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.
Electromigration (EM) is an important reliability concern in ultralarge-scale integration interconnects. A refined EM model based on a driving force approach is proposed in this work. The distribution of atomic flux divergence is computed by an finite element method to predict the void nucleation site in interconnects. It is demonstrated that the proposed model is more accurate than the conventional counterpart for narrow interconnects. The validity of the proposed model is verified through the study of the reservoir effect in EM. The predicted critical reservoir length agrees well with the reported values.
Electromigration (EM) is a major failure mechanism in ultralarge-scale integration interconnections. Various atomic migration mechanisms due to the electron wind force, temperature gradients, and thermomechanical stress gradients are involved during an EM failure process. In this study, a methodology that combines a Monte Carlo algorithm and finite element analysis is developed to study the underlying dynamic physical processes of EM, including void nucleation and void growth. The microstructure inhomogeneity of an interconnect thin film and the different atomic diffusivities along various diffusion paths in interconnections are also considered in this three-dimensional dynamic simulation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.