Localisation of the Brain in Fetal MRI Using Bundled SIFT Features

Kevin Keraudren¹, Vanessa Kyriakopoulou², Mary Rutherford², Joseph V. Hajnal², and Daniel Rueckert¹

¹Biomedical Image Analysis Group, Imperial College London, UK

²Centre for the Developing Brain & Department Biomedical Engineering Division of Imaging Sciences, King’s College London, UK

Abstract. Fetal MRI is a rapidly emerging diagnostic imaging tool. Its main focus is currently on brain imaging, but there is a huge potential for whole body studies. We propose a method for accurate and robust localisation of the fetal brain in MRI when the image data is acquired as a stack of 2D slices misaligned due to fetal motion. We first detect possible brain locations in 2D images with a Bag-of-Words model using SIFT features aggregated within Maximally Stable Extremal Regions (called bundled SIFT), followed by a robust fitting of an axis-aligned 3D box to the selected regions. We rely on prior knowledge of the fetal brain development to define size and shape constraints. In a cross-validation experiment, we obtained a median error distance of 5.7mm from the ground truth and no missed detection on a database of 59 fetuses. This 2D approach thus allows a robust detection even in the presence of substantial fetal motion.

LNCS 8149, p. 582 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2013