Transformers, the default model of choices in natural language processing, have drawn scant attention from the medical imaging community. Given the ability to exploit long-term dependencies, transformers are promising to help atypical convolutional neural networks (convnets) to overcome its inherent shortcomings of spatial inductive bias. However, most of recently proposed transformer-based segmentation approaches simply treated transformers as assisted modules to help encode global context into convolutional representations without investigating how to optimally combine self-attention (i.e., the core of transformers) with convolution. To address this issue, in this paper, we introduce nnFormer (i.e., not-another transFormer), a powerful segmentation model with an interleaved architecture based on empirical combination of self-attention and convolution. In practice, nnFormer learns volumetric representations from 3D local volumes. Compared to the naive voxel-level self-attention implementation, such volume-based operations help to reduce the computational complexity by approximate 98% and 99.5% on Synapse and ACDC datasets, respectively. In comparison to prior-art network configurations, nnFormer achieves tremendous improvements over previous transformer-based methods on two commonly used datasets Synapse and ACDC. For instance, nnFormer outperforms Swin-UNet by over 7 percents on Synapse. Even when compared to nnUNet, currently the best performing fully-convolutional medical segmentation network, nnFormer still provides slightly better performance on Synapse and ACDC. Codes and models are available at https://github.com/282857341/nnFormer.

No abstract

No abstract

No abstract

The combination of III–V compound semiconductor materials and organic semiconductor materials to construct hybrid solar cells is a potential pathway to resolve the problems of conventional doped p–n junction solar cells, such as complexities in fabrication process and high costs. This review presents the recent progress of organic–inorganic hybrid solar cells based on polymers and III–V semiconductors, from materials to devices. The available growth process for planar/nanostructured III–V semiconductor materials, along with patterning and etching processes for nanostructured materials, are reviewed. As an emphasis of this review, advanced device structure designs are reviewed for facilitation of carrier collection and high efficiency, at planar structure level and nanowire structure level, respectively. Optimization pathways for efficiency enhancement are discussed with respect to polymer layers and surface/interface passivation, respectively. Finally, perspectives on the future development of such hybrid cells are presented.