Lung segmentation in chest X‐ray image using multi‐interaction feature fusion network
Abstract Lung segmentation is an essential step in a computer‐aided diagnosis system for chest radiographs. The lung parenchyma is first segmented in pulmonary computer‐aided diagnosis systems to remove the interference of non‐lung regions while increasing the effectiveness of the subsequent work. N...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-12-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.12923 |
| _version_ | 1827595573985804288 |
|---|---|
| author | Xuebin Xu Meng Lei Dehua Liu Muyu Wang Longbin Lu |
| author_facet | Xuebin Xu Meng Lei Dehua Liu Muyu Wang Longbin Lu |
| author_sort | Xuebin Xu |
| collection | DOAJ |
| description | Abstract Lung segmentation is an essential step in a computer‐aided diagnosis system for chest radiographs. The lung parenchyma is first segmented in pulmonary computer‐aided diagnosis systems to remove the interference of non‐lung regions while increasing the effectiveness of the subsequent work. Nevertheless, most medical image segmentation methods nowadays use U‐Net and its variants. These variant networks perform poorly in segmentation to detect smaller structures and cannot accurately segment boundary regions. A multi‐interaction feature fusion network model based on Kiu‐Net is presented in this paper to address this problem. Specifically, U‐Net and Ki‐Net are first utilized to extract high‐level and detailed features of chest images, respectively. Then, cross‐residual fusion modules are employed in the network encoding stage to obtain complementary features from these two networks. Second, the global information module is introduced to guarantee the segmented region's integrity. Finally, in the network decoding stage, the multi‐interaction module is presented, which allows to interact with multiple kinds of information, such as global contextual information, branching features, and fused features, to obtain more practical information. The performance of the proposed model was assessed on both the Montgomery County (MC) and Shenzhen datasets, demonstrating its superiority over existing methods according to the experimental results. |
| first_indexed | 2024-03-09T02:56:28Z |
| format | Article |
| id | doaj.art-d39816629e2e46f8b03332a8d5ea3692 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-03-09T02:56:28Z |
| publishDate | 2023-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-d39816629e2e46f8b03332a8d5ea36922023-12-05T06:22:51ZengWileyIET Image Processing1751-96591751-96672023-12-0117144129414110.1049/ipr2.12923Lung segmentation in chest X‐ray image using multi‐interaction feature fusion networkXuebin Xu0Meng Lei1Dehua Liu2Muyu Wang3Longbin Lu4School of Computer Science and Technology Xi'an University of Posts & Telecommunications Xi'an Shaanxi ChinaSchool of Computer Science and Technology Xi'an University of Posts & Telecommunications Xi'an Shaanxi ChinaSchool of Computer Science and Technology Xi'an University of Posts & Telecommunications Xi'an Shaanxi ChinaSchool of Computer Science and Technology Xi'an University of Posts & Telecommunications Xi'an Shaanxi ChinaSchool of Computer Science and Technology Xi'an University of Posts & Telecommunications Xi'an Shaanxi ChinaAbstract Lung segmentation is an essential step in a computer‐aided diagnosis system for chest radiographs. The lung parenchyma is first segmented in pulmonary computer‐aided diagnosis systems to remove the interference of non‐lung regions while increasing the effectiveness of the subsequent work. Nevertheless, most medical image segmentation methods nowadays use U‐Net and its variants. These variant networks perform poorly in segmentation to detect smaller structures and cannot accurately segment boundary regions. A multi‐interaction feature fusion network model based on Kiu‐Net is presented in this paper to address this problem. Specifically, U‐Net and Ki‐Net are first utilized to extract high‐level and detailed features of chest images, respectively. Then, cross‐residual fusion modules are employed in the network encoding stage to obtain complementary features from these two networks. Second, the global information module is introduced to guarantee the segmented region's integrity. Finally, in the network decoding stage, the multi‐interaction module is presented, which allows to interact with multiple kinds of information, such as global contextual information, branching features, and fused features, to obtain more practical information. The performance of the proposed model was assessed on both the Montgomery County (MC) and Shenzhen datasets, demonstrating its superiority over existing methods according to the experimental results.https://doi.org/10.1049/ipr2.12923computer visionconvolutional neural netsimage segmentation |
| spellingShingle | Xuebin Xu Meng Lei Dehua Liu Muyu Wang Longbin Lu Lung segmentation in chest X‐ray image using multi‐interaction feature fusion network IET Image Processing computer vision convolutional neural nets image segmentation |
| title | Lung segmentation in chest X‐ray image using multi‐interaction feature fusion network |
| title_full | Lung segmentation in chest X‐ray image using multi‐interaction feature fusion network |
| title_fullStr | Lung segmentation in chest X‐ray image using multi‐interaction feature fusion network |
| title_full_unstemmed | Lung segmentation in chest X‐ray image using multi‐interaction feature fusion network |
| title_short | Lung segmentation in chest X‐ray image using multi‐interaction feature fusion network |
| title_sort | lung segmentation in chest x ray image using multi interaction feature fusion network |
| topic | computer vision convolutional neural nets image segmentation |
| url | https://doi.org/10.1049/ipr2.12923 |
| work_keys_str_mv | AT xuebinxu lungsegmentationinchestxrayimageusingmultiinteractionfeaturefusionnetwork AT menglei lungsegmentationinchestxrayimageusingmultiinteractionfeaturefusionnetwork AT dehualiu lungsegmentationinchestxrayimageusingmultiinteractionfeaturefusionnetwork AT muyuwang lungsegmentationinchestxrayimageusingmultiinteractionfeaturefusionnetwork AT longbinlu lungsegmentationinchestxrayimageusingmultiinteractionfeaturefusionnetwork |