Image Classification for Ultrasound Fetal Images with Increased Nuchal Translucency during First Trimester Using SVM Classifier

Increased Nuchal Translucency is an indicator of increased risk for Down syndrome, which is identified by measuring Nuchal Translucency from ultrasound fetal images during 11 to 13 weeks of gestation. Increased NT is associated with chromosomal abnormalities. In this study an efficient classification system based on Discrete Wavelet Transform (DWT) is proposed to detect the normal and abnormal images with NT. Feature extraction is an essential pre-processing step for pattern recognition and machine learning problems. In order to classify the ultrasound image accurately, the texture features must be extracted effectively. In the proposed system, wavelet band signature, energy is used as features to classify the ultrasound image for the detection of Down syndrome using Support Vector Machine (SVM) classifier. The experimental results of pre diagnosed database with Discrete wavelet Transform and SVM classifier give best results for classification of Down Syndrome images with Normal NT and abnormal NT.