DPBET: A dual-path lung nodules segmentation model based on boundary enhancement and hybrid transformer. (December 2022)

• Record Type: Journal Article
• Authors: Wang, Sihui; Jiang, Ailian; Li, Xiaotian; Qiu, Yanfang; Li, Mengyang; Li, Feixiang
• Is Part Of: Computers in biology and medicine. Volume 151:Part B(2022)
• Publication Date: 2022-12
• Subjects: Lung nodules segmentation -- Boundary enhancement -- Convolutional neural networks -- Transformer -- Dual-path; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.106330
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Accurate segmentation of lung nodules is an important basis for the subsequent differentiation of benign and malignant pathological types, which is conducive to early detection of lung cancer. Due to the local feature extraction characteristics of convolution and the limited receptive field of continuous down-sampling, the existing deep convolutional neural networks (CNN) for lung nodules segmentation cause the loss of information of lesion boundaries and locations. To address this issue, a dual-path lung nodules segmentation model based on boundary enhancement and hybrid transformer (DPBET) is proposed in this paper. The model consists of a global path, an edge path, and a feature aggregation module. In the global path, a de-redundant transformer module with explicit guidance is proposed, called Cascade-Axial-Prune Transformer (CAP-Trans). It is combined with CNN to form a hybrid architecture to generate a global representation of the target lesion. In the edge path, an edge detection operator is introduced to construct a lung nodule edge enhancement dataset, which improves the dataset utilization while providing more prior knowledge of the target lesion boundar. In addition, the Down-Attention Sample (DASample) as a basic encoding block is designed to effectively perceive local features of different ranges and scales in the down-sampling process of lung nodule feature extraction. Finally, a feature aggregation module is designed to fuse the outputs of the two paths to get the final segmentation result. Our DPBET can delineate the boundaries of various types of pulmonary nodules, with an average DSC of 89.86% and an average Sensitivity of 90.50% on the public dataset LIDC-IDRI. Compared with the state-of-the-art approaches, a substantial improvement has been achieved. The experimental results demonstrate that DPBET can use edge enhancement to promote the global-edge consistency relationship, and the network architecture is effective in lung nodule segmentation. Highlights: We propose a dual-path lung nodules segmentation model based on boundary enhancement and hybrid transformer. Hybrid CNN-Transformer compensates for the drawback that pure CNN has difficulty in capturing long distance relationships. The boundary enhanced dataset is constructed to improve the utilization rate of the original dataset. The CAP-Trans module with explicit guidance enables multi-head attention pruning based on head contribution values.