Search

For significant memory concern (SMC) and mild cognitive impairment (MCI), their classification performance is limited by confounding features, diverse imaging protocols, and limited sample size. To address the above limitations, we introduce a dual-modality fused brain connectivity network combining resting-state functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI), and propose three mechanisms in the current graph convolutional network (GCN) to improve classifier performance. First, we introduce a DTI-strength penalty term for constructing functional connectivity networks. Stronger structural connectivity and bigger structural strength diversity between groups provide a higher opportunity for retaining connectivity information. Second, a multi-center attention graph with each node representing a subject is proposed to consider the influence of data source, gender, acquisition equipment, and disease status of those training samples in GCN. The attention mechanism captures their different impacts on edge weights. Third, we propose a multi-channel mechanism to improve filter performance, assigning different filters to features based on feature statistics. Applying those nodes with low-quality features to perform convolution would also deteriorate filter performance. Therefore, we further propose a pooling mechanism, which introduces the disease status information of those training samples to evaluate the quality of nodes. Finally, we obtain the final classification results by inputting the multi-center attention graph into the multi-channel pooling GCN. The proposed method is tested on three datasets (i.e., an ADNI 2 dataset, an ADNI 3 dataset, and an in-house dataset). Experimental results indicate that the proposed method is effective and superior to other related algorithms, with a mean classification accuracy of 93.05% in our binary classification tasks. Our code is available at: https://github.com/Xuegang-S.

The risk of osteoporotic fracture is inversely related to bone mineral density (BMD), but how spatial BMD pattern influences fracture risk remains incompletely understood. This study used a pixel-level spatiotemporal atlas of proximal femoral BMD in 13,338 white European women (age 20-97 years) to quantitate age-related texture variation in BMD maps and generate a "reference" map of bone aging. We introduce a new index, called Densitometric Bone Age (DBA), as the age at which an individual site-specific BMD map (the proximal femur is studied here) best matches the median aging trajectory at that site in terms of the root mean squared error (RMSE). The ability of DBA to predict incident hip fracture and hip fracture pattern over 5 years following baseline BMD was compared against conventional region-based BMD analysis in a subset of 11,899 women (age 45-97 years), for which follow-up fracture records exist. There were 208 subsequent incident hip fractures in the study populations (138 femoral necks [FNs], 52 trochanteric [TR], 18 sites unspecified). DBA had modestly better performance compared to the conventional FN-BMD, TR-BMD, and total hip (TOT)-BMD in identifying hip fractures measured as the area under the curve (AUC) using receiver operating characteristics (ROC) curve analysis by 2% (95% confidence interval [CI], -0.5% to 3.5%), 3% (95% CI, 1.0% to 4.0%), and 1% (95% CI, 0.4% to 1.6%), respectively. Compared to FN-BMD T-score, DBA improved the ROC-AUC for predicting TR fractures by ~5% (95% CI, 1.1% to 9.8%) with similar performance in identifying FN fractures. Compared to TR-BMD T-score, DBA improved the ROC-AUC for the prediction of FN fractures by ~3% (95% CI, 1.1% to 4.9%), with similar performance in identifying TR fractures. Our findings suggest that DBA may provide a spatially sensitive measure of proximal femoral fragility that is not captured by FN-BMD or TR-BMD alone. © 2022 The Authors. Journal of Bone and Mineral Research published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research (ASBMR). ispartof: JOURNAL OF BONE AND MINERAL RESEARCH vol:37 issue:9 pages:1679-1688 ispartof: location:United States status: published