Create a Mathematical Model to Estimate the Weight of Iraqi Fetuses Using Ultrasound Images
DOI:
https://doi.org/10.61841/ghxd2g78Keywords:
Ultrasound Imaging, Pregnancy, Fetal Biometry, Estimated Fetal Weight ModelsAbstract
Background: Ultrasound (US) imaging is a medical imaging technique considered one of the most used techniques in hospitals and clinical centers around the world due to its being safe, economical, transferable, and adaptable. US imaging is used to diagnose human body parts and their functions. The most common use of US in pregnancy is to monitor the developments of fetuses and reveal abnormalities, estimate gestational age (GA), and estimate fetal weight (EFW). EFW is an important component of maternity health care, especially in the management and planning of the delivery mode. This will play a major role in newborn and maternal safety. EFW depends on the measurement of fetal biometry, such as abdominal circumference (AC), femur length (FL), bi-parietal diameter (BPD), and others. Accurate measurement of fetal biometry depends on the experience of sonographers. There are several models that were used to estimate fetal weight (EFW) depending on one or more biometrics of fetuses, but these models still give some errors in EFW in Iraq. So, this study has been carried out for creating the first EFW model for the first time in Iraq and the Middle East; a study is conducted to determine the weight of the fetus by finding a special mathematical model for the Iraqi fetuses. Depending on the US images taken from Iraqi hospitals, as will be explained in this search.
Methods: This study was performed in the department of Obstetrics and Gynecology in Al-Yarmouk Teaching Hospital and Al-Alawiya Teaching Hospital in Baghdad, Iraq, during 2019 on 200 pregnant women with singleton and normal pregnancies, fetal GA (36-40) weeks (W), and the last US scan was less than 7 days before birth. The obtained dataset (fetal biometry and actual birth weight (ABW)) was utilized to develop EFW using the IBM SPSS Version 23 software package (software).
Results: Statistical analysis indicated that there was a significant difference between the ABW and EFW using most weight estimation models. Only our proposed model and the Hadlock2 model produced acceptable results, where the correlation between ABW and EFW by the proposed model was R = 0.964 and by the Hadlock2 model was R = 0.920, while it extremely declined when using other models and showed less correlation. By using the Hsieh model, R=0.330; by using the Woo model, R=0.236; and by using the Jordaan model, R=0.667.
Conclusion: The proposed model and Hadlock2 model produce results better than other models in EFW for Iraqi pregnant women, but depending on the absolute mean error (AME), absolute percentage error (APE), and R value, we conclude that the proposed model was the best model for EFW in Iraq and gave the most acceptable results compared with ABW.
Downloads
References
[1] Karimi, Moghaddam, Naematollahi and Rezazadeh, 2008, “In Vitro Ultrasonography of the Normal Sheep
Heart,” Pakistan Vet. J., Vol. 28, No. 2, pp. 92-94.
[2] P. Loughna, L. Chitty, T. Evans, and T. Chudleigh, 2009, “Fetal size and dating: charts recommended for
clinical obstetric practice,” Ultrasound, Vol. 17, No. 3, pp. 160–166.
[3] Ramya, K Srinivasan, Pavithra Devi, Preethi, and Poonkuzhali, 2018, " Perinatal Fetal Weight
Detection Using Image Processing," International Journal of Scientific & Technology Research, Vol. 7,
No. 8, pp. 37-39.
[4] Bajracharya J, Shrestha N S, Karki C., 2012, "Accuracy of prediction of birth weight by fetal Ultrasound,"
Nepal Med Coll Journal, Vol. 38, No. 2, pp. 74–5.
[5] Sylvia Rueda, Sana Fathima, Caroline Knight, Julia Alison Noble, 2014, “Evaluation and comparison of
current fetal ultrasound image segmentation methods for biometric measurements: a grand challenge,”
IEEE Trans. Med. Imaging, Vol. 33, No. 4, pp. 797–813.
[6] Muhammad Shahin Uddin, Kalyan Kumar Halder, Murat Tahtali, Andrew J. Lambert, Mark R., 2016,
“Intelligent estimation of noise and blur variances using ANN for the restoration of ultrasound images,”
Appl. Opt., Vol. 55, No. 31, pp. 8905–8915.
[7] Khalid Shehzad, Moazzam Ali, and Shahida Zaidi, 2006 “Fetal Biometry,” Pakistan Journal of Medical
Sciences, Vol. 22, No. 4, pp. 503-508.
[8] Mahboobeh Shirazi, Shirin Niroomanes, Fatemeh Rahimi, and Fatemeh Golshahi, 2019, "Ultrasound
Assessment of Fetal Biometry in Iranian Normal Pregnancies," International Journal of Preventive
Medicine, pp. 1-6.
[9] Sujitkumar S. Hiwale, Hemant Misra, and Shrutin Ulman, 2017, " Ultrasonography-based Fetal Weight
Estimation: Finding an Appropriate Model for an Indian Population," Journal of Medical Ultrasound, Vol.
25, No. 1, pp. 24-32.
[10] Sujitkumar Hiwale, Hemant Misra, and Shrutin Ulman, 2019, "Fetal weight estimation by ultrasound:
development of Indian population-based models," Journal of Medical Ultrasound, Vol. 38, No. 1, pp. 50-57.
[11] Loc Nguyen, Truong-Duyet Phan, and Thu-Hang T. Ho, 2018, "Phoebe Framework and Experimental Results for Estimating Fetal Age and Weight," http://dx.doi.org/10.5772/intechopen.74883.
[12] Citations and Reads, 2018, "Foetal weight prediction models at a given gestational age in the absence of ultrasound facilities: Application in Indonesia," BMC Pregnancy and Childbirth, Vol. 18, No. 436, pp. 1-12.
[13] S. C. Westerway, 2012, “Estimating fetal weight for best clinical outcome,” Australian Journal of Ultrasound in Medicine, Vol. 15, No. 1, pp. 13–17.
Downloads
Published
Issue
Section
License
Copyright (c) 2020 AUTHOR

This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.