An Algorithm for Medical Specialists to Assist in the Diagnosis of Down Syndrome Using Nasal Bone Location in Ultrasound Images

Down syndrome is a genetic disorder caused by the presence of an additional chromosome at position 21, also known as trisomy 21. This condition leads to intellectual disability and affects the physical and cognitive development of the child. For early diagnosis, medical specialists consider two key parameters: the absence or presence of the nasal bone and the size of the nuchal translucency. These assessments are typically conducted between 11–13 weeks of the 1^st trimester of gestation using ultrasound imaging. In this paper we propose an algorithm to assist in the diagnosis of Down Syndrome by detecting the presence of nasal bone using a data-independent algorithm. The image processing pipeline consists of segmentation procedures developed grouping higher intensity pixels with similar features and detecting the nasal bone based on pattern recognition using geometrical features. The algorithm was tested with 45 images captured locally, 43 of which are normal cases and 2 are Down Syndrome obtaining an accuracy of 84% and the evaluation was carried out with an ultrasound specialist doctor.