Automatic Lung Segmentation on Chest X-rays Using Self-Attention Deep Neural Network
Accurate identification of the boundaries of organs or abnormal objects (e.g., tumors) in medical images is important in surgical planning and in the diagnosis and prognosis of diseases. In this study, we propose a deep learning-based method to segment lung areas in chest X-rays. The novel aspect of...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/2/369 |
| _version_ | 1827603548552036352 |
|---|---|
| author | Minki Kim Byoung-Dai Lee |
| author_facet | Minki Kim Byoung-Dai Lee |
| author_sort | Minki Kim |
| collection | DOAJ |
| description | Accurate identification of the boundaries of organs or abnormal objects (e.g., tumors) in medical images is important in surgical planning and in the diagnosis and prognosis of diseases. In this study, we propose a deep learning-based method to segment lung areas in chest X-rays. The novel aspect of the proposed method is the self-attention module, where the outputs of the channel and spatial attention modules are combined to generate attention maps, with each highlighting those regions of feature maps that correspond to “what” and “where” to attend in the learning process, respectively. Thereafter, the attention maps are multiplied element-wise with the input feature map, and the intermediate results are added to the input feature map again for residual learning. Using X-ray images collected from public datasets for training and evaluation, we applied the proposed attention modules to U-Net for segmentation of lung areas and conducted experiments while changing the locations of the attention modules in the baseline network. The experimental results showed that our method achieved comparable or better performance than the existing medical image segmentation networks in terms of Dice score when the proposed attention modules were placed in lower layers of both the contracting and expanding paths of U-Net. |
| first_indexed | 2024-03-09T05:41:13Z |
| format | Article |
| id | doaj.art-750a5029275e4773a613cc9d3cfcacdb |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:41:13Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-750a5029275e4773a613cc9d3cfcacdb2023-12-03T12:24:44ZengMDPI AGSensors1424-82202021-01-0121236910.3390/s21020369Automatic Lung Segmentation on Chest X-rays Using Self-Attention Deep Neural NetworkMinki Kim0Byoung-Dai Lee1School of Computer Science and Engineering, Kyonggi University, Gyeonggi-do 16227, KoreaSchool of Computer Science and Engineering, Kyonggi University, Gyeonggi-do 16227, KoreaAccurate identification of the boundaries of organs or abnormal objects (e.g., tumors) in medical images is important in surgical planning and in the diagnosis and prognosis of diseases. In this study, we propose a deep learning-based method to segment lung areas in chest X-rays. The novel aspect of the proposed method is the self-attention module, where the outputs of the channel and spatial attention modules are combined to generate attention maps, with each highlighting those regions of feature maps that correspond to “what” and “where” to attend in the learning process, respectively. Thereafter, the attention maps are multiplied element-wise with the input feature map, and the intermediate results are added to the input feature map again for residual learning. Using X-ray images collected from public datasets for training and evaluation, we applied the proposed attention modules to U-Net for segmentation of lung areas and conducted experiments while changing the locations of the attention modules in the baseline network. The experimental results showed that our method achieved comparable or better performance than the existing medical image segmentation networks in terms of Dice score when the proposed attention modules were placed in lower layers of both the contracting and expanding paths of U-Net.https://www.mdpi.com/1424-8220/21/2/369deep learningmedical imageattention moduleimage segmentationlung segmentation |
| spellingShingle | Minki Kim Byoung-Dai Lee Automatic Lung Segmentation on Chest X-rays Using Self-Attention Deep Neural Network Sensors deep learning medical image attention module image segmentation lung segmentation |
| title | Automatic Lung Segmentation on Chest X-rays Using Self-Attention Deep Neural Network |
| title_full | Automatic Lung Segmentation on Chest X-rays Using Self-Attention Deep Neural Network |
| title_fullStr | Automatic Lung Segmentation on Chest X-rays Using Self-Attention Deep Neural Network |
| title_full_unstemmed | Automatic Lung Segmentation on Chest X-rays Using Self-Attention Deep Neural Network |
| title_short | Automatic Lung Segmentation on Chest X-rays Using Self-Attention Deep Neural Network |
| title_sort | automatic lung segmentation on chest x rays using self attention deep neural network |
| topic | deep learning medical image attention module image segmentation lung segmentation |
| url | https://www.mdpi.com/1424-8220/21/2/369 |
| work_keys_str_mv | AT minkikim automaticlungsegmentationonchestxraysusingselfattentiondeepneuralnetwork AT byoungdailee automaticlungsegmentationonchestxraysusingselfattentiondeepneuralnetwork |