Quality Assurance of Chest X-ray Images with a Combination of Deep Learning Methods
Background: Chest X-ray (CXR) imaging is the most common examination; however, no automatic quality assurance (QA) system using deep learning (DL) has been established for CXR. This study aimed to construct a DL-based QA system and assess its usefulness. Method: Datasets were created using over 23,0...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/4/2067 |
| _version_ | 1797622665522970624 |
|---|---|
| author | Daisuke Oura Shinpe Sato Yuto Honma Shiho Kuwajima Hiroyuki Sugimori |
| author_facet | Daisuke Oura Shinpe Sato Yuto Honma Shiho Kuwajima Hiroyuki Sugimori |
| author_sort | Daisuke Oura |
| collection | DOAJ |
| description | Background: Chest X-ray (CXR) imaging is the most common examination; however, no automatic quality assurance (QA) system using deep learning (DL) has been established for CXR. This study aimed to construct a DL-based QA system and assess its usefulness. Method: Datasets were created using over 23,000 images from Chest-14 and clinical images. The QA system consisted of three classification models and one regression model. The classification method was used for the correction of image orientation, left–right reversal, and estimating the patient’s position, such as standing, sitting, and lying. The regression method was used for the correction of the image angle. ResNet-50, VGG-16, and the original convolutional neural network (CNN) were compared under five cross-fold evaluations. The overall accuracy of the QA system was tested using clinical images. The mean correction time of the QA system was measured. Result: ResNet-50 demonstrated higher performance in the classification. The original CNN was preferred in the regression. The orientation, angle, and left–right reversal of all images were fully corrected in all images. Moreover, patients’ positions were estimated with 96% accuracy. The mean correction time was approximately 0.4 s. Conclusion: The DL-based QA system quickly and accurately corrected CXR images. |
| first_indexed | 2024-03-11T09:13:30Z |
| format | Article |
| id | doaj.art-e021142913fd4e5899ec643244b5701b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:13:30Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e021142913fd4e5899ec643244b5701b2023-11-16T18:50:23ZengMDPI AGApplied Sciences2076-34172023-02-01134206710.3390/app13042067Quality Assurance of Chest X-ray Images with a Combination of Deep Learning MethodsDaisuke Oura0Shinpe Sato1Yuto Honma2Shiho Kuwajima3Hiroyuki Sugimori4Department of Radiology, Otaru General Hospital, Otaru 047-0152, JapanDepartment of Radiology, Otaru General Hospital, Otaru 047-0152, JapanDepartment of Radiology, Otaru General Hospital, Otaru 047-0152, JapanDepartment of Radiology, Otaru General Hospital, Otaru 047-0152, JapanFaculty of Health Sciences, Hokkaido University, Sapporo 060-0812, JapanBackground: Chest X-ray (CXR) imaging is the most common examination; however, no automatic quality assurance (QA) system using deep learning (DL) has been established for CXR. This study aimed to construct a DL-based QA system and assess its usefulness. Method: Datasets were created using over 23,000 images from Chest-14 and clinical images. The QA system consisted of three classification models and one regression model. The classification method was used for the correction of image orientation, left–right reversal, and estimating the patient’s position, such as standing, sitting, and lying. The regression method was used for the correction of the image angle. ResNet-50, VGG-16, and the original convolutional neural network (CNN) were compared under five cross-fold evaluations. The overall accuracy of the QA system was tested using clinical images. The mean correction time of the QA system was measured. Result: ResNet-50 demonstrated higher performance in the classification. The original CNN was preferred in the regression. The orientation, angle, and left–right reversal of all images were fully corrected in all images. Moreover, patients’ positions were estimated with 96% accuracy. The mean correction time was approximately 0.4 s. Conclusion: The DL-based QA system quickly and accurately corrected CXR images.https://www.mdpi.com/2076-3417/13/4/2067quality assuranceX-raydeep learningartificial intelligence |
| spellingShingle | Daisuke Oura Shinpe Sato Yuto Honma Shiho Kuwajima Hiroyuki Sugimori Quality Assurance of Chest X-ray Images with a Combination of Deep Learning Methods Applied Sciences quality assurance X-ray deep learning artificial intelligence |
| title | Quality Assurance of Chest X-ray Images with a Combination of Deep Learning Methods |
| title_full | Quality Assurance of Chest X-ray Images with a Combination of Deep Learning Methods |
| title_fullStr | Quality Assurance of Chest X-ray Images with a Combination of Deep Learning Methods |
| title_full_unstemmed | Quality Assurance of Chest X-ray Images with a Combination of Deep Learning Methods |
| title_short | Quality Assurance of Chest X-ray Images with a Combination of Deep Learning Methods |
| title_sort | quality assurance of chest x ray images with a combination of deep learning methods |
| topic | quality assurance X-ray deep learning artificial intelligence |
| url | https://www.mdpi.com/2076-3417/13/4/2067 |
| work_keys_str_mv | AT daisukeoura qualityassuranceofchestxrayimageswithacombinationofdeeplearningmethods AT shinpesato qualityassuranceofchestxrayimageswithacombinationofdeeplearningmethods AT yutohonma qualityassuranceofchestxrayimageswithacombinationofdeeplearningmethods AT shihokuwajima qualityassuranceofchestxrayimageswithacombinationofdeeplearningmethods AT hiroyukisugimori qualityassuranceofchestxrayimageswithacombinationofdeeplearningmethods |