This document presents a new non-invasive method for early detection of Down syndrome by identifying the absence of the fetal nasal bone during the first trimester through ultrasound imaging and artificial neural networks. The proposed approach employs image processing algorithms and a back-propagation neural network to enhance accuracy, reduce operator error, and improve overall detection rates. By extracting features in both spatial and transform domains, the method demonstrates a higher classification rate compared to existing non-invasive screening methods.