The Student's-t mixture model, which is heavily tailed and more robust than the Gaussian mixture model, has recently received great attention on image processing. In this paper, we propose a robust non-rigid point set registration algorithm using the Student's-t mixture model. Specifically, first, we consider the alignment of two point sets as a probability density estimation problem and treat one point set as Student's-t mixture model centroids. Then, we fit the Student's-t mixture model centroids to the other point set which is treated as data. Finally, we get the closed-form solutions of registration parameters, leading to a computationally efficient registration algorithm. The proposed algorithm is especially effective for addressing the non-rigid point set registration problem when significant amounts of noise and outliers are present. Moreover, less registration parameters have to be set manually for our algorithm compared to the popular coherent points drift (CPD) algorithm. We have compared our algorithm with other state-of-the-art registration algorithms on both 2D and 3D data with noise and outliers, where our non-rigid registration algorithm showed accurate results and outperformed the other algorithms.

The neuroimaging-based computer-aided diagnosis for Parkinson's disease (PD) has attracted considerable attention in recent years, where the classifier plays a critical role. Random vector functional link network (RVFL) has shown its effectiveness for classification task, while its extended version, namely RVFL plus (RVFL+), integrates the additional privileged information (PI) about training samples in RVFL to help training a more effective classifier. On the other hand, it is still a popular way to adopt only a single neuroimaging modality for PD diagnosis in clinical practice. In this work, we construct a novel cascaded multi-column RVFL+ (cmcRVFL+) framework for the single-modal neuroimaging-based PD diagnosis without the additional neuroimaging modality as PI. Specifically, the predicted values of RVFL+ classifiers in the current layers are used as the PI for the following classifiers, and therefore, the PI features are self-generated without additional modality. Furthermore, only the multi-column RVFL+ classifiers in the last layer of cmcRVFL+ are finally ensembled to generate the predictive result in the test stage. The experimental results on both the transcranial sonography dataset and the magnetic resonance imaging dataset for PD show that the proposed cmcRVFL+ algorithm achieves superior performance to all the compared algorithms. It suggests that the proposed cmcRVFL+ has the potential to be flexibly applied to various single-modal imaging based CAD.

The classification of motor imagery-electroencephalogram(MI-EEG)based brain-computer interface(BCI)can be used to decode neurological activities, which has been widely applied in the control of external devices. However, two factors still hinder the improvement of classification accuracy and robustness, especially in multi-class tasks. First, existing algorithms are based on a single space (measuring or source space). They suffer from the holistic low spatial resolution of the measuring space or the locally high spatial resolution information accessed from the source space, failing to provide holistic and high-resolution representations. Second, the subject specificity is not sufficiently characterized, resulting in the loss of personalized intrinsic information. Therefore, we propose a cross-space convolutional neural network (CS-CNN) with customized characteristics for four-class MI-EEG classification. This algorithm uses the modified customized band common spatial patterns (CBCSP) and duplex mean-shift clustering (DMSClustering) to express the specific rhythms and source distribution information in cross-space. At the same time, multi-view features from the time, frequency and space domains are extracted, connecting with CNN to fuse the characteristics from two spaces and classify them. MI-EEG was collected from 20 subjects. Lastly, the classification accuracy of the proposed is 96.05% with real MRI information and 94.79% without MRI in the private dataset. And the results in the BCI competition IV-2a show that CS-CNN outperforms the state-of-the-art algorithms, achieving an accuracy improvement of 1.98%, and a standard deviation reduction of 5.15%.