The CNN-based methods have achieved impressive results in medical image segmentation, but it failed to capture the long-range dependencies due to the inherent locality of convolution operation. Transformer-based methods are popular in vision tasks recently because of its capacity of long-range dependencies and get a promising performance. However, it lacks in modeling local context, although some works attempted to embed convolutional layer to overcome this problem and achieved some improvement, but it makes the feature inconsistent and fails to leverage the natural multi-scale features of hierarchical transformer, which limit the performance of models. In this paper, taking medical image segmentation as an example, we present MISSFormer, an effective and powerful Medical Image Segmentation tranSFormer. MISSFormer is a hierarchical encoder-decoder network and has two appealing designs: 1) A feed forward network is redesigned with the proposed Enhanced Transformer Block, which makes features aligned adaptively and enhances the long-range dependencies and local context. 2) We proposed Enhanced Transformer Context Bridge, a context bridge with the enhanced transformer block to model the long-range dependencies and local context of multi-scale features generated by our hierarchical transformer encoder. Driven by these two designs, the MISSFormer shows strong capacity to capture more valuable dependencies and context in medical image segmentation. The experiments on multi-organ and cardiac segmentation tasks demonstrate the superiority, effectiveness and robustness of our MISSFormer, the exprimental results of MISSFormer trained from scratch even outperforms state-of-the-art methods pretrained on ImageNet, and the core designs can be generalized to other visual segmentation tasks. The code will be released in Github.

No abstract

No abstract

A horizontally aligned GaAs p–i–n nanowire array solar cell is proposed and studied via coupled three-dimensional optoelectronic simulations. Benefiting from light-concentrating and light-trapping properties, the horizontal nanowire array yields a remarkable efficiency of 10.8% with a radius of 90 nm and a period of 5 radius, more than twice that of its thin-film counterpart with the same thickness. To further enhance the absorption, the nanowire array is placed on a low-refractive-index MgF2 substrate and capsulated in SiO2, which enables multiple reflection and reabsorption of light due to the refractive index difference between air/SiO2 and SiO2/MgF2. The absorption-enhancement structure increases the absorption over a broad wavelength range, resulting in a maximum conversion efficiency of 18%, 3.7 times higher than that of the thin-film counterpart, which is 3 times larger in GaAs material volume. This work may pave the way for the development of ultra-thin high-efficiency solar cells with very low material cost.

Telemedicine over Internet of Things (IoT) generates an unprecedented amount of data, which further requires transmission, analysis, and storage. Deploying cloud computing to handle data of this magnitude will introduce unacceptable data analysis latency and high storage costs. Thus, mobile edge computing (MEC) deployed between the cloud and users, which is close to the nodes of data generation, can tackle these problems in 5G scenarios with the help of artificial intelligence. This paper proposes a telemedicine system based on MEC and artificial intelligence for remote health monitoring and automatic disease diagnosis. The integration of different technologies such as computers, medicine, and telecommunications will significantly improve the efficiency of patient treatment and reduce the cost of health care.