No abstract

Due to the high heterogeneity of brain tumors, automatic segmentation of brain tumors remains a challenging task. In this paper, we propose RDAU-Net by adding dilated feature pyramid blocks with 3D CBAM blocks and inserting 3D CBAM blocks after skip-connection layers. Moreover, a CBAM with channel attention and spatial attention facilitates the combination of more expressive feature information, thereby leading to more efficient extraction of contextual information from images of various scales. The performance was evaluated on the Multimodal Brain Tumor Segmentation (BraTS) challenge data. Experimental results show that RDAU-Net achieves state-of-the-art performance. The Dice coefficient for WT on the BraTS 2019 dataset exceeded the baseline value by 9.2%.

With the development of rocket and aerospace technology in recent decades, people have put forward higher requirements on the heat resistance and ablation performance of thermal protection materials. In this paper, zirconia fibre hybrid alumina fibre/boron phenolic (ZA/ BPF) ceramifiable composites, based on ceramic fillers of MgO, Al 2 O 3 , SiC and mica-modified boron phenolic resin matrix, were prepared with different hybrid fibre contents (5, 10, 15, 20, 25, 30 wt-%) by hot compression moulding. The result shows that fibre contents have little effect on the ablation resistance of composite materials which all have a low linear ablation rate below 0. 01 mm s −1 . When the fiber content is 25%, the ZA/BPF composite reaches the highest bending strength 48. 86 MPa and 15. 57 MPa before and after sintering respectively. It is showed by the SEM results that too high and too low fibre content would both lead to poor bonding between resin and fibre interfaces.

No abstract

No abstract