TransAttUnet: Multi-Level Attention-Guided U-Net With Transformer for Medical Image Segmentation

Accurate segmentation of organs or lesions from medical images is crucial for reliable diagnosis of diseases and organ morphometry. In recent years, convolutional encoder-decoder solutions have achieved substantial progress in the field of automatic medical image segmentation. Due to the inherent bias in the convolution operations, prior models mainly focus on local visual cues formed by the neighboring pixels, but fail to fully model the long-range contextual dependencies. In this article, we propose a novel Transformer-based Attention Guided Network called TransAttUnet, in which the multi-level guided attention and multi-scale skip connection are designed to jointly enhance the performance of the semantical segmentation architecture. Inspired by Transformer, the self-aware attention (SAA) module with Transformer Self Attention (TSA) and Global Spatial Attention (GSA) is incorporated into TransAttUnet to effectively learn the non-local interactions among encoder features. Moreover, we also use additional multi-scale skip connections between decoder blocks to aggregate the upsampled features with different semantic scales. In this way, the representation ability of multi-scale context information is strengthened to generate discriminative features. Benefitting from these complementary components, the proposed TransAttUnet can effectively alleviate the loss of fine details caused by the stacking of convolution layers and the consecutive sampling operations, finally improving the segmentation quality of medical images. Extensive experiments were conducted on multiple medical image segmentation datasets from various imaging modalities, which demonstrate that the proposed method consistently outperforms the existing state-of-the-art methods.

I. Introduction

In Clinical diagnosis, the core of medical image segmentation is to delineate the objects of interest from the complex background on various biomedical images [1], [2], [3], such as X-ray, Computerized Tomography (CT), Magnetic Resonance Imaging (MRI), and Ultrasound. It is useful for quantitative diagnosis and morphological analysis of specific lesions in human organs and tissues. As shown in Fig. 1, it requires enormous effort and patience to handle the complex contours and textures. However, traditional manual annotation heavily relies on clinical experiences. Measurements based on manual annotations by clinicians might be highly accurate, but they can also be labor-intensive under typical clinical settings. Therefore, it is in great demand to develop accurate medical image segmentation methods.