Abstract #4649

Application of radiomics for predicting poor psychomotor outcome in preterm neonates using brain MRI

You Won Shin¹, Taehoon Shin¹, Yoon Ho Nam^2,3, and Hyun Gi Kim²

¹Division of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul, Korea, Republic of, ²Department of Radiology, Eunpyeong St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea, Republic of, ³Department of Radiology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea, Republic of

To predict poor psychomotor development in preterm neonates who underwent MRI at term-equivalent age, we implemented radiomics feature analysis of white matter on T1-and T2-weighted images. A total 1920 features were derived, and optimal number of features were selected. The area under the ROC curve (AUC) for the diagnostic abilities of the radiomics analysis were 0.657, 0.814, and 0.690, using T1-weighted images, T2-weighted images, and both T1- and T2-weighted images, respectively. In conclusion, radiomics for term-equivalent age brain MRI can be useful for predicting poor psychomotor outcome in preterm neonates.

This abstract and the presentation materials are available to members only; a login is required.

Join Here