HR-MPF: high-resolution representation network with multi-scale progressive fusion for pulmonary nodule segmentation and classification

EURASIP Journal on Image and Video Processing

Suyi Yang¹  Hongqing Zhu²  Ling Zhu²  Yang Yu²  Pengyu Wang² 

[1] Department of Mathematics, Natural, Mathematical & Engineering Sciences, King’s College London, WC2R 2LS, London, United Kingdom;School of Information Science & Engineering, East China University of Science and Technology, Mei Long Road, 200237, Shanghai, China;

关键词: Pulmonary nodule;    Segmentation and classification;    High-resolution network;    Multi-scale progressive fusion;    Generative adversarial network;   

DOI  :  10.1186/s13640-021-00574-2

来源: Springer

【 摘 要 】

Accurate segmentation and classification of pulmonary nodules are of great significance to early detection and diagnosis of lung diseases, which can reduce the risk of developing lung cancer and improve patient survival rate. In this paper, we propose an effective network for pulmonary nodule segmentation and classification at one time based on adversarial training scheme. The segmentation network consists of a High-Resolution network with Multi-scale Progressive Fusion (HR-MPF) and a proposed Progressive Decoding Module (PDM) recovering final pixel-wise prediction results. Specifically, the proposed HR-MPF firstly incorporates boosted module to High-Resolution Network (HRNet) in a progressive feature fusion manner. In this case, feature communication is augmented among all levels in this high-resolution network. Then, downstream classification module would identify benign and malignant pulmonary nodules based on feature map from PDM. In the adversarial training scheme, a discriminator is set to optimize HR-MPF and PDM through back propagation. Meanwhile, a reasonably designed multi-task loss function optimizes performance of segmentation and classification overall. To improve the accuracy of boundary prediction crucial to nodule segmentation, a boundary consistency constraint is designed and incorporated in the segmentation loss function. Experiments on publicly available LUNA16 dataset show that the framework outperforms relevant advanced methods in quantitative evaluation and visual perception.

【 授权许可】

CC BY