In recent years, researchers have introduced various methods in many domains into medical image processing so that its effectiveness and efficiency can be improved to some extent. The applications of generative adversarial networks (GAN) in medical image processing are evolving very fast. In this paper, the state of the art in this area has been reviewed. Firstly, the basic concepts of the GAN were introduced. And then, from the perspectives of the medical image denoising, detection, segmentation, synthesis, reconstruction and classification, the applications of the GAN were summarized. Finally, prospects for further research in this area were presented.
Alzheimer's disease (AD) is a typical neurodegenerative disease, which is clinically manifested as amnesia, loss of language ability and self-care ability, and so on. So far, the cause of the disease has still been unclear and the course of the disease is irreversible, and there has been no cure for the disease yet. Hence, early prognosis of AD is important for the development of new drugs and measures to slow the progression of the disease. Mild cognitive impairment (MCI) is a state between AD and healthy controls (HC). Studies have shown that patients with MCI are more likely to develop AD than those without MCI. Therefore, accurate screening of MCI patients has become one of the research hotspots of early prognosis of AD. With the rapid development of neuroimaging techniques and deep learning, more and more researchers employ deep learning methods to analyze brain neuroimaging images, such as magnetic resonance imaging (MRI), for early prognosis of AD. Hence, in this paper, a three-dimensional multi-slice classifiers ensemble based on convolutional neural network (CNN) and ensemble learning for early prognosis of AD has been proposed. Compared with the CNN classification model based on a single slice, the proposed classifiers ensemble based on multiple two-dimensional slices from three dimensions could use more effective information contained in MRI to improve classification accuracy and stability in a parallel computing mode.
Exoskeleton nursing robot is a typical human-machine co-drive system. To full play the subjective control and action orientation of human, it is necessary to comprehensively analyze exoskeleton wearer’s surface electromyography (EMG) in the process of moving patients, especially identifying the spatial distribution and internal relationship of the EMG information. Aiming at the location of electrodes and internal relation between EMG channels, the complex muscle system at the upper limb was abstracted as a muscle functional network. Firstly, the correlation characteristics were analyzed among EMG channels of the upper limb using the mutual information method, so that the muscle function network was established. Secondly, by calculating the characteristic index of network node, the features of muscle function network were analyzed for different movements. Finally, the node contraction method was applied to determine the key muscle group that reflected the intention of wearer’s movement, and the characteristics of muscle function network were analyzed in each stage of moving patients. Experimental results showed that the location of the myoelectric collection could be determined quickly and efficiently, and also various stages of the moving process could effectively be distinguished using the muscle functional network with the key muscle groups. This study provides new ideas and methods to decode the relationship between neural controls of upper limb and physical motion.