Spatial resolution is a critical imaging parameter in magnetic resonance imaging (MRI). The image super-resolution (SR) is an effective and cost efficient alternative technique to improve the spatial resolution of MR images. Over the past several years, the convolutional neural networks (CNN)-based SR methods have achieved state-of-the-art performance. However, CNNs with very deep network structures usually suffer from the problems of degradation and diminishing feature reuse, which add difficulty to network training and degenerate the transmission capability of details for SR. To address these problems, in this work, a progressive wide residual network with a fixed skip connection (named FSCWRN) based SR algorithm is proposed to reconstruct MR images, which combines the global residual learning and the shallow network based local residual learning. The strategy of progressive wide networks is adopted to replace deeper networks, which can partially relax the abovementioned problems, while a fixed skip connection helps provide rich local details at high frequencies from a fixed shallow layer network to subsequent networks. The experimental results on one simulated MR image database and three real MR image databases show the effectiveness of the proposed FSCWRN SR algorithm, which achieves improved reconstruction performance compared with 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 main goal of this study is to build an artificial intelligence (AI) architecture for automated extraction of dual-modal image features from both shear-wave elastography (SWE) and B-mode ultrasound, and to evaluate the AI architecture for classification between benign and malignant breast tumors. In this AI architecture, ultrasound images were segmented by the reaction diffusion level set model combined with the Gabor-based anisotropic diffusion algorithm. Then morphological features and texture features were extracted from SWE and B-mode ultrasound images at the contourlet domain. Finally, we employed a framework for feature learning and classification with the deep polynomial network (DPN) on dual-modal features to distinguish between malignant and benign breast tumors. With the leave-one-out cross validation, the DPN method on dual-modal features achieved a sensitivity of 97.8%, a specificity of 94.1%, an accuracy of 95.6%, a Youden's index of 91.9% and an area under the receiver operating characteristic curve of 0.961, which was superior to the classic single-modal methods, and the dual-modal methods using the principal component analysis and multiple kernel learning. These results have demonstrated that the dual-modal AI-based technique with DPN has the potential for breast tumor classification in future clinical practice.