Part-Aware Mask-Guided Attention for Thorax Disease Classification
Thorax disease classification is a challenging task due to complex pathologies and subtle texture changes, etc. It has been extensively studied for years largely because of its wide application in computer-aided diagnosis. Most existing methods directly learn global feature representations from whol...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/6/653 |
| _version_ | 1827691772868820992 |
|---|---|
| author | Ruihua Zhang Fan Yang Yan Luo Jianyi Liu Jinbin Li Cong Wang |
| author_facet | Ruihua Zhang Fan Yang Yan Luo Jianyi Liu Jinbin Li Cong Wang |
| author_sort | Ruihua Zhang |
| collection | DOAJ |
| description | Thorax disease classification is a challenging task due to complex pathologies and subtle texture changes, etc. It has been extensively studied for years largely because of its wide application in computer-aided diagnosis. Most existing methods directly learn global feature representations from whole Chest X-ray (CXR) images, without considering in depth the richer visual cues lying around informative local regions. Thus, these methods often produce sub-optimal thorax disease classification performance because they ignore the very informative pathological changes around organs. In this paper, we propose a novel Part-Aware Mask-Guided Attention Network (PMGAN) that learns complementary global and local feature representations from all-organ region and multiple single-organ regions simultaneously for thorax disease classification. Specifically, multiple innovative soft attention modules are designed to progressively guide feature learning toward the global informative regions of whole CXR image. A mask-guided attention module is designed to further search for informative regions and visual cues within the all-organ or single-organ images, where attention is elegantly regularized by automatically generated organ masks and without introducing computation during the inference stage. In addition, a multi-task learning strategy is designed, which effectively maximizes the learning of complementary local and global representations. The proposed PMGAN has been evaluated on the ChestX-ray14 dataset and the experimental results demonstrate its superior thorax disease classification performance against the state-of-the-art methods. |
| first_indexed | 2024-03-10T11:08:18Z |
| format | Article |
| id | doaj.art-686f85b61c0e4a958d1b749d35d82cd3 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T11:08:18Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-686f85b61c0e4a958d1b749d35d82cd32023-11-21T20:59:07ZengMDPI AGEntropy1099-43002021-05-0123665310.3390/e23060653Part-Aware Mask-Guided Attention for Thorax Disease ClassificationRuihua Zhang0Fan Yang1Yan Luo2Jianyi Liu3Jinbin Li4Cong Wang5School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronics Engineering and Computer Science, Peking University, Beijing 100871, ChinaSchool of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaLocal Servive Center, National Population Health Data Center, Beijing 100005, ChinaSchool of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaThorax disease classification is a challenging task due to complex pathologies and subtle texture changes, etc. It has been extensively studied for years largely because of its wide application in computer-aided diagnosis. Most existing methods directly learn global feature representations from whole Chest X-ray (CXR) images, without considering in depth the richer visual cues lying around informative local regions. Thus, these methods often produce sub-optimal thorax disease classification performance because they ignore the very informative pathological changes around organs. In this paper, we propose a novel Part-Aware Mask-Guided Attention Network (PMGAN) that learns complementary global and local feature representations from all-organ region and multiple single-organ regions simultaneously for thorax disease classification. Specifically, multiple innovative soft attention modules are designed to progressively guide feature learning toward the global informative regions of whole CXR image. A mask-guided attention module is designed to further search for informative regions and visual cues within the all-organ or single-organ images, where attention is elegantly regularized by automatically generated organ masks and without introducing computation during the inference stage. In addition, a multi-task learning strategy is designed, which effectively maximizes the learning of complementary local and global representations. The proposed PMGAN has been evaluated on the ChestX-ray14 dataset and the experimental results demonstrate its superior thorax disease classification performance against the state-of-the-art methods.https://www.mdpi.com/1099-4300/23/6/653thorax disease classificationsoft attentionmask-guided attentionmulti-task learning |
| spellingShingle | Ruihua Zhang Fan Yang Yan Luo Jianyi Liu Jinbin Li Cong Wang Part-Aware Mask-Guided Attention for Thorax Disease Classification Entropy thorax disease classification soft attention mask-guided attention multi-task learning |
| title | Part-Aware Mask-Guided Attention for Thorax Disease Classification |
| title_full | Part-Aware Mask-Guided Attention for Thorax Disease Classification |
| title_fullStr | Part-Aware Mask-Guided Attention for Thorax Disease Classification |
| title_full_unstemmed | Part-Aware Mask-Guided Attention for Thorax Disease Classification |
| title_short | Part-Aware Mask-Guided Attention for Thorax Disease Classification |
| title_sort | part aware mask guided attention for thorax disease classification |
| topic | thorax disease classification soft attention mask-guided attention multi-task learning |
| url | https://www.mdpi.com/1099-4300/23/6/653 |
| work_keys_str_mv | AT ruihuazhang partawaremaskguidedattentionforthoraxdiseaseclassification AT fanyang partawaremaskguidedattentionforthoraxdiseaseclassification AT yanluo partawaremaskguidedattentionforthoraxdiseaseclassification AT jianyiliu partawaremaskguidedattentionforthoraxdiseaseclassification AT jinbinli partawaremaskguidedattentionforthoraxdiseaseclassification AT congwang partawaremaskguidedattentionforthoraxdiseaseclassification |