Objective: To assess the role of ultrasound (US) in the diagnosis of biliary atresia. Methodology: Fasting infants with conjugated hyperbilirubinemia were subjected for US examination in Hospital Sultanah Bahiyah, Kedah. The patients were grouped into biliary atresia (BA) and non-biliary atresia (non-BA) based on the surgical findings and clinical follow up. The following features were recorded: tri-angular cord sign, gall bladder morphology, liver size, and echotexture, splenic size, hepatic artery size, hepatic artery to portal vein ratio, presence of a common bile duct, and presence of subcapsular flow on colour Doppler. Sensitivity, specificity, positive and negative predictive values were calculated for each US variable. BA and non-BA groups were compared by using the Fisher exact test for categorical variables and an unpaired t test for continues variable. Results: A total of 82 infants were included in the study; 42 had surgically confirmed BA and 40 had other documented causes of neonatal jaundice. Nine US features showed a significant different between BA and non-BA group. Ultrasound able to correctly classified 82 infants into BA and non-BA group with 98% accuracy. Conclusions: BA can be diagnosed with US from other cause of conjugated hyperbilirubinemia in 98% of patients if multiple US features are carefully evaluated. These ultrasound variables may serve as independent predictors of BA.