Automatic Fetal Middle Sagittal Plane Detection in Ultrasound Using Generative Adversarial Network
Open accessAbstract
Background and Objective: In the first trimester of pregnancy, fetal growth, and abnormalities can be assessed using the exact middle sagittal plane (MSP) of the fetus. However, the ultrasound (US) image quality and operator experience affect the accuracy. We present an automatic system that enables precise fetal MSP detection from three-dimensional (3D) US and provides an evaluation of its performance using a generative adversarial network (GAN) framework. Method: The neural network is designed as a filter and generates masks to obtain the MSP, learning the features and MSP location in 3D space. Using the proposed image analysis system, a seed point was obtained from 218 first-trimester fetal 3D US volumes using deep learning and the MSP was automatically extracted. Results: The experimental results reveal the feasibility and excellent performance of the proposed approach between the automatically and manually detected MSPs. There was no significant difference between the semi-automatic and automatic systems. Further, the inference time in the automatic system was up to two times faster than the semi-automatic approach. Conclusion: The proposed system offers precise fetal MSP measurements. Therefore, this automatic fetal MSP detection and measurement approach is anticipated to be useful clinically. The proposed system can also be applied to other relevant clinical fields in the future.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A limitation of first trimester AI models was difficulty assessing fetal limbs due to small anatomy and close surroundings.
“Limitations could be uncovered when assessing fetal limbs due to its small anatomy and close surroundings [136,137,138]”
From Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology (2023) · cites this paper as [136]
The Discussion (section 6; page not provided) says that images of smaller fetuses can increase processing errors and that soft tissue adhered to the fetus complicates image analysis. It does not discuss assessing fetal limbs or attribute a limb-specific difficulty to their small anatomy and close surroundings; the reported limitation concerns detection of the fetal middle sagittal plane. (LLM, conf=0.85)
Experimental — accuracy not yet measuredThree studies focused on detection of the midsagittal plane of the fetus, with one study focusing on 2D ultrasound and two studies on 3D ultrasound.
“Three studies focused on the detection of the midsagittal plane of the fetus, with one study focusing on 2D ultrasound 19 and two studies on 3D ultrasound.20,21”
From Artificial intelligence in obstetric ultrasound: A scoping review. (2023) · cites this paper as [20]
A potential benefit of first trimester AI models was reduced workload.
“and reduced workload [133,135,136,137].”
Tsai et al. aimed at automated detection of the correct mid-sagittal plane in 3D volumes to facilitate NT measurement.
“Tsai et al. aimed at facilitating the preliminary step for NT measurement, which was the automated detection of the correct mid-sagittal plane in 3D volumes [136]”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · see citing works
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392 · cited 1× · see citing works
“The atrous spatial pyramid pooling (ASPP) probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multipl scales [21].”
BackgroundHumans and automation: Use, misuse, disuse, abuse
Parasuraman, R., & Riley, V. (1997) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/001872097778543886 · Cited by 4,554 · see citing works
Nuchal translucency and other first-trimester sonographic markers of chromosomal abnormalities
Nicolaides, K. H. (2004) · American Journal of Obstetrics and Gynecology · doi:10.1016/j.ajog.2004.03.090 · Cited by 626 · cited 2× · see citing works
“In the first trimester, the MSP has proven to be useful for assessing fetal development and congenital fetal anomalies [1].”
BackgroundAutomatic Model-Based Segmentation of the Heart in CT Images
Ecabert, O., Peters, J., Schramm, H., Lorenz, C., von Berg, J., Walker, M. J. P., Vembar, M., Olszewski, M. E., Subramanyan, K., Lavi, G., et al. (2008) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2008.918330 · Cited by 368 · see citing works
Fetal face visualization using three-dimensional ultrasonography.
Pretorius, D. H., & Nelson, T. R. (1995) · Journal of Ultrasound in Medicine · doi:10.7863/jum.1995.14.5.349 · Cited by 154 · cited 1× · see citing works
“Three-dimensional (3D) US is valuable in prenatal diagnosis of fetal structures because it provides a multi-planar view [6,7].”
BackgroundReal-Time Deep Pose Estimation With Geodesic Loss for Image-to-Template Rigid Registration
Salehi, S. S. M., Khan, S., Deniz Erdogmus, B., & Gholipour, A. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2866442 · Cited by 133 · see citing works
Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registration
Salehi, S. S. M., Khan, S., Erdogmus, D., & Gholipour, A. (2018) · arXiv · doi:10.48550/arxiv.1803.05982 · Cited by 118 · see citing works
Kenkhuis, M. J. A., Bakker, M. K., Bardi, F., Fontanella, F., Bakker, M. K., Fleurke‐Rozema, J. H., & Bilardo, C. M. (2017) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.17487 · Cited by 113 · cited 1× · see citing works
“Furthermore, early scanning for fetal congenital anomalies is an essential component of modern pregnancy care in the cell-free DNA era [5].”
BackgroundYu, Z., Tan, E.-L., Ni, D., Qin, J., Chen, S., Li, S., Lei, B., & Wang, T. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2705031 · Cited by 109 · see citing works
Namburete, A. I. L., Xie, W., Yaqub, M., Zisserman, A., & Noble, J. A. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.02.006 · Cited by 95 · see citing works
Three dimensional ultrasound: abnormalities of the fetal face in surface and volume rendering mode
Lee, A., Deutinger, J., & BERNASCHEK, G. (1995) · BJOG An International Journal of Obstetrics & Gynaecology · doi:10.1111/j.1471-0528.1995.tb09136.x · Cited by 91 · see citing works
Abuhamad, A., Falkensammer, P., Reichartseder, F., & Zhao, Y. (2007) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.5228 · Cited by 69 · see citing works
Semi‐automated system for measurement of nuchal translucency thickness
Moratalla, J., Pintoffl, K., Minekawa, R., Lachmann, R., Wright, D., & Nicolaides, K. H. (2010) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.7737 · Cited by 64 · cited 1× · see citing works
“Although some semi-automatic and automatic systems involving 2D US have been developed for first trimester fetal evaluation [16,17,22,26], we presented a novel automatic MSP detection system with excellent accuracy.”
MethodTutschek, B., & Sahn, D. J. (2008) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.5403 · Cited by 43 · see citing works
Nie, S., Yu, J., Chen, P., Wang, Y., & Zhang, J. Q. (2017) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2016.08.034 · Cited by 42 · cited 1× · see citing works
“Although some semi-automatic and automatic systems involving 2D US have been developed for first trimester fetal evaluation [16,17,22,26], we presented a novel automatic MSP detection system with excellent accuracy.”
MethodReiff, E. S., Little, S. E., Dobson, L. J., Wilkins-Haug, L. E., & Bromley, B. (2016) · Prenatal Diagnosis · doi:10.1002/pd.4774 · Cited by 41 · see citing works
Abele, H., Hoopmann, M., Wright, D. E., Hoffmann-Pröll, B., Huettelmaier, M., Pintoffl, K., Wallwiener, D. R., & Kagan, K. O. (2010) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.8809 · Cited by 36 · cited 1× · see citing works
“The ideal plane is the main requirement for obtaining effective and repeatable measurements and maintaining inspection quality [9].”
BackgroundCraniofacial variability index in utero: a three‐dimensional ultrasound study
Roelfsema, N. M., Hop, W. C. J., van Adrichem, L. N. A., & Wladimiroff, J. W. (2007) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.3904 · Cited by 30 · cited 1× · see citing works
“Fetal structural measurements require that an expert obtain a standard plane, which is time consuming and subjective [10].”
BackgroundShould cell‐free DNA testing be used in pregnancy with increased fetal nuchal translucency?
Miranda, J., y Miño, F. P., Borobio, V., Bádenas, C., Rodríguez‐Revenga, L., Pauta, M., & BORRELL, A. (2019) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.20397 · Cited by 30 · see citing works
Effect of deviation from the mid‐sagittal plane on the measurement of fetal nuchal translucency
Abele, H., Wagner, N., Hoopmann, M., Grischke, E. ‐., Wallwiener, D. R., & Kagan, K. O. (2010) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.7599 · Cited by 28 · cited 2× · see citing works
“The optimal plane acquired in prenatal US is important for obtaining valid, precise, and reproducible measurements [8,22].”
BackgroundMethodMidsagittal plane extraction from brain images based on 3D SIFT
Wu, H., Wang, D., Shi, L., Wen, Z., & Ming, Z. (2014) · Physics in Medicine and Biology · doi:10.1088/0031-9155/59/6/1367 · Cited by 20 · cited 1× · see citing works
“Although some semi-automatic and automatic systems involving 2D US have been developed for first trimester fetal evaluation [16,17,22,26], we presented a novel automatic MSP detection system with excellent accuracy.”
MethodHow true is a ‘true’ midsagittal section?
Wah, Y. M. I., Chan, L. W., Leung, T. Y., Fung, T. Y., & Lau, T. K. (2008) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.6125 · Cited by 16 · cited 2× · see citing works
“reliable measurement and the basis for the nuchal translucency exam that provides a risk assessment for chromosomal aberrations in the first trimester [8].”
BackgroundSemi‐automated measurement of nuchal translucency thickness: blasphemy or oblation to quality?
Ville, Y. G. (2010) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.8810 · Cited by 12 · cited 1× · see citing works
“In the present study, we developed an accurate automatic system using deep learning to help resolve the problems encountered in conventional manual, two-dimensional (2D) methods [15].”
MethodAutomatic measurement of fetal Nuchal translucency from three-dimensional ultrasound data
Nie, S., Yu, J., Chen, P., Wang, Y., Guo, Y., & Zhang, J. Q. (2017) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2017.8037590 · Cited by 12 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- [2]Gorlin R. Cohen M. Levin L. Syndromes of the Head and the Neck Oxford University Press New York, NY, USA 1990
- [19]Arjovsky M. Chintala S. Bottou L. Wasserstein gan arXiv 2017 1701.07875
Cited by
Sorted by citations
A review on deep-learning algorithms for fetal ultrasound-image analysis
Fiorentino, M. C., Villani, F. P., Cosmo, M. D., Frontoni, E., & Moccia, S. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102629 · Cited by 209 · see citing works
“, [52] (2021) Middle sagittal plane 112 3D 28 3D ED = 0.”
Artificial intelligence in obstetric ultrasound: A scoping review.
Horgan, R., Nehme, L., & Abuhamad, A. (2023) · Prenatal Diagnosis · doi:10.1002/pd.6411 · Cited by 72 · see citing works
“sagittal plane of the fetus, with one study focusing on 2D ultrasound(19) and two studies on 3D ultrasound.(20,21) One study focused on three‐dimensional ultrasound in the first trimester to measure fetal biometry and to detect the presence of fetal limbs(22) and the final”
MethodJost, E., Kosian, P., Jimenez Cruz, J., Albarqouni, S., Gembruch, U., Strizek, B., & Recker, F. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12216833 · Cited by 44 · see citing works
“Tsai et al. aimed at facilitating the preliminary step for NT measurement, which was the automated detection of the correct mid-sagittal plane in 3D volumes [136], and Ryou et al. and Yang et al. proposed a model for the assessment of the whole fetus in 3D volumes [137,138].”
BackgroundFetalBrainAwareNet: Bridging GANs with anatomical insight for fetal ultrasound brain plane synthesis
Lasala, A., Fiorentino, M. C., Bandini, A., & Moccia, S. (2024) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2024.102405 · Cited by 29 · see citing works
Sriraam, N., Chinta, B., Seshadri, S., & Suresh, S. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11160-7 · Cited by 18 · see citing works
Artificial Intelligence in Imaging in the First Trimester of Pregnancy: A Systematic Review
Umans, E., Dewilde, K., Williams, H., Deprest, J. A., & den Bosch, T. V. (2024) · Fetal Diagnosis and Therapy · doi:10.1159/000538243 · Cited by 11 · see citing works
“The generator makes new examples and the discriminator clas-si fi es if the generated examples are “ real ” training data or “ fake ” data generated by the generator model [21, 57].”
InfluentialLiu, L., Wang, T., Zhu, W., Zhang, H., Tian, H., Li, Y., Cai, W., & Yang, P. (2025) · BMC Pregnancy and Childbirth · doi:10.1186/s12884-025-07863-y · Cited by 8 · see citing works
Detection of Fetal Cardiac Chamber Three Vessel Trachea View using Deep Learning
Sapitri, A. I., Nurmaini, S., Rini, D. P., Rachmatullah, M. N., Darmawahyuni, A., & Gusendi, A. (2022) · Proceeding of the Electrical Engineering Computer Science and Informatics · doi:10.23919/eecsi56542.2022.9946528 · Cited by 3 · see citing works
“The Faster R-CNNs model is a very good CNN model to perform the detection process in biomedical image processing [19][20].”
MethodZhang, Y., Huang, Y., Chen, C., Hu, X., Pan, W., Luo, H., Huang, Y., Wang, H., Cao, Y., Yi, Y., et al. (2025) · BMC Pregnancy and Childbirth · doi:10.1186/s12884-025-07823-6 · Cited by 2 · see citing works
Self-citationExamining Craniofacial and Velopharyngeal Structures in Premature Infants: A Window Into the Womb
Loomis-Goltl, E. I., Power, S. J., Neuberger, I., Barhaghi, K., & Kotlarek, K. J. (2024) · Journal of Craniofacial Surgery · doi:10.1097/scs.0000000000010390 · Cited by 1 · see citing works
Kwon, H., Hur, H., Cho, H. C., Jung, Y. J., Kim, S., & Kwon, J. (2026) · Journal of Ultrasound in Medicine · doi:10.1002/jum.70281 · Cited by 1 · see citing works
“Tsai et al 27 proposed a 2-stage framework combining DL-based seed point localization with Gener-ative Adversarial Network (GAN)-based MSP segmentation using a 3D binary mask.”
Psychological behavior Analysis in social media based on automated deep learning method
Shnawa, A. H., Ali, A., Hussien, N. A., Zaydan, N. R. W., Jaffer, Z., & Jawad, I. A. (2023) · Annual International Conference on Emerging Research Areas and International Conference on Microelectronics, Communications and Renewable Energy · doi:10.1109/aicera/icis59538.2023.10420058
“For example, similar work in social media on the idea of suicide is shown below, Pei-Yin Tsai et al. [23] recommended Automatic Fetal Middle Sagittal Plane Detection in Ultrasound Using Generative Adversarial Network (GAN) for Context and objective: The fetus's precise middle sagittal plane can be…”
BackgroundSriraam, N., Chinta, B., Suresh, S., & Sudharshan, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4812061
Automated Ultrasound Image Segmentation for Mid-Sagittal Plane Recognition Using Faster R-CNN
Sriraam, N., Mamatha, V. L., Chinta, B., Suresh, S., Raghavan, S., & Suresh, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14044-9_37
Liu, L., Wang, T., Li, Y., Tian, H., Zhang, H., Zhou, C., Zhu, W., & Cai, W. (2026) · The Ultrasound Journal · doi:10.5826/tuj.2026.18334
Deep Learning–Based Segmentation of Fetal Anatomical Structures in the First Trimester
Hong, S., Kim, O. H., Kang, B. S., Won, S., Ko, H. S., Byun, J. H., Wie, J. H., Kwon, J. Y., Lee, K. E., Shin, J. E., et al. (2026) · Prenatal Diagnosis · doi:10.1002/pd.70156
Tamara, Kaunang, F. J., Stefano, R., Thenata, A. P., & Hakim, B. (2026) · International Conference on Advancement in Data Science, E-learning and Information System (ICADEIS) · doi:10.1109/icadeis71120.2026.11644579
“Nevertheless, the study concentrated on plane localization and did not directly perform NT or nasal bone (NB) detection [14].”
Timor‐Tritsch, I. E., Monteagudo, A., & D’Antonio, F. (2026) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.70337
- Authors
- Tsai, P.-Y., Hung, C.-H., Chen, C.-Y., & Sun, Y.-N.
- Affiliations
- National Cheng Kung University Hospital (TW)
- National Cheng Kung University (TW)
- Corresponding author
- Chen, Chi-Yeh
- Sun, Yung-Nien
- Venue
- Diagnostics
- Publisher
- MDPI AG
- Published
- 2020-12-24
- Volume
- 11
- Issue
- 1
- Pages
- 21
- ISSN
- 2075-4418 (ISSN-L)
- PMC
- PMC7824131
- OpenAlex
- W3115188228
- Cited by
- 18
- References
- 24
- Citations by year
- 2026: 6 · 2025: 3 · 2024: 4 · 2023: 3 · 2022: 2
- FWCI
- 0.49
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Diagnostics (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, other-oa)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Ministry of Science and Technology, Taiwan (NSC 100-2314-B-006-013-MY3 and MOST 108-2634-F-006-005)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Engineering › Biomedical Engineering › Medical Imaging and Analysis
- Keywords
- 3D ultrasound, generative adversarial networks, seed point detection, fetal growth assessment, semi-automatic segmentation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
