BackgroundTo explore patterns of brain structural alteration in chronic obstructive pulmonary disease (COPD) patients with different levels of lung function impairment and the associations of those patterns with cognitive functional deficits using voxel-based morphometry (VBM) and tract-based spatial statistics (TBSS) analyses based on high-resolution structural MRI and diffusion tensor imaging (DTI).MethodsA total of 115 right-handed participants (26 severe, 29 moderate, and 29 mild COPD patients and a comparison group of 31 individuals without COPD) completed tests of cognitive (Montreal Cognitive Assessment [MoCA]) and pulmonary function (forced expiratory volume in 1 s [FEV1]) and underwent MRI scanning. VBM and TBSS analyses were used to identify changes in grey matter density (GMD) and white matter (WM) integrity in COPD patients. In addition, correlation analyses between these imaging parameter changes and cognitive and pulmonary functional impairments were performed.ResultsThere was no significant difference in brain structure between the comparison groups and the mild COPD patients. Patients with moderate COPD had atrophy of the left middle frontal gyrus and right opercular part/triangular part of the inferior frontal gyrus, and WM changes were present mainly in the superior and posterior corona radiata, corpus callosum and cingulum. Patients with severe COPD exhibited the most extensive changes in GMD and WM. Some grey matter (GM) and WM changes were correlated with MoCA scores and FEV1.ConclusionsThese findings suggest that patients with COPD exhibit progressive structural impairments in both the GM and the WM, along with impaired levels of lung function, highlighting the importance of early clinical interventions.

DTI may play a significant role in diagnosing and predicting the development of CSM. These slides can be retrieved under Electronic Supplementary Material.

No abstract

Background and objectivesCognitive impairment is a common extrapulmonary comorbidity in COPD patients. The default mode network (DMN) plays a critical role in maintaining the normal activities of humans, and its function can be evaluated by resting state functional magnetic resonance imaging. The aim of this study was to investigate the correlations between cognition and function changes of the DMN in COPD patients.MethodsOne hundred and thirteen eligible participants including 30 control subjects and 83 COPD patients matched for demographic characteristics were recruited. All participants performed cognitive function tests and underwent resting state functional magnetic resonance imaging.ResultsThe total cognitive function scores of COPD patients were significantly different from those of control subjects (P<0.05) and worsened with the degree of airflow obstruction. The activated brain regions in the DMN of COPD patients were less than those of normal controls. Six activated brain regions in the DMN were found to develop significantly different functional connectivity (FC) values among the subjects. Meanwhile, the FC values of the left posterior cingulate cortex and left hippocampus correlated well with cognitive functions and pulmonary function.ConclusionCOPD patients have cognitive impairments that correlate well with disease severity. FC changes in activated brain regions in the DMN may predict cognitive impairment, and the left posterior cingulate cortex and left hippocampus may be important brain regions related to cognitive impairment in COPD patients.

No abstract

No abstract

Medical image segmentation is one of the key technologies in computer aided diagnosis. Due to the complexity and diversity of medical images, the wavelet multi-scale analysis is introduced into GVF (gradient vector flow) snake model. The modulus values of each scale and phase angle values are calculated using wavelet transform, and the local maximum points of modulus values, which are the contours of the object edges, are obtained along phase angle direction at each scale. Then, location of the edges of the object and segmentation is implemented by GVF snake model. The experiments on some medical images show that the improved algorithm has small amount of computation, fast convergence and good robustness to noise.

There exists a large number of datasets for organ segmentation, which are partially annotated and sequentially constructed. A typical dataset is constructed at a certain time by curating medical images and annotating the organs of interest. In other words, new datasets with annotations of new organ categories are built over time. To unleash the potential behind these partially labeled, sequentially-constructed datasets, we propose to incrementally learn a multi-organ segmentation model. In each incremental learning (IL) stage, we lose the access to previous data and annotations, whose knowledge is assumingly captured by the current model, and gain the access to a new dataset with annotations of new organ categories, from which we learn to update the organ segmentation model to include the new organs. While IL is notorious for its 'catastrophic forgetting' weakness in the context of natural image analysis, we experimentally discover that such a weakness mostly disappears for CT multi-organ segmentation. To further stabilize the model performance across the IL stages, we introduce a light memory module and some loss functions to restrain the representation of different categories in feature space, aggregating feature representation of the same class and separating feature representation of different classes. Extensive experiments on five open-sourced datasets are conducted to illustrate the effectiveness of our method.