Automated Assessment of the Pulmonary Artery-to-Ascending Aorta Ratio in Fetal Cardiac Ultrasound Screening Using Artificial Intelligence
The three-vessel view (3VV) is a standardized transverse scanning plane used in fetal cardiac ultrasound screening to measure the absolute and relative diameters of the pulmonary artery (PA), ascending aorta (Ao), and superior vena cava, as required. The PA/Ao ratio is used to support the diagnosis...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/11/12/1256 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846105759505448960 |
|---|---|
| author | Rina Aoyama Masaaki Komatsu Naoaki Harada Reina Komatsu Akira Sakai Katsuji Takeda Naoki Teraya Ken Asada Syuzo Kaneko Kazuki Iwamoto Ryu Matsuoka Akihiko Sekizawa Ryuji Hamamoto |
| author_facet | Rina Aoyama Masaaki Komatsu Naoaki Harada Reina Komatsu Akira Sakai Katsuji Takeda Naoki Teraya Ken Asada Syuzo Kaneko Kazuki Iwamoto Ryu Matsuoka Akihiko Sekizawa Ryuji Hamamoto |
| author_sort | Rina Aoyama |
| collection | DOAJ |
| description | The three-vessel view (3VV) is a standardized transverse scanning plane used in fetal cardiac ultrasound screening to measure the absolute and relative diameters of the pulmonary artery (PA), ascending aorta (Ao), and superior vena cava, as required. The PA/Ao ratio is used to support the diagnosis of congenital heart disease (CHD). However, vascular diameters are measured manually by examiners, which causes intra- and interobserver variability in clinical practice. In the present study, we aimed to develop an artificial intelligence-based method for the standardized and quantitative evaluation of 3VV. In total, 315 cases and 20 examiners were included in this study. We used the object-detection software YOLOv7 for the automated extraction of 3VV images and compared three segmentation algorithms: DeepLabv3+, UNet3+, and SegFormer. Using the PA/Ao ratios based on vascular segmentation, YOLOv7 plus UNet3+ yielded the most appropriate classification for normal fetuses and those with CHD. Furthermore, YOLOv7 plus UNet3+ achieved an arithmetic mean value of 0.883 for the area under the receiver operating characteristic curve, which was higher than 0.749 for residents and 0.808 for fellows. Our automated method may support unskilled examiners in performing quantitative and objective assessments of 3VV images during fetal cardiac ultrasound screening. |
| format | Article |
| id | doaj-art-26d705ab7b5b4c82a68d6369aa171054 |
| institution | Kabale University |
| issn | 2306-5354 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj-art-26d705ab7b5b4c82a68d6369aa1710542024-12-27T14:11:38ZengMDPI AGBioengineering2306-53542024-12-011112125610.3390/bioengineering11121256Automated Assessment of the Pulmonary Artery-to-Ascending Aorta Ratio in Fetal Cardiac Ultrasound Screening Using Artificial IntelligenceRina Aoyama0Masaaki Komatsu1Naoaki Harada2Reina Komatsu3Akira Sakai4Katsuji Takeda5Naoki Teraya6Ken Asada7Syuzo Kaneko8Kazuki Iwamoto9Ryu Matsuoka10Akihiko Sekizawa11Ryuji Hamamoto12Division of Medical AI Research and Development, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanDivision of Medical AI Research and Development, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanDivision of Medical AI Research and Development, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanDepartment of Obstetrics and Gynecology, School of Medicine, Showa University, 1-5-8 Hatanodai, Shinagawa-ku, Tokyo 142-8666, JapanArtificial Intelligence Laboratory, Fujitsu Ltd., 4-1-1 Kamikodanaka, Nakahara-ku, Kawasaki 211-8588, JapanCancer Translational Research Team, RIKEN Center for Advanced Intelligence Project, 1-4-1 Nihonbashi, Chuo-ku, Tokyo 103-0027, JapanDivision of Medical AI Research and Development, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanDivision of Medical AI Research and Development, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanDivision of Medical AI Research and Development, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanHLPF Data Analytics Department, Fujitsu Ltd., 1-5 Omiya-cho, Saiwai-ku, Kawasaki 212-0014, JapanDepartment of Obstetrics and Gynecology, School of Medicine, Showa University, 1-5-8 Hatanodai, Shinagawa-ku, Tokyo 142-8666, JapanDepartment of Obstetrics and Gynecology, School of Medicine, Showa University, 1-5-8 Hatanodai, Shinagawa-ku, Tokyo 142-8666, JapanDivision of Medical AI Research and Development, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanThe three-vessel view (3VV) is a standardized transverse scanning plane used in fetal cardiac ultrasound screening to measure the absolute and relative diameters of the pulmonary artery (PA), ascending aorta (Ao), and superior vena cava, as required. The PA/Ao ratio is used to support the diagnosis of congenital heart disease (CHD). However, vascular diameters are measured manually by examiners, which causes intra- and interobserver variability in clinical practice. In the present study, we aimed to develop an artificial intelligence-based method for the standardized and quantitative evaluation of 3VV. In total, 315 cases and 20 examiners were included in this study. We used the object-detection software YOLOv7 for the automated extraction of 3VV images and compared three segmentation algorithms: DeepLabv3+, UNet3+, and SegFormer. Using the PA/Ao ratios based on vascular segmentation, YOLOv7 plus UNet3+ yielded the most appropriate classification for normal fetuses and those with CHD. Furthermore, YOLOv7 plus UNet3+ achieved an arithmetic mean value of 0.883 for the area under the receiver operating characteristic curve, which was higher than 0.749 for residents and 0.808 for fellows. Our automated method may support unskilled examiners in performing quantitative and objective assessments of 3VV images during fetal cardiac ultrasound screening.https://www.mdpi.com/2306-5354/11/12/1256fetal cardiac ultrasound screeningthree-vessel viewPA/Ao ratioartificial intelligence |
| spellingShingle | Rina Aoyama Masaaki Komatsu Naoaki Harada Reina Komatsu Akira Sakai Katsuji Takeda Naoki Teraya Ken Asada Syuzo Kaneko Kazuki Iwamoto Ryu Matsuoka Akihiko Sekizawa Ryuji Hamamoto Automated Assessment of the Pulmonary Artery-to-Ascending Aorta Ratio in Fetal Cardiac Ultrasound Screening Using Artificial Intelligence Bioengineering fetal cardiac ultrasound screening three-vessel view PA/Ao ratio artificial intelligence |
| title | Automated Assessment of the Pulmonary Artery-to-Ascending Aorta Ratio in Fetal Cardiac Ultrasound Screening Using Artificial Intelligence |
| title_full | Automated Assessment of the Pulmonary Artery-to-Ascending Aorta Ratio in Fetal Cardiac Ultrasound Screening Using Artificial Intelligence |
| title_fullStr | Automated Assessment of the Pulmonary Artery-to-Ascending Aorta Ratio in Fetal Cardiac Ultrasound Screening Using Artificial Intelligence |
| title_full_unstemmed | Automated Assessment of the Pulmonary Artery-to-Ascending Aorta Ratio in Fetal Cardiac Ultrasound Screening Using Artificial Intelligence |
| title_short | Automated Assessment of the Pulmonary Artery-to-Ascending Aorta Ratio in Fetal Cardiac Ultrasound Screening Using Artificial Intelligence |
| title_sort | automated assessment of the pulmonary artery to ascending aorta ratio in fetal cardiac ultrasound screening using artificial intelligence |
| topic | fetal cardiac ultrasound screening three-vessel view PA/Ao ratio artificial intelligence |
| url | https://www.mdpi.com/2306-5354/11/12/1256 |
| work_keys_str_mv | AT rinaaoyama automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT masaakikomatsu automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT naoakiharada automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT reinakomatsu automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT akirasakai automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT katsujitakeda automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT naokiteraya automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT kenasada automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT syuzokaneko automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT kazukiiwamoto automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT ryumatsuoka automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT akihikosekizawa automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence AT ryujihamamoto automatedassessmentofthepulmonaryarterytoascendingaortaratioinfetalcardiacultrasoundscreeningusingartificialintelligence |