MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation
This work addresses medical image segmentation, which is crucial for healthcare applications, but it is incremental as it builds upon existing hybrid vision transformer approaches.
The authors tackled the problem of medical image segmentation by proposing MaxViT-UNet, a hybrid CNN-Transformer model that integrates multi-axis attention to enhance discrimination between object and background regions, achieving improved segmentation efficiency as demonstrated on MoNuSeg18 and MoNuSAC20 datasets.
Since their emergence, Convolutional Neural Networks (CNNs) have made significant strides in medical image analysis. However, the local nature of the convolution operator may pose a limitation for capturing global and long-range interactions in CNNs. Recently, Transformers have gained popularity in the computer vision community and also in medical image segmentation due to their ability to process global features effectively. The scalability issues of the self-attention mechanism and lack of the CNN-like inductive bias may have limited their adoption. Therefore, hybrid Vision transformers (CNN-Transformer), exploiting the advantages of both Convolution and Self-attention Mechanisms, have gained importance. In this work, we present MaxViT-UNet, a new Encoder-Decoder based UNet type hybrid vision transformer (CNN-Transformer) for medical image segmentation. The proposed Hybrid Decoder is designed to harness the power of both the convolution and self-attention mechanisms at each decoding stage with a nominal memory and computational burden. The inclusion of multi-axis self-attention, within each decoder stage, significantly enhances the discriminating capacity between the object and background regions, thereby helping in improving the segmentation efficiency. In the Hybrid Decoder, a new block is also proposed. The fusion process commences by integrating the upsampled lower-level decoder features, obtained through transpose convolution, with the skip-connection features derived from the hybrid encoder. Subsequently, the fused features undergo refinement through the utilization of a multi-axis attention mechanism. The proposed decoder block is repeated multiple times to segment the nuclei regions progressively. Experimental results on MoNuSeg18 and MoNuSAC20 datasets demonstrate the effectiveness of the proposed technique.