Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 21, Issue 1
  5. Article
Volume 21, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
file format text download EPUB
side by side viewer icon HTML

Abstract

Aim

This research aims to develop and evaluate a novel health classification and severity detection system based on Vision Transformers (ViTs) for fetal ultrasound imagery. This contributes to improved precision in fetal health status detection and abnormalities with more accurate results than other traditional models.

Background

Amidst the other imperatives of resource-deficient developing nations, mitigating neonatal mortality rates is a challenge that demands precision-based solutions in the era of artificial intelligence. Though the advent of machine learning models has added an optimal dimension to deal with emerging complexity in fetal ultrasound imagery, there is a call to address the huge gap in the demanded precision for prediction than the existing interpretation.

Objective

This research strives to formulate and access a novel health classification and severity detection system based on the implementation of the Vision Transformers frameworks. This pioneering investigation represents an unparalleled exploration into the efficacy of ViTs for discerning intricate patterns within fetal ultrasonographic imagery, facilitating precise categorization of fetal well-being and prognosticating the magnitude of potential anomalies.

Methodology

A private and confidential dataset of 500 fetal ultrasound images has been collected from diverse hospitals. Each image has been annotated by radiologists according to two main labels: the health status of the fetus, which includes healthy, mild, moderate, or severe, and the severity of abnormalities as a continuous measure. At different levels, the dataset underwent pre-processing via distinct techniques. Then, the composite loss function Cross-Entropy has been deployed to train the optimized VIT model using the Adam algorithm.

Results

The classification accuracy of the proposed model is 90% for detecting the severity with an F1-score of 0.87 and MAE of 0.30. The research ascertained that the model ViT evinced a superlative efficacy for the capturing of fine-grained spatial relations in ultrasound images to produce revolutionary predictions.

Conclusion

These results emphasize that ViTs have the potential to revolutionize fetal health monitoring and will contribute significantly to reducing neonatal mortality by supplying clinicians with accurate and reliable predictions for early interventions. This work stands as a yardstick for further diagnostic applications using AI in fetal health care.

© 2025 The Author(s).
© 2025 The Author(s). Published by Bentham Science Publishers. This is an open access article published under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/legalcode
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056360199250227053012
2025-01-01
2025-07-03

  • From This Site

    /content/journals/cmir/10.2174/0115734056360199250227053012
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. GribbinC. JamesD. Assessing fetal health.Curr. Obstet. Gynaecol.200515422122710.1016/j.curobgyn.2005.05.001
     [Google Scholar]
  2. SaliniY. MohantyS.N. RameshJ.V.N. YangM. ChalapathiM.M.V. Cardiotocography data analysis for fetal health classification using machine learning models.IEEE Access202412260052602210.1109/ACCESS.2024.3364755
     [Google Scholar]
  3. XieH.N. WangN. HeM. ZhangL.H. CaiH.M. XianJ.B. LinM.F. ZhengJ. YangY.Z. Using deep‐learning algorithms to classify fetal brain ultrasound images as normal or abnormal.Ultrasound Obstet. Gynecol.202056457958710.1002/uog.2196731909548
     [Google Scholar]
  4. FarleyD. DudleyD.J. Fetal assessment during pregnancy.Pediatr. Clin. North Am.200956348950410.1016/j.pcl.2009.03.00119501688
     [Google Scholar]
  5. MehbodniyaA. LazarA.J.P. WebberJ. SharmaD.K. JayagopalanS. KK. SinghP. RajanR. PandyaS. SenganS. Fetal health classification from cardiotocographic data using machine learning.Expert Syst.2022396e1289910.1111/exsy.12899
     [Google Scholar]
  6. AlzubaidiM. AgusM. AlyafeiK. AlthelayaK.A. ShahU. Abd-AlrazaqA. AnbarM. MakhloufM. HousehM. Toward deep observation: A systematic survey on artificial intelligence techniques to monitor fetus via ultrasound images.iScience202225810471310.1016/j.isci.2022.10471335856024
     [Google Scholar]
  7. SivariE. CivelekZ. SahinS. Determination and classification of fetal sex on ultrasound images with deep learning.Expert Syst. Appl.202424012250810.1016/j.eswa.2023.122508
     [Google Scholar]
  8. SridarP. KumarA. QuintonA. NananR. KimJ. KrishnakumarR. Decision fusion-based fetal ultrasound image plane classification using convolutional neural networks.Ultrasound Med. Biol.20194551259127310.1016/j.ultrasmedbio.2018.11.01630826153
     [Google Scholar]
  9. SantosoA.P. SigitR. Health monitoring of fetal ultrasound image using active contour models.2017 International Seminar on Application for Technology of Information and Communication (iSemantic)Semarang, Indonesia, 07-08 October 2017, pp. 192-197.10.1109/ISEMANTIC.2017.8251868
     [Google Scholar]
  10. AvazovK. AbdusalomovA. MukhiddinovM. BaratovN. MakhmudovF. ChoY.I. An improvement for the automatic classification method for ultrasound images used on CNN.Int. J. Wavelets Multiresolution Inf. Process.2022202215005410.1142/S0219691321500545
     [Google Scholar]
  11. CarneiroG. GeorgescuB. GoodS. ComaniciuD. Detection and measurement of fetal anatomies from ultrasound images using a constrained probabilistic boosting tree.IEEE Trans. Med. Imaging20082791342135510.1109/TMI.2008.92891718753047
     [Google Scholar]
  12. RyouH. YaqubM. CavallaroA. PapageorghiouA.T. Alison NobleJ. Automated 3D ultrasound image analysis for first trimester assessment of fetal health.Phys. Med. Biol.2019641818501010.1088/1361‑6560/ab3ad131408850
     [Google Scholar]
  13. LinB. Quality assessment of fetal head ultrasound images based on faster R-CNN.Simulation, Image Processing, and Ultrasound Systems for Assisted Diagnosis and NavigationSpringer, Cham, 15 September 2018, pp 38–46.10.1007/978‑3‑030‑01045‑4_5
     [Google Scholar]
  14. ParkN. KimS. How do vision transformers work?ICLR 2022 - 10th Int. Conf. Learn. Represent2022
     [Google Scholar]
  15. KatharopoulosA. VyasA. PappasN. FleuretF. Transformers are {RNN}s: Fast autoregressive transformers with linear attention.Proceedings of the 37th International Conference on Machine Learning13 July 2020, pp. 5156 - 5165.
     [Google Scholar]
  16. LiuY. WangC. LuM. YangJ. GuiJ. ZhangS. From simple to complex scenes: Learning robust feature representations for accurate human parsing.IEEE Trans. Pattern Anal. Mach. Intell.20244685449546210.1109/TPAMI.2024.336676938363663
     [Google Scholar]
  17. Al-hammuriK. GebaliF. KananA. ChelvanI.T. Vision transformer architecture and applications in digital health: A tutorial and survey.Vis. Comput. Ind. Biomed. Art2023611410.1186/s42492‑023‑00140‑937428360
     [Google Scholar]
  18. GhabriH. AlqahtaniM.S. Ben OthmanS. Al-RasheedA. AbbasM. AlmubarakH.A. SakliH. AbdelkarimM.N. Transfer learning for accurate fetal organ classification from ultrasound images: A potential tool for maternal healthcare providers.Sci. Rep.20231311790410.1038/s41598‑023‑44689‑037863944
     [Google Scholar]
  19. DasS. MukherjeeH. RoyK. SahaC.K. Fetal health classification from cardiotocograph for both stages of labor—a soft-computing-based approach.Diagnostics202313585810.3390/diagnostics1305085836900002
     [Google Scholar]
  20. KhedrO.S. WahedM.E. Al-AttarA.S.R. Abdel-RehimE.A. The classification of the bladder cancer based on vision transformers (ViT).Sci. Rep.20231312063910.1038/s41598‑023‑47992‑y38001352
     [Google Scholar]
  21. HarikumarA. SurendranS. GargiS. Explainable AI in deep learning based classification of fetal ultrasound image planes.Procedia Comput. Sci.20242331023103310.1016/j.procs.2024.03.291
     [Google Scholar]
  22. LiJ. LiuX. Fetal health classification based on machine learning.2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE)Nanchang, China, 26-28 March 2021, pp. 899-902.10.1109/ICBAIE52039.2021.9389902
     [Google Scholar]
  23. NoorN.F.M. AhmadN. NoorN.M. Fetal health classification using supervised learning approach.2021 IEEE National Biomedical Engineering Conference (NBEC)Kuala Lumpur, Malaysia, 09-10 November 2021, pp. 36-41.10.1109/NBEC53282.2021.9618748
     [Google Scholar]
  24. KASIMÖ. Multi-classification of fetal health status using extreme learning machine.Icontech Int. J.2021526270
     [Google Scholar]
  25. QuR. XuG. DingC. JiaW. SunM. Deep learning-based methodology for recognition of fetal brain standard scan planes in 2D ultrasound images.IEEE Access20208444434445110.1109/ACCESS.2019.2950387
     [Google Scholar]
  26. FiorentinoM.C. VillaniF.P. Di CosmoM. FrontoniE. MocciaS. A review on deep-learning algorithms for fetal ultrasound-image analysis.Med. Image Anal.20238310262910.1016/j.media.2022.10262936308861
     [Google Scholar]
  27. DosovitskiyA. An image is worth 16x16 words: Transformers for image recognition at scale.ArXiv2020
     [Google Scholar]
  28. JoiceC.S. SrinivasanC. SridharP. Feature selection and classification to detect fetal abnormalities.Soft Computing: Theories and Applications. KumarR. VermaA.K. VermaO.P. WadehraT. SingaporeSpringer Nature Singapore202423925110.1007/978‑981‑97‑2089‑7_22
     [Google Scholar]
  29. OvadiaO. KahanaA. StinisP. TurkelE. GivoliD. KarniadakisG.E. ViTO: Vision transformer-operator.Comput. Methods Appl. Mech. Eng.202442811710910.1016/j.cma.2024.117109
     [Google Scholar]
  30. MulitaF. VerrasG.I. AnagnostopoulosC.N. KotisK. A smarter health through the internet of surgical things.Sensors20222212457710.3390/s2212457735746359
     [Google Scholar]
  31. MengQ. RueckertD. Unsupervised cross-domain image classification by distance metric guided feature alignment.Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis: First International Workshop, ASMUS 2020, and 5th International Workshop, PIPPI 2020, Held in Conjunction with MICCAI 2020Lima, Peru, 04 October 2020, pp. 146–157.
     [Google Scholar]
  32. MonteroA. Bonet-CarneE. Burgos-ArtizzuX.P. Generative adversarial networks to improve fetal brain fine-grained plane classification.Sensors20212123797510.3390/s2123797534883977
     [Google Scholar]
  33. ChenH. Ultrasound standard plane detection using a composite neural network framework.IEEE Trans Cybern20174761576158610.1109/TCYB.2017.2685080
     [Google Scholar]
  34. PuB. LiK. LiS. ZhuN. Automatic fetal ultrasound standard plane recognition based on deep learning and IIoT.IEEE Trans. Industr. Inform.202117117771778010.1109/TII.2021.3069470
     [Google Scholar]
  35. LeeL.H. GaoY. NobleJ.A. Principled ultrasound data augmentation for classification of standard planes.International Conference on Information Processing in Medical ImagingSpringer, Cham, 14 June 2021, pp 729–741.10.1007/978‑3‑030‑78191‑0_56
     [Google Scholar]
  36. DongJ. LiuS. LiaoY. WenH. LeiB. LiS. WangT. A generic quality control framework for fetal ultrasound cardiac four-chamber planes.IEEE J. Biomed. Health Inform.202024493194210.1109/JBHI.2019.294831631634851
     [Google Scholar]
  37. BaumgartnerC.F. KamnitsasK. MatthewJ. FletcherT.P. SmithS. KochL.M. KainzB. RueckertD. SonoNet: Real-time detection and localisation of fetal standard scan planes in freehand ultrasound.IEEE Trans. Med. Imaging201736112204221510.1109/TMI.2017.271236728708546
     [Google Scholar]
  38. YaqubM. KellyB. PapageorghiouA.T. NobleJ.A. A deep learning solution for automatic fetal neurosonographic diagnostic plane verification using clinical standard constraints.Ultrasound Med. Biol.201743122925293310.1016/j.ultrasmedbio.2017.07.01328958729
     [Google Scholar]
  39. SchlemperJ. OktayO. SchaapM. HeinrichM. KainzB. GlockerB. RueckertD. Attention gated networks: Learning to leverage salient regions in medical images.Med. Image Anal.20195319720710.1016/j.media.2019.01.01230802813
     [Google Scholar]
  40. Burgos-ArtizzuX.P. Coronado-GutiérrezD. Valenzuela-AlcarazB. Bonet-CarneE. EixarchE. CrispiF. GratacósE. Evaluation of deep convolutional neural networks for automatic classification of common maternal fetal ultrasound planes.Sci. Rep.20201011020010.1038/s41598‑020‑67076‑532576905
     [Google Scholar]
  41. SundaresanJ.A. Automated characterization of the fetal heart in ultrasound images using fully convolutional neural networks.2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)Melbourne, VIC, Australia, 18-21 April 2017, pp. 671-674.10.1109/ISBI.2017.7950609
     [Google Scholar]
  42. TanB. Semi-supervised learning of fetal anatomy from ultrasound.Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect DataSpringer, Cham, 13 October 2019, pp 157–164.10.1007/978‑3‑030‑33391‑1_18
     [Google Scholar]
  43. CaiY. SharmaH. ChatelainP. NobleJ.A. Multi-task sonoeyenet: Detection of fetal standardized planes assisted by generated sonographer attention maps.International Conference on Medical Image Computing and Computer-Assisted InterventionSpringer, Cham, 26 September 2018, pp 871–879.10.1007/978‑3‑030‑00928‑1_98
     [Google Scholar]
  44. QuR. XuG. DingC. JiaW. SunM. Standard plane identification in fetal brain ultrasound scans using a differential convolutional neural network.IEEE Access20208838218383010.1109/ACCESS.2020.2991845
     [Google Scholar]
  45. DouD. Agent with warm start and active termination for plane localization in 3D ultrasound.International Conference on Medical Image Computing and Computer-Assisted InterventionSpringer, Cham, 10 October 2019, pp 290–298.10.1007/978‑3‑030‑32254‑0_33
     [Google Scholar]
  46. LiangB. SPRNet: Automatic fetal standard plane recognition network for ultrasound images.Smart Ultrasound Imaging and Perinatal, Preterm and Paediatric Image Analysis.Springer, Cham, 08 October 2019, pp 38–46.10.1007/978‑3‑030‑32875‑7_5
     [Google Scholar]
  47. GaoY. BeriwalS. CraikR. PapageorghiouA.T. NobleJ.A. Label efficient localization of fetal brain biometry planes in ultrasound through metric learning.Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis.Springer, Cham, 01 October 2020, pp 126–135.10.1007/978‑3‑030‑60334‑2_13
     [Google Scholar]
  48. KomatsuM. SakaiA. KomatsuR. MatsuokaR. YasutomiS. ShozuK. DozenA. MachinoH. HidakaH. ArakakiT. AsadaK. KanekoS. SekizawaA. HamamotoR. Detection of cardiac structural abnormalities in fetal ultrasound videos using deep learning.Appl. Sci.202111137110.3390/app11010371
     [Google Scholar]
  49. ZhangB. LiuH. LuoH. LiK. Automatic quality assessment for 2D fetal sonographic standard plane based on multitask learning.Medicine20211004e2442710.1097/MD.0000000000024427
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056360199250227053012
Loading
Fetal Diagnostics using Vision Transformer for Enhanced Health and Severity Prediction in Ultrasound Imaging
Curr. Med. Imaging 21, E15734056360199 (2025); https://doi.org/10.2174/0115734056360199250227053012
/content/journals/cmir/10.2174/0115734056360199250227053012
/content/journals/cmir/10.2174/0115734056360199250227053012
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Fetal anomaly detection; Fetal health classification; Prenatal diagnosis; Severity detection; Transformer; Ultrasound images

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test