Improvement of chest X-ray image segmentation accuracy based on FCA-Net
AbstractMedical image segmentation is a crucial stage in computer vision and image processing to help the later-stage diagnosis process become more accurate. Because medical image segmentation, such as X-ray, can extract tissue, organs, and pathological structures. However, medical image processing,...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Cogent Engineering |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/23311916.2023.2229571 |
| _version_ | 1827344450398978048 |
|---|---|
| author | Rima Tri Wahyuningrum Indah Yunita Indah Agustien Siradjuddin Budi Dwi Satoto Amillia Kartika Sari Anggraini Dwi Sensusiati |
| author_facet | Rima Tri Wahyuningrum Indah Yunita Indah Agustien Siradjuddin Budi Dwi Satoto Amillia Kartika Sari Anggraini Dwi Sensusiati |
| author_sort | Rima Tri Wahyuningrum |
| collection | DOAJ |
| description | AbstractMedical image segmentation is a crucial stage in computer vision and image processing to help the later-stage diagnosis process become more accurate. Because medical image segmentation, such as X-ray, can extract tissue, organs, and pathological structures. However, medical image processing, primarily in the segmentation process, has significant challenges regarding feature representation. Because medical images have different characteristics than other images related to contrast, blur, and noise. This study proposes the use of lung segmentation on chest X-ray images based on deep learning with the FCA-Net (Fully Convolutional Attention Network) architecture. In addition, attention modules, namely spatial attention and channel attention, are added to the Res2Net encoder so that it is expected to be able to represent features better. This research was conducted on chest X-ray images from Qatar University contained in the Kaggle repository. A chest x-ray image measuring 256 × 256 pixels and as many as 1500 images were then divided into 10% testing data and 90% training data. The training data will then be processed in K-Fold Cross validation from K = 2 until K = 10. The experiment was conducted with scenarios that used spatial attention, channel attention, and a combination of spatial and channel attention. The best test results in this study were using a variety of spatial attention and channel attention in the division of K-Fold with a value of K = 5 with a DSC (Dice Similarity Coefficient) value in the testing data of 97.24% and IoU (Intersection over Union) in the testing data of 94.66%. This accuracy result is better than the UNet++, DeepLabV3+, and SegNet architectures. |
| first_indexed | 2024-03-07T22:47:28Z |
| format | Article |
| id | doaj.art-46a66b288271471e95cb574adae201c8 |
| institution | Directory Open Access Journal |
| issn | 2331-1916 |
| language | English |
| last_indexed | 2024-03-07T22:47:28Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Cogent Engineering |
| spelling | doaj.art-46a66b288271471e95cb574adae201c82024-02-23T15:01:40ZengTaylor & Francis GroupCogent Engineering2331-19162023-12-0110110.1080/23311916.2023.2229571Improvement of chest X-ray image segmentation accuracy based on FCA-NetRima Tri Wahyuningrum0Indah Yunita1Indah Agustien Siradjuddin2Budi Dwi Satoto3Amillia Kartika Sari4Anggraini Dwi Sensusiati5Department of Informatics Engineering, Faculty of Engineering, University of Trunojoyo Madura, Bangkalan, IndonesiaDepartment of Informatics Engineering, Faculty of Engineering, University of Trunojoyo Madura, Bangkalan, IndonesiaDepartment of Informatics Engineering, Faculty of Engineering, University of Trunojoyo Madura, Bangkalan, IndonesiaDepartment of Informatics Engineering, Faculty of Engineering, University of Trunojoyo Madura, Bangkalan, IndonesiaDepartment of Health, Faculty of Vocational Studies, Universitas Airlangga, Surabaya, IndonesiaDepartment of Radiology, Medical Faculty, Universitas Airlangga, Surabaya, IndonesiaAbstractMedical image segmentation is a crucial stage in computer vision and image processing to help the later-stage diagnosis process become more accurate. Because medical image segmentation, such as X-ray, can extract tissue, organs, and pathological structures. However, medical image processing, primarily in the segmentation process, has significant challenges regarding feature representation. Because medical images have different characteristics than other images related to contrast, blur, and noise. This study proposes the use of lung segmentation on chest X-ray images based on deep learning with the FCA-Net (Fully Convolutional Attention Network) architecture. In addition, attention modules, namely spatial attention and channel attention, are added to the Res2Net encoder so that it is expected to be able to represent features better. This research was conducted on chest X-ray images from Qatar University contained in the Kaggle repository. A chest x-ray image measuring 256 × 256 pixels and as many as 1500 images were then divided into 10% testing data and 90% training data. The training data will then be processed in K-Fold Cross validation from K = 2 until K = 10. The experiment was conducted with scenarios that used spatial attention, channel attention, and a combination of spatial and channel attention. The best test results in this study were using a variety of spatial attention and channel attention in the division of K-Fold with a value of K = 5 with a DSC (Dice Similarity Coefficient) value in the testing data of 97.24% and IoU (Intersection over Union) in the testing data of 94.66%. This accuracy result is better than the UNet++, DeepLabV3+, and SegNet architectures.https://www.tandfonline.com/doi/10.1080/23311916.2023.2229571lung segmentationchest X-rayFCA-Netattention moduledeep learning |
| spellingShingle | Rima Tri Wahyuningrum Indah Yunita Indah Agustien Siradjuddin Budi Dwi Satoto Amillia Kartika Sari Anggraini Dwi Sensusiati Improvement of chest X-ray image segmentation accuracy based on FCA-Net Cogent Engineering lung segmentation chest X-ray FCA-Net attention module deep learning |
| title | Improvement of chest X-ray image segmentation accuracy based on FCA-Net |
| title_full | Improvement of chest X-ray image segmentation accuracy based on FCA-Net |
| title_fullStr | Improvement of chest X-ray image segmentation accuracy based on FCA-Net |
| title_full_unstemmed | Improvement of chest X-ray image segmentation accuracy based on FCA-Net |
| title_short | Improvement of chest X-ray image segmentation accuracy based on FCA-Net |
| title_sort | improvement of chest x ray image segmentation accuracy based on fca net |
| topic | lung segmentation chest X-ray FCA-Net attention module deep learning |
| url | https://www.tandfonline.com/doi/10.1080/23311916.2023.2229571 |
| work_keys_str_mv | AT rimatriwahyuningrum improvementofchestxrayimagesegmentationaccuracybasedonfcanet AT indahyunita improvementofchestxrayimagesegmentationaccuracybasedonfcanet AT indahagustiensiradjuddin improvementofchestxrayimagesegmentationaccuracybasedonfcanet AT budidwisatoto improvementofchestxrayimagesegmentationaccuracybasedonfcanet AT amilliakartikasari improvementofchestxrayimagesegmentationaccuracybasedonfcanet AT anggrainidwisensusiati improvementofchestxrayimagesegmentationaccuracybasedonfcanet |