In a recent article [Commun. Theor. Phys. (Beijing, China) 43 (2005) 39], Xie et al. improved the extended tanh function method by introducing a generalized Riccati equation and its new solutions. Then they choose the Karamoto–Sivashinsky (KS) equation to illustrate their approach and obtain many exact solutions of the KS equation. So they claim that, by using their method, one not only can successfully recover the previously known formal solutions but also construct new and more general formal solutions for some nonlinear evolution equations. In this comment, we will show that the claim is incorrect.

Semi-supervised medical image segmentation (SSMIS)is a research hotspot.However,existing consistency regular-ization methods do not adequately consider the robustness gains obtained by the model overcoming perturbations in the network structure and the spatial context. To address this problem, we propose a regional consistency strategy for SSMIS. Specifically, we construct network structure perturbations by making the two networks use different downsampling strategies. As for spatial contextual perturbations, we perform two random crops for each 3D medical image and feed different sub-image to different networks. We introduce entropy minimization to encourage both networks to produce consistent, high-confidence predictions for intersecting regions. A weighted combination of supervised and unsupervised losses optimizes the networks. We conducted extensive experiments on two datasets, and the results show that introducing network structure perturbations and spatial environmental perturbations can improve various metrics and demonstrate the effectiveness of our method