This research discussed a deep learning method based on an improved generative adversarial network to segment the hippocampus. Different convolutional configurations were proposed to capture information obtained by a segmentation network. In addition, a generative adversarial network based on Pixel2Pixel was proposed. The generator was a codec structure combining a residual network and an attention mechanism to capture detailed information. The discriminator used a convolutional neural network to discriminate the segmentation results of the generated model and that of the expert. Through the continuously transmitted losses of the generator and discriminator, the generator reached the optimal state of hippocampus segmentation. T1-weighted magnetic resonance imaging scans and related hippocampus labels of 130 healthy subjects from the Alzheimer’s disease Neuroimaging Initiative dataset were used as training and test data; similarity coefficient, sensitivity, and positive predictive value were used as evaluation indicators. Results showed that the network model could achieve an efficient automatic segmentation of the hippocampus and thus has practical relevance for the correct diagnosis of diseases, such as Alzheimer’s disease.

It remains a challenging task to segment images that are distorted by noise and intensity inhomogeneity. To overcome these problems, in this paper, we present a novel region-based active contour model based on local intensity information and a kernel metric. By introducing intensity information about the local region, the proposed model can accurately segment images with intensity inhomogeneity. To enhance the model’s robustness to noise and outliers, we introduce a kernel metric as its objective functional. To more accurately detect boundaries, we apply convex optimization to this new model, which uses a weighted total-variation norm given by an edge indicator function. Lastly, we use the split Bregman iteration method to obtain the numerical solution. We conducted an extensive series of experiments on both synthetic and real images to evaluate our proposed method, and the results demonstrate significant improvements in terms of efficiency and accuracy, compared with the performance of currently popular methods.

Link prediction attempts to estimate the likelihood of the existence of links between nodes based on available brain network information, such as node attributes and observed links. In response to the problem of the poor efficiency of general link prediction methods applied to brain networks, this paper proposes a hierarchical random graph model based on maximum likelihood estimation. This algorithm uses brain network data to create a hierarchical random graph model. Then, it samples the space of all possible dendrograms using a Markov-chain Monte Carlo algorithm. Finally, it calculates the average connection probability. It also employs an evaluation index. Comparing link prediction in a brain network with link prediction in three different networks (Treponemapallidum metabolic network, terrorist networks, and grassland species food webs) using the hierarchical random graph model, experimental results show that the algorithm applied to the brain network has the highest prediction accuracy in terms of AUC scores. With the increase of network scale, AUC scores of the brain network reach 0.8 before gradually leveling off. In addition, the results show AUC scores of various algorithms computed in networks of eight different scales in 28 normal people. They show that the HRG algorithm is far better than random prediction and the ACT global index, and slightly inferior to local indexes CN and LP. Although the HRG algorithm does not produce the best results, its forecast effect is obvious, and shows good time complexity.