Fetal brain magnetic resonance imaging (MRI) is a rapidly emerging diagnostic imaging tool. However, automated fetal brain\nlocalization is one of the biggest obstacles in expediting and fully automating large-scale fetal MRI processing.We propose amethod\nfor automatic localization of fetal brain in 3 T MRI when the images are acquired as a stack of 2D slices that are misaligned due\nto fetal motion. First, the Histogram of Oriented Gradients (HOG) feature descriptor is extended from 2D to 3D images. Then, a\nsliding window is used to assign a score to all possible windows in an image, depending on the likelihood of it containing a brain,\nand the window with the highest score is selected. In our evaluation experiments using a leave-one-out cross-validation strategy,\nwe achieved 96% of complete brain localization using a database of 104 MRI scans at gestational ages between 34 and 38 weeks.We\ncarried out comparisons against templatematching and randomforest based regressionmethods and the proposed method showed\nsuperior performance.We also showed the application of the proposed method in the optimization of fetal motion correction and\nhow it is essential for the reconstruction process. The method is robust and does not rely on any prior knowledge of fetal brain\ndevelopment.
Loading....