SACNet: Shuffling atrous convolutional U‐Net for medical image segmentation

Medical images exhibit multi‐granularity and high obscurity along boundaries. As representative work, the U‐Net and its variants exhibit two shortcomings on medical image segmentation: (a) they expand the range of reception fields by applying addition or concatenate operators to features with different reception fields, which disrupts the distribution of the essential feature of objects; (b) they utilize the downsampling or atrous convolution to characterize multi‐granular features of objects, which can obtain a large range of reception fields but leads to blur boundaries of objects. A Shuffling Atrous Convolutional U‐Net (SACNet) for circumventing those issues is proposed. The significant component of SACNet is the Shuffling Atrous Convolution (SAC) module, which fuses different atrous convolutional layers together by using a shuffle concatenate operation, so that the features from the same channel (which correspond to the same attribute of objects) are merged together. Besides the SAC modules, SACNet utilizes an EP module during the fine and medium levels to enhance the boundaries of objects, and utilizes a Transformer module during the coarse level to capture an overall correlation of pixels. Experiments on three medical image segmentation tasks: abdominal organ, cardiac, and skin lesion segmentation demonstrate that, SACNet outperforms several state‐of‐the‐art methods and facilitates easy transplant to other semantic segmentation tasks. We propose a Shuffling Atrous Convolutional U‐Net (SACNet) for medical image segmentation. SACNet utilizes a fine‐medium‐coarse U‐Net architecture. Both the fine level and medium level consist of a shuffling atrous convolution module and an edge‐preserving module, which are organized parallel and fused by a residual block.