Institutes of Health Stroke Scale (NIHSS) score of patient is correlated with the betweenness centrality of right pallidum and local clustering coefficient of left superior occipital gyrus. Our findings suggest that patients with chronic stroke still exhibit efficient small-world organization and unaltered topological efficiency, with altered topology at orbitofrontal cortex and parietal-occipital cortex in the overall structural network. Findings from this study could help in understanding the mechanism of cognitive impairment and functional compensation occurred in patients with chronic stroke.