Fetal echocardiography is a standard diagnostic tool used to evaluate and monitor fetuses with a defective heart associated with a number of fetal conditions. Deep learning is a machine learning technology which can perform specific tasks with specific goals. Deep learning techniques are used to evaluate fetal cardiac ultrasound cine loops and improve the evaluation of fetal abnormalities. Convolutional neural network along with recurrent neural network was applied in this study as CNN + LSTM, CNN + GRU, and 3D CNN for the processing and classification of ultrasonographic cine loops into various classes. The models were able to sort the fetal cardiac cine loops into five standard views with 92.63%, 94.99%, and 82.69% accuracy, respectively. Furthermore, the models were able to diagnose Tricuspid atresia (TA) and Hypoplastic left heart syndrome (HLHS) with an accuracy of 94.61%, 91.99%, and 86.54%, respectively. These deep learning-based algorithms were found to be effective tools for evaluating and monitoring normal and abnormal fetal heart cine loops.