Conference Paper

Automatic Segmentation of Head Structures on Fetal MRI

Inst. TELECOM, Telecom ParisTech, Paris, France
DOI: 10.1109/ISBI.2009.5192995 Conference: Biomedical Imaging: From Nano to Macro, 2009. ISBI '09. IEEE International Symposium on
Source: IEEE Xplore

ABSTRACT

Recent improvements of fetal MRI acquisitions now allow three-dimensional segmentation of fetal structures, to extract bio-metrical measures for pregnancy follow-up. Automation of the segmentation process remains a difficult challenge, given the complexity of the fetal organs and their spatial organization. As a starting point, we propose in this paper a fully automated segmentation method to localize the eyes and segment the skull bone content (SBC). Priors, embedding contrast, morphological and bio-metrical information, are used to assist the segmentation process. A validation of the proposed segmentation method, on 24 MRI volumes of fetuses between 30 and 35 gestational weeks, demonstrated a high accuracy for eyes and SBC extraction.

Full-text preview

Available from: telecom-paristech.fr
  • Source
    • "In contrast to adult brain studies, automatic segmentation of fetal brain has limited in research. Few semi-automatic [1] [2], automatic [3] [4] [5] [6] and atlas based [7] methods have been reported for segmentation of brain from fetal MRI. The existing fetal brain segmentation algorithms have both strengths and weaknesses, also varied in different anatomic regions. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Fetal MRI is an essential tool for analyzing morphological changes of fetal brain structure. The automated methods developed for adult brain extraction are unsuitable for fetal brain extraction because of the differences in tissue types and tissue properties between adult and fetal brain. However, only few automated fetal brain segmentation methods are available. In this paper we propose a fully automatic method to extract fetal brain. The proposed method finds an ROI that encloses the fetal brain, using the anatomical geometry. An intensity threshold is computed using Otsu’s method, from which a binary image is obtained for the ROI. Using anatomical knowledge the fetal brain is extracted. Experiments were performed on clinical in utero fetal MR volume and the results are validated against manual segmentation and quantified in terms of Dice (D) similarity coefficient, Sensitivity (S), Specificity (Sp) and Hausdorff distance (HD). The results emphasize the robustness of the method.
    Full-text · Article · Apr 2015
  • Source
    • "The system takes 8 min to run to segment eight brain structures. Anquez et al. [38] segment fetal eyes and skull bone content in MRI volumes. The eyes are first found by template matching. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Routine ultrasound exam in the second and third trimesters of pregnancy involves manually measuring fetal head and brain structures in 2-D scans. The procedure requires a sonographer to find the standardized visualization planes with a probe and manually place measurement calipers on the structures of interest. The process is tedious, time consuming, and introduces user variability into the measurements. This paper proposes an automatic fetal head and brain (AFHB) system for automatically measuring anatomical structures from 3-D ultrasound volumes. The system searches the 3-D volume in a hierarchy of resolutions and by focusing on regions that are likely to be the measured anatomy. The output is a standardized visualization of the plane with correct orientation and centering as well as the biometric measurement of the anatomy. The system is based on a novel framework for detecting multiple structures in 3-D volumes. Since a joint model is difficult to obtain in most practical situations, the structures are detected in a sequence, one-by-one. The detection relies on Sequential Estimation techniques, frequently applied to visual tracking. The interdependence of structure poses and strong prior information embedded in our domain yields faster and more accurate results than detecting the objects individually. The posterior distribution of the structure pose is approximated at each step by sequential Monte Carlo. The samples are propagated within the sequence across multiple structures and hierarchical levels. The probabilistic model helps solve many challenges present in the ultrasound images of the fetus such as speckle noise, signal drop-out, shadows caused by bones, and appearance variations caused by the differences in the fetus gestational age. This is possible by discriminative learning on an extensive database of scans comprising more than two thousand volumes and more than thirteen thousand annotations. The average difference between ground truth and automatic measurements is below 2 mm with a running time of 6.9 s (GPU) or 14.7 s (CPU). The accuracy of the AFHB system is within inter-user variability and the running time is fast, which meets the requirements for clinical use.
    Full-text · Article · May 2014
  • Source
    • "Related work: Fetal MRI is a relatively new field, with little work published on fully automatic processing of these datasets. In [5] [6], 3D template matching is used to detect the eyes, enabling a subsequent 2D/3D graph-cut segmentation to extract the brain. This approach based on 3D rigid templates lacks the flexibility necessary to deal with motion artifacts as well as fetal malformations. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Automatic detection of the fetal brain in Magnetic Resonance (MR) Images is especially difficult due to arbitrary orientation of the fetus and possible movements during the scan. In this paper, we propose a method to facilitate fully automatic brain voxel classification by means of rotation invariant volume descriptors. We calculate features for a set of 50 prenatal fast spin echo T2 volumes of the uterus and learn the appearance of the fetal brain in the feature space. We evaluate our novel classification method and show that we can localize the fetal brain with an accuracy of 100% and classify fetal brain voxels with an accuracy above 97%. Furthermore, we show how the classification process can be used for a direct segmentation of the brain by simple refinement methods within the raw MR scan data leading to a final segmentation with a Dice score above 0.90.
    Full-text · Conference Paper · Apr 2014
Show more