Correlation of Ultrasonographic Estimation of Fetal Weight with Actual Birth Weight as Seen in a Private Specialist Hospital in South East Nigeria

M., Arvind K. S.. Predictive Assessment of Fetus Features Using Scanned Image Segmentation Techniques and Deep Learning Strategy

Fetus weight at various stages of pregnancy is a critical component in determining the health of the baby. Abnormalities arising early in the pregnancy may be prevented by preventive measures. A variety of techniques suggested to predict foetus weight. Computer vision is a capability that can estimate the weight of a baby based on ultra-sonograms taken at various stages of pregnancy. Using the scanned data, one may train an advanced convolutional neural network that helps in accurately forecasting the fetus's size, weight, and overall health. The research utilizes computer vision techniques with image clustering methods for preprocessing, to predict the foetus's health, training datasets defective foetus datasets and healthy foetus datasets. Developing an integrated computer vision and a deep neural network is the hour which decrease the cost of operations and manual processes This study estimate the fetus's weight with optimal accuracy range at varying gestation age.

Accuracy of Fetal Weight Estimation by Ultrasonographic Evaluation in a Northeastern Region of India

Methods

The cross-sectional study included 100 pregnant women aged 20–45 years from the Kamrup district admitted to Guwahati Medical College and Hospital, Guwahati, Assam. The data were analyzed using Microsoft Excel and SPSS version 16. The EFW at term was calculated using Shepard's formula and Hadlock's formula. Differences in means are compared using the one-way ANOVA or Kruskal–Wallis test and paired t-test. The accuracy of the two procedures was evaluated using mean absolute error (MAE) and mean absolute percentage error (MAPE). A p value<0.05 was considered significant.

Results

The present study included 100 pregnant women aged 21–38 years with term or postterm pregnancies subjected to ultrasonographic evaluation within 72 hours of delivery. The mean (±s.d.) EFW by Shepard's formula was 2716.05 (±332.38) g and Hadlock's formula was 2740.44 (±353.23) g, respectively. For Hadlock's formula, MAE ± s.d. was found to be higher (overall 84.59 ± 76.54) specifically in the weight category less than 2500 (106.42 ± 88.11) as compared to Shepard's (overall MAE ± s.d = 79.86 ± 64.78, and among ABW < 2500 g, MAE ± s.d = 65.04 ± 61.02). The overall MAPE of Hadlock's formula was 3.14% and that for Shepard's formula was 2.91%, and the difference was not statistically significant. Both Shepard's formula and Hadlock's formula had a sensitivity of 92.85% in detecting IUGR, but Hadlock's method had higher specificity (66%), higher PPV (86.67%), and higher NPV (80%).

Conclusion

The ultrasonographic evaluation of fetal weight helps predict fetal birth weight precisely and can influence obstetric management decisions concerning timing and route of delivery, thus reducing perinatal morbidity and mortality.