Hippocampus Segmentation Method Based on Subspace Patch-Sparsity Clustering in Noisy Brain MRI

Since the hippocampus is of small size, low contrast, and irregular shape, a novel hippocampus segmentation method based on subspace patch-sparsity clustering in brain MRI is proposed to improve the segmentation accuracy, which requires that the representation coefficients in different subspaces should be as sparse as possible, while the representation coefficients in the same subspace should be as average as possible. By restraining the coefficient matrix with the patch-sparse constraint, the coefficient matrix contains a patch-sparse structure, which is helpful to the hippocampus segmentation. The experimental results show that our proposed method is effective in the noisy brain MRI data, which can well deal with hippocampus segmentation problem.

Sparse Representation for Cardiac Electrical Activity Imaging in Magnetocardiography

Signal sparsity has been widely discussed in communication system, cloud computing, multimedia processing and computational biology. Reconstructing the sparsely distributed current sources of the heart by means of non-invasive magnetocardiography (MCG) measurement and various optimization methods provides a new way to solve the inverse problem of the cardiac magnetic field. The problem of sparse source location of MCG is in the time series of MCG measurement caused by active sparse current source, can the spatiotemporal source be reconstructed accurately and effectively? For the above problem, the scientific contributions of the paper include: (1) A modified focal underdetermined system solver algorithm is proposed for a sparse solution, by combing with dynamic regularization factor and smoothed sparse constraint; (2) Lead field matrix is reduced by prior information of cardiac magnetic field map to reduce under-determination; (3) Spatiotemporal sources are reconstructed for non-invasive cardiac electrical activity imaging. The results of real MCG data demonstrate the effectiveness of this method for cardiac electrical activity imaging. The temporal and spatial changes of the current sources are similar to the depolarization and repolarization process of the ventricle.

Neighbor-Based Label Distribution Learning to Model Label Ambiguity for Aerial Scene Classification

Many aerial images with similar appearances have different but correlated scene labels, which causes the label ambiguity. Label distribution learning (LDL) can express label ambiguity by giving each sample a label distribution. Thus, a sample contributes to the learning of its ground-truth label as well as correlated labels, which improve data utilization. LDL has gained success in many fields, such as age estimation, in which label ambiguity can be easily modeled on the basis of the prior knowledge about local sample similarity and global label correlations. However, LDL has never been applied to scene classification, because there is no knowledge about the local similarity and label correlations and thus it is hard to model label ambiguity. In this paper, we uncover the sample neighbors that cause label ambiguity by jointly capturing the local similarity and label correlations and propose neighbor-based LDL (N-LDL) for aerial scene classification. We define a subspace learning problem, which formulates the neighboring relations as a coefficient matrix that is regularized by a sparse constraint and label correlations. The sparse constraint provides a few nearest neighbors, which captures local similarity. The label correlations are predefined according to the confusion matrices on validation sets. During subspace learning, the neighboring relations are encouraged to agree with the label correlations, which ensures that the uncovered neighbors have correlated labels. Finally, the label propagation among the neighbors forms the label distributions, which leads to label smoothing in terms of label ambiguity. The label distributions are used to train convolutional neural networks (CNNs). Experiments on the aerial image dataset (AID) and NWPU_RESISC45 (NR) datasets demonstrate that using the label distributions clearly improves the classification performance by assisting feature learning and mitigating over-fitting problems, and our method achieves state-of-the-art performance.