Notwithstanding all of our current knowledge, cutting-edge diagnostic tools, computerised databases, and other readily available supporting resources, fetal syndrome detection continues to be a challenge for healthcare professionals both in prenatal and postnatal periods. The early treatment of fetal disorders is a difficult puzzle to put together and solve. One anomaly should always raise concerns about the existence of everyone else, and it may act as a spur for further research and increased awareness of other disorders. The measurement of the standardized plane is necessary for biometric assessment and diagnosis during an ultrasound (US) examination. Based on a review of existing algorithms for autonomously monitoring fetal development, a unique genetic algorithm named Neuro-Fuzzy was developed. First, the benchmark image from the fetal ultrasound is automatically pre-processed to use the Normal Shrink Elliptic curve method. Second, to extract features, Rotation Invariant Moments (RIM), Intensity Histogram (IH), and Gray Level Co-occurrence Matrix (GLCM) are utilized (IM). Finally, a genetically based Neuro-Fuzzy approach is used to distinguish between abnormal and normal prenatal growth. When compared to state-of-the-art approaches, experimental results using a benchmark and actual dataset reveal that the suggested strategy achieves 97% accuracy in terms of parameters like Sensitivity, Specificity, Recall, F-Measure, and Precision Rate. The Support Vector Machine (SVM) achieved the highest accuracy rate of 95.7 percent in comparison to certain other classification methods such as KNN, Ensemble methods, Linear Discriminate Analysis (LDA), and Decision Tree, the with ROC curve covering 0.97 SVM. The area underneath the receiver of characteristics (AUC) and the confusion matrix are also used as assessment indicators.