The resolution of feature maps is a critical factor for accurate medical image segmentation. Most of the existing Transformer-based networks for medical image segmentation adopt a U-Net-like architecture, which contains an encoder that converts the high-resolution input image into low-resolution feature maps using a sequence of Transformer blocks and a decoder that gradually generates high-resolution representations from low-resolution feature maps. However, the procedure of recovering high-resolution representations from low-resolution representations may harm the spatial precision of the generated segmentation masks. Unlike previous studies, in this study, we utilized the high-resolution network (HRNet) design style by replacing the convolutional layers with Transformer blocks, continuously exchanging feature map information with different resolutions generated by the Transformer blocks. The proposed Transformer-based network is named the high-resolution Swin Transformer network (HRSTNet). Extensive experiments demonstrated that the HRSTNet can achieve performance comparable with that of the state-of-the-art Transformer-based U-Net-like architecture on the 2021 Brain Tumor Segmentation dataset, the Medical Segmentation Decathlon’s liver dataset, and the BTCV multi-organ segmentation dataset.

Ion mobility spectrometer (IMS) is a powerful chemical composition analysis tool working at atmospheric pressure that can be used to separate complex samples and study molecular structures. Resolution is a key parameter for evaluating the performance of IMS. However, for the pulsed sampling technique used by drift tube IMS, there is an upper limit to the resolution due to the diffusion between ions and the drift gas. In this work, an inverse diffusion counterbalance method is proposed to break the resolution limit. The method is inspired by the stimulated emission depletion (STED). In optical microscopy systems, STED is used to break the optical diffraction limit by a ring of depleted light to counteract diffraction effects of the excited light. We modified this strategy and applied it to an IMS system for counteracting the diffusion effect of the pulsed ion packet. The method can increase the resolution up to 1.55 times through theoretical analysis, and the improvement is verified by simulations. The simulation results find that the initial width of the ion packet has an influence on the effectiveness of the method, and the narrower the initial width, the better the effect. The proposed inverse counterbalance strategy may also be applied to other spectral analysis instruments to break the resolution limit.