Effectiveness and clinical impact of using deep learning for first-trimester fetal ultrasound image quality auditing
Abstract Background Regular auditing of ultrasound images is required to maintain quality; however, manual auditing is time-consuming and can be inconsistent. We therefore aimed to develop and validate an artificial intelligence-based image quality audit (AI-IQA) system to audit images from the four...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-03-01
|
| Series: | BMC Pregnancy and Childbirth |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12884-025-07485-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850153560499552256 |
|---|---|
| author | Xiaoyan Cao Binghan Li Yongsong Zhou Yan Cao Xin Yang Xindi Hu Chaoyu Chen Shaokao Zhu Hengli Lin Tao Wang Yuling Yan Tao Tan Lin Wang Dong Ni |
| author_facet | Xiaoyan Cao Binghan Li Yongsong Zhou Yan Cao Xin Yang Xindi Hu Chaoyu Chen Shaokao Zhu Hengli Lin Tao Wang Yuling Yan Tao Tan Lin Wang Dong Ni |
| author_sort | Xiaoyan Cao |
| collection | DOAJ |
| description | Abstract Background Regular auditing of ultrasound images is required to maintain quality; however, manual auditing is time-consuming and can be inconsistent. We therefore aimed to develop and validate an artificial intelligence-based image quality audit (AI-IQA) system to audit images from the four key planes used in first-trimester scanning. Methods The AI-IQA system was developed based on the YOLOv7 structure detection network and a multi-branch image quality regression network using a large multicenter internal dataset. Clinical validation was performed using 567 cases scanned by four radiologists with different experience levels, of which 349 were performed without AI-IQA feedback (clinical test set 1) and 218 were performed after 2–3 rounds of AI-IQA feedback (clinical test set 2). The proportion of standard images obtained and detailed expert audit results were compared to verify whether AI-IQA could objectively and accurately provide feedback on deficiencies in nonstandard images to assist radiologists at different experience levels in improving image quality. Results In the internal test set, the AI-IQA system achieved high average accuracy precision, recall and F1-score in auditing the overall plane quality (0.881, 0.833, 0.842 and 0.837, respectively) and structure quality (0.906, 0.861, 0.857 and 0.859, respectively). In clinical test sets 1 and 2, AI-IQA results showed strong consistency with expert assessment results, with the average Cohen’s Kappa coefficient exceeding 0.8 for all four planes. In addition, following AI-IQA feedback, the proportion of standard images obtained by junior and mid-level radiologists increased by 7.7% and 5.1%, respectively. AI-IQA takes only 0.05 s to assess each image, while experts require more than 20 s (p < 0.001). Conclusions The proposed AI-IQA system proved to be a highly accurate and efficient method of automatically auditing first-trimester scanning image quality, providing precise and rapid key plane quality control. This tool can also assist radiologists with different levels of experience to improve the image quality. |
| format | Article |
| id | doaj-art-1b9cbc86b09d42bd8a5a4dca0febbb62 |
| institution | OA Journals |
| issn | 1471-2393 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Pregnancy and Childbirth |
| spelling | doaj-art-1b9cbc86b09d42bd8a5a4dca0febbb622025-08-20T02:25:41ZengBMCBMC Pregnancy and Childbirth1471-23932025-03-0125111310.1186/s12884-025-07485-4Effectiveness and clinical impact of using deep learning for first-trimester fetal ultrasound image quality auditingXiaoyan Cao0Binghan Li1Yongsong Zhou2Yan Cao3Xin Yang4Xindi Hu5Chaoyu Chen6Shaokao Zhu7Hengli Lin8Tao Wang9Yuling Yan10Tao Tan11Lin Wang12Dong Ni13Ultrasound Department, Shenzhen Futian District Maternity & Child Healthcare HospitalNational-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen UniversityNational-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen UniversityShenzhen RayShape Medical Technology Co., Ltd.National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen UniversityShenzhen RayShape Medical Technology Co., Ltd.National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen UniversityUltrasound Department, Shenzhen Futian District Maternity & Child Healthcare HospitalUltrasound Department, Shenzhen Futian District Maternity & Child Healthcare HospitalUltrasound Department, Shenzhen Futian District Maternity & Child Healthcare HospitalUltrasound Department, Shenzhen Futian District Maternity & Child Healthcare HospitalFaculty of Applied Sciences, Macao Polytechnic University, Macao SARUltrasound Department, Shenzhen Futian District Maternity & Child Healthcare HospitalNational-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen UniversityAbstract Background Regular auditing of ultrasound images is required to maintain quality; however, manual auditing is time-consuming and can be inconsistent. We therefore aimed to develop and validate an artificial intelligence-based image quality audit (AI-IQA) system to audit images from the four key planes used in first-trimester scanning. Methods The AI-IQA system was developed based on the YOLOv7 structure detection network and a multi-branch image quality regression network using a large multicenter internal dataset. Clinical validation was performed using 567 cases scanned by four radiologists with different experience levels, of which 349 were performed without AI-IQA feedback (clinical test set 1) and 218 were performed after 2–3 rounds of AI-IQA feedback (clinical test set 2). The proportion of standard images obtained and detailed expert audit results were compared to verify whether AI-IQA could objectively and accurately provide feedback on deficiencies in nonstandard images to assist radiologists at different experience levels in improving image quality. Results In the internal test set, the AI-IQA system achieved high average accuracy precision, recall and F1-score in auditing the overall plane quality (0.881, 0.833, 0.842 and 0.837, respectively) and structure quality (0.906, 0.861, 0.857 and 0.859, respectively). In clinical test sets 1 and 2, AI-IQA results showed strong consistency with expert assessment results, with the average Cohen’s Kappa coefficient exceeding 0.8 for all four planes. In addition, following AI-IQA feedback, the proportion of standard images obtained by junior and mid-level radiologists increased by 7.7% and 5.1%, respectively. AI-IQA takes only 0.05 s to assess each image, while experts require more than 20 s (p < 0.001). Conclusions The proposed AI-IQA system proved to be a highly accurate and efficient method of automatically auditing first-trimester scanning image quality, providing precise and rapid key plane quality control. This tool can also assist radiologists with different levels of experience to improve the image quality.https://doi.org/10.1186/s12884-025-07485-4Prenatal ultrasoundFirst-trimester scanningImage quality controlArtificial intelligenceDeep learning |
| spellingShingle | Xiaoyan Cao Binghan Li Yongsong Zhou Yan Cao Xin Yang Xindi Hu Chaoyu Chen Shaokao Zhu Hengli Lin Tao Wang Yuling Yan Tao Tan Lin Wang Dong Ni Effectiveness and clinical impact of using deep learning for first-trimester fetal ultrasound image quality auditing BMC Pregnancy and Childbirth Prenatal ultrasound First-trimester scanning Image quality control Artificial intelligence Deep learning |
| title | Effectiveness and clinical impact of using deep learning for first-trimester fetal ultrasound image quality auditing |
| title_full | Effectiveness and clinical impact of using deep learning for first-trimester fetal ultrasound image quality auditing |
| title_fullStr | Effectiveness and clinical impact of using deep learning for first-trimester fetal ultrasound image quality auditing |
| title_full_unstemmed | Effectiveness and clinical impact of using deep learning for first-trimester fetal ultrasound image quality auditing |
| title_short | Effectiveness and clinical impact of using deep learning for first-trimester fetal ultrasound image quality auditing |
| title_sort | effectiveness and clinical impact of using deep learning for first trimester fetal ultrasound image quality auditing |
| topic | Prenatal ultrasound First-trimester scanning Image quality control Artificial intelligence Deep learning |
| url | https://doi.org/10.1186/s12884-025-07485-4 |
| work_keys_str_mv | AT xiaoyancao effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT binghanli effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT yongsongzhou effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT yancao effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT xinyang effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT xindihu effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT chaoyuchen effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT shaokaozhu effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT henglilin effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT taowang effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT yulingyan effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT taotan effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT linwang effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing AT dongni effectivenessandclinicalimpactofusingdeeplearningforfirsttrimesterfetalultrasoundimagequalityauditing |