The genetic disorder of foetus leads to the formation of Down Syndrome (DS) which can be screened manually by screening the first and second trimester ultra sonogram images. This can be fully automated with the help of computer-aided approaches proposed in this paper. The DS can be screened by enhancing the foetus image using Adaptive histogram equalization technique. Then, Gabor multi resolution transform is applied on the enhanced foetus image in order to convert the spatial domain foetus image into multi resolution foetus image. The features as Effective Binary Pattern (EBP), Grey Level Occurrence Matrix (GLCM) and Local Derivative Pattern (LDP) are extracted from the enhanced Gabor transformed foetus image and then these features are trained and classified using Adaptive Neural Fuzzy Inference System (ANFIS) classifier, which classifies the foetus image into either normal or abnormal. Further, morphological-based segmentation technique is applied on the abnormal classified foetus image to segment the nasal bone region. The segmented nasal bone region is compared with clinical diagnosis results to detect DS in foetus image. The performance of the proposed DS detection system is analyzed in terms of sensitivity, specificity, positive predictive value, negative predictive value and accuracy
Digital Object Identifier (DOI)
Saranya, S. and Sudha, S.
"Certain Mathematical Investigations on Prenatal Down Syndrome Detection using ANFIS Classification Approach,"
Applied Mathematics & Information Sciences: Vol. 14:
1, Article 13.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol14/iss1/13