Segmentation of ground glass pulmonary nodules using full convolution residual network based on atrous spatial pyramid pooling structure and attention mechanism.
10.7507/1001-5515.202010051
- Author:
Ting DONG
1
;
Long WEI
2
;
Xiaodan YE
3
;
Yang CHEN
1
;
Xuewen HOU
1
;
Shengdong NIE
1
Author Information
1. School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, P. R. China.
2. School of Computer Science and Technology, Shandong Jianzhu University, JiNan 250101, P. R. China.
3. Shanghai Chest Hospital, Shanghai 200030, P. R. China.
- Publication Type:Journal Article
- Keywords:
Atrous convolution;
Attention mechanism;
Computed tomography image;
Ground glass nodule segmentation;
Residual network
- MeSH:
Algorithms;
China;
Disease Progression;
Humans;
Multiple Pulmonary Nodules;
Neural Networks, Computer;
Tomography, X-Ray Computed/methods*
- From:
Journal of Biomedical Engineering
2022;39(3):441-451
- CountryChina
- Language:Chinese
-
Abstract:
Accurate segmentation of ground glass nodule (GGN) is important in clinical. But it is a tough work to segment the GGN, as the GGN in the computed tomography images show blur boundary, irregular shape, and uneven intensity. This paper aims to segment GGN by proposing a fully convolutional residual network, i.e., residual network based on atrous spatial pyramid pooling structure and attention mechanism (ResAANet). The network uses atrous spatial pyramid pooling (ASPP) structure to expand the feature map receptive field and extract more sufficient features, and utilizes attention mechanism, residual connection, long skip connection to fully retain sensitive features, which is extracted by the convolutional layer. First, we employ 565 GGN provided by Shanghai Chest Hospital to train and validate ResAANet, so as to obtain a stable model. Then, two groups of data selected from clinical examinations (84 GGN) and lung image database consortium (LIDC) dataset (145 GGN) were employed to validate and evaluate the performance of the proposed method. Finally, we apply the best threshold method to remove false positive regions and obtain optimized results. The average dice similarity coefficient (DSC) of the proposed algorithm on the clinical dataset and LIDC dataset reached 83.46%, 83.26% respectively, the average Jaccard index (IoU) reached 72.39%, 71.56% respectively, and the speed of segmentation reached 0.1 seconds per image. Comparing with other reported methods, our new method could segment GGN accurately, quickly and robustly. It could provide doctors with important information such as nodule size or density, which assist doctors in subsequent diagnosis and treatment.
