Segmentation of Lung Lesions through Bilateral Learning Branches to Aggregating Contextual and Local Characteristics

Detecting and analyzing lung lesion regions using artificial intelligence is of great significance in the medical diagnosis of lung CT images, which can substantially improve the efficiency of doctors. However, segmentation of the inflammatory region in the CT image of the lung remains challenging due to the varied sizes, blurry local details, irregular shapes, and limited sizes of datasets. Faced with these challenges, this paper proposes a novel lung lesion segmentation network that incorporates two feature extraction branches to achieve a balance of speed and accuracy. We first design a context branch (CB) to preserve the scale-invariant global context information by the transformer-like module. Besides, a shallow detail branch (DB) based on a deep aggregation pyramid (DAP) module is designed to provide detailed information. Extensive experiments are conducted on two datasets, including the public COVID-19 dataset and a private dataset. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods. Moreover, the trade-off between accuracy and inference speed is achieved.