Brain tumor segmentation technology plays a pivotal role in the process of diagnosis and treatment of MRI brain tumors. It helps doctors to locate and measure tumors, as well as develop treatment and rehabilitation strategies. Recently, MRI brain tumor segmentation methods based on U-Net architecture have become popular as they largely improve the segmentation accuracy by applying skip connection to combine high-level feature information and low-level feature information. Meanwhile, researchers have demonstrated that introducing attention mechanism into U-Net can enhance local feature expression and improve the performance of medical image segmentation. In this work, we aim to explore the effectiveness of a recent attention module called attention gate for brain tumor segmentation task, and a novel Attention Gate Residual U-Net model, i.e., AGResU-Net, is further presented. AGResU-Net integrates residual modules and attention gates with a primeval and single U-Net architecture, in which a series of attention gate units are added into the skip connection for highlighting salient feature information while disambiguating irrelevant and noisy feature responses. AGResU-Net not only extracts abundant semantic information to enhance the ability of feature learning, but also pays attention to the information of small-scale brain tumors. We extensively evaluate attention gate units on three authoritative MRI brain tumor benchmarks, i.e., BraTS 2017, BraTS 2018 and BraTS 2019. Experimental results illuminate that models with attention gate units, i.e., Attention Gate U-Net (AGU-Net) and AGResU-Net, outperform their baselines of U-Net and ResU-Net, respectively. In addition, AGResU-Net achieves competitive performance than the representative brain tumor segmentation methods.

Automatic segmentation of brain tumors from magnetic resonance imaging (MRI) is a challenging task due to the uneven, irregular and unstructured size and shape of tumors. Recently, brain tumor segmentation methods based on the symmetric U-Net architecture have achieved favorable performance. Meanwhile, the effectiveness of enhancing local responses for feature extraction and restoration has also been shown in recent works, which may encourage the better performance of the brain tumor segmentation problem. Inspired by this, we try to introduce the attention mechanism into the existing U-Net architecture to explore the effects of local important responses on this task. More specifically, we propose an end-to-end 2D brain tumor segmentation network, i.e., attention residual U-Net (AResU-Net), which simultaneously embeds attention mechanism and residual units into U-Net for the further performance improvement of brain tumor segmentation. AResU-Net adds a series of attention units among corresponding down-sampling and up-sampling processes, and it adaptively rescales features to effectively enhance local responses of down-sampling residual features utilized for the feature recovery of the following up-sampling process. We extensively evaluate AResU-Net on two MRI brain tumor segmentation benchmarks of BraTS 2017 and BraTS 2018 datasets. Experiment results illustrate that the proposed AResU-Net outperforms its baselines and achieves comparable performance with typical brain tumor segmentation methods.

This article investigates an output consensus control problem for heterogeneous multi-agent systems with switching disconnected networks. As compared to similar works, each follower can measure only part information of the leader’s output in this paper, which lightens the measurement burden of simple agents when the dimension of leader’s output is large-scaled. In this case, due to the coexistence of incomplete measurements of leader’s output and disconnected networks, the outputs of some agents can deviate from the leader though there exists the observer-based control on them. In order to overcome this difficulty, we utilize the theory of switching unstable systems and propose a novel segmented time unit method. With the aid of this method, the switching intervals are segmented into some time units. Then by analyzing the cooperative control rule within the time units, the stabilizing characteristics of switching behaviors can be obtained to offset the divergence during the switching intervals. On this basis, a novel segmented time-varying Lyapunov function is developed to analyze the error states and sufficient criteria for the output consensus are derived. At last, a numerical simulation is shown to verify the theoretical results. Note to Practitioners —Most existing works on switching disconnected networks require that the leader (or the exosystem) is critically stable (or stable). However, unstable high-dimensional leader widely exists in the fields of multi-agent systems, such as the formation control of MASs where the agents are affine functions of time. On this account, this paper studies multi-agent systems with unstable high-dimensional leader under switching disconnected networks. To solve this problem, a novel segmented time unit method is proposed in this paper to study multi-agent systems with switching disconnected networks and incomplete leader measurement. Based on the segmented time unit approach, the observer-based control protocols and switching signals are given to realize the overall consensus. Numerical simulations suggest that this approach is feasible but it has not been tested in production. Future works will consider the formation control problem with switching disconnected networks and incomplete leader measurement.

Background: The main causes of lung cancer are smoking, environmental pollution and genetic susceptibility. It is an indisputable fact that PAHs are related to lung cancer, and benzo(a) pyrene is a representative of PAHs. The purpose of the current investigation was to investigate the interaction between AhR and HIF-1 signaling pathways in A549 cells, which provide some experimental basis for scientists to find drugs that block AhR and HIF-1 signaling pathway to prevent and treat cancer. Methods: This project adopts the CYP1A1 signaling pathways and the expression of CYP1B1 is expressed as a measure of AhR strength index. The expression of VEGF and CAIX volume as a measure of the strength of the signal path HIF-1 indicators. Through the construction of plasmid vector, fluorescence resonance energy transfer, real-time quantitative PCR, western blotting and immunoprecipitation, the interaction between AhR signaling pathway and HIF-1 signaling pathway was observed. Results: BaP can enhance the binding ability of HIF-1α protein to HIF-1β/ARNT in a dose-dependent manner without CoCl₂. However, the binding ability of AhR protein to HIF-1β/ARNT is inhibited by HIF-1α signaling pathway in a dose-dependent manner with CoCl₂. Conclusion: It is shown that activation of the AhR signaling pathway does not inhibit the HIF-1α signaling pathway, but activation of the HIF-1α signaling pathway inhibits the AhR signaling pathway.

The precise segmentation of tumor regions plays a pivotal role in the diagnosis and treatment of brain tumors. However, due to the variable location, size, and shape of brain tumors, the automatic segmentation of brain tumors is a relatively challenging application. Recently, U-Net related methods, which largely improve the segmentation accuracy of brain tumors, have become the mainstream of this task. Following merits of the 3D U-Net architecture, this work constructs a novel 3D U-Net model called SGEResU-Net to segment brain tumors. SGEResU-Net simultaneously embeds residual blocks and spatial group-wise enhance (SGE) attention blocks into a single 3D U-Net architecture, in which SGE attention blocks are employed to enhance the feature learning of semantic regions and reduce possible noise and interference with almost no extra parameters. Besides, the self-ensemble module is also utilized to improve the segmentation accuracy of brain tumors. Evaluation experiments on the Brain Tumor Segmentation (BraTS) Challenge 2020 and 2021 benchmarks demonstrate the effectiveness of the proposed SGEResU-Net for this medical application. Moreover, it achieves DSC values of 83.31, 91.64 and 86.85%, as well as Hausdorff distances (95%) of 19.278, 5.945 and 7.567 for the enhancing tumor, whole tumor, and tumor core on BraTS 2021 dataset, respectively.