Abstract #0714

Automatic fetal ocular measurements in MRI

Netanell Avisdris^1,2, Daphna Link-Sourani², Liat Ben-Sira^3,4,5, Leo Joskowicz¹, Elka Miller⁶, and Dafna Ben-Bashat^2,3,5

¹School of computer science and engineering, Hebrew University of Jerusalem, Jerusalem, Israel, ²Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel, ³Sagol School of Neuroscience, Tel Aviv University, Tel Aviv, Israel, ⁴Division of Pediatric Radiology, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel, ⁵Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel, ⁶Medical Imaging, Children's Hospital of Eastern Ontario, University of Ottawa, Ottawa, ON, Canada

The aim of this study was to establish a fully automatic method for ocular measurements from in-vivo fetal brain MRI. Axial brain MRI of 47 fetuses (29-38 weeks’ gestational age) were included. The method includes fetal brain ROI computation and fetal eye segmentation using deep learning, followed by geometric algorithms for 2D and 3D measurements of the binocular (BOD), interocular (IOD), and ocular (OD) diameters. The performance of the 2D measurements was found to be preferable over 3D, with <1mm deviation from manual expert neuro-radiologist annotations. This is the first fully automatic method for fetal ocular biometric measurements in MRI.

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

Join Here