No abstract

No abstract

We propose a new method name LSA that achieves dynamic alignment of local features by setting sliding windows for their local stripes• LSA can effectively suppress spatially misalignment and the noises from unshared regions.• LSA does not require the additional auxiliary pose information.• We design a Global-Local Dynamic Feature Alignment Network (GLDFA-Net) framework, which contains two branches, global and local.• LSA is introduced into the local branch of GLDFA-Net to guide the computation of the distance metric.

In this paper, we are interested in exploring the problem of full-resolution image segmentation, with the focus placed on learning full-resolution representations for biomedicine images. We divide the original resolution image into patches of different sizes in different stages and then extracte local features from large to small patches using efficient and flexible components in modern convolutional neural networks (CNN). Meanwhile, a multilayer perceptron (MLP) block intended for modeling long-range dependencies between patches is designed to compensate for the inherent inductive bias caused by convolution operations. In addition, we perform multiscale fusion and receive representation information from parallel paths at each stage, resulting in a rich full-resolution representation. We evaluate the proposed method on different biomedical image segmentation tasks and it achieves a competitive performance compared to the latest deep learning segmentation methods. It is hoped that this method will serve as a useful alternative to biomedical image segmentation and provide an improved idea for the research based on full-resolution representation.