Kevin Keraudren

Fast Volume Reconstruction From Motion Corrupted Stacks of 2D Slices

Capturing an enclosing volume of moving subjects and organs using fast individual image slice acquisition has shown promise in dealing with motion artefacts. Motion between slice acquisitions results in spatial inconsistencies that can be resolved by slice-to-volume reconstruction (SVR) methods to provide high quality 3D image data. Existing algorithms are, however, typically very slow, specialised to specific applications and rely on approximations, which impedes their potential clinical use. In this paper, we present a fast multi-GPU accelerated framework for slice-to-volume reconstruction. It is based on optimised 2D/3D registration, super-resolution with automatic outlier rejection and an additional (optional) intensity bias correction. We introduce a novel and fully automatic procedure for selecting the image stack with least motion to serve as an initial registration target. We evaluate the proposed method using artificial motion corrupted phantom data as well as clinical data, including tracked freehand ultrasound of the liver and fetal Magnetic Resonance Imaging. We achieve speed-up factors greater than 30 compared to a single CPU system and greater than 10 compared to currently available state-of-the-art multi-core CPU methods. We ensure high reconstruction accuracy by exact computation of the point-spread function for every input data point, which has not previously been possible due to computational limitations. Our framework and its implementation is scalable for available computational infrastructures and tests show a speed-up factor of 1.70 for each additional GPU. This paves the way for the online application of image based reconstruction methods during clinical examinations. The source code for the proposed approach is publicly available.

Automated fetal brain segmentation from 2D MRI slices for motion correction

Motion correction is a key element for imaging the fetal brain in-utero using Magnetic Resonance Imaging (MRI). Maternal breathing can introduce motion, but a larger effect is frequently due to fetal movement within the womb. Consequently, imaging is frequently performed slice-by-slice using single shot techniques, which are then combined into volumetric images using slice-to-volume reconstruction methods (SVR). For successful SVR, a key preprocessing step is to isolate fetal brain tissues from maternal anatomy before correcting for the motion of the fetal head. This has hitherto been a manual or semi-automatic procedure. We propose an automatic method to localize and segment the brain of the fetus when the image data is acquired as stacks of 2D slices with anatomy misaligned due to fetal motion. We combine this segmentation process with a robust motion correction method, enabling the segmentation to be refined as the reconstruction proceeds. The fetal brain localization process uses Maximally Stable Extremal Regions (MSER), which are classified using a Bag-of-Words model with Scale-Invariant Feature Transform (SIFT) features. The segmentation process is a patch-based propagation of the MSER regions selected during detection, combined with a Conditional Random Field (CRF). The gestational age (GA) is used to incorporate prior knowledge about the size and volume of the fetal brain into the detection and segmentation process. The method was tested in a ten-fold cross-validation experiment on 66 datasets of healthy fetuses whose GA ranged from 22 to 39 weeks. In 85% of the tested cases, our proposed method produced a motion corrected volume of a relevant quality for clinical diagnosis, thus removing the need for manually delineating the contours of the brain before motion correction. Our method automatically generated as a side-product a segmentation of the reconstructed fetal brain with a mean Dice score of 93%, which can be used for further processing.

Localisation of the brain in fetal MRI using bundled SIFT features.

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.

Fast fully automatic brain detection in fetal MRI using dense rotation invariant image descriptors

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.

Flexible Reconstruction and Correction of Unpredictable Motion from Stacks of 2D Images

We present a method to correct motion in fetal in-utero scan sequences. The proposed approach avoids previously necessary manual segmentation of a region of interest. We solve the problem of non-rigid motion by splitting motion corrupted slices into overlapping patches of finite size. In these patches the assumption of rigid motion approximately holds and they can thus be used to perform a slice-to-volume-based (SVR) reconstruction during which their consistency with the other patches is learned. The learned information is used to reject patches that are not conform with the motion corrected reconstruction in their local areas. We evaluate rectangular and evenly distributed patches for the reconstruction as well as patches that have been derived from super-pixels. Both approaches achieve on 29 subjects aged between 22–37 weeks a sufficient reconstruction quality and facilitate following 3D segmentation of fetal organs and the placenta.

Motion corrected 3D reconstruction of the fetal thorax from prenatal MRI

In this paper we present a semi-automatic method for analysis of the fetal thorax in genuine three-dimensional volumes. After one initial click we localize the spine and accurately determine the volume of the fetal lung from high resolution volumetric images reconstructed from motion corrupted prenatal Magnetic Resonance Imaging (MRI). We compare the current state-of-the-art method of segmenting the lung in a slice-by-slice manner with the most recent multi-scan reconstruction methods. We use fast rotation invariant spherical harmonics image descriptors with Classification Forest ensemble learning methods to extract the spinal cord and show an efficient way to generate a segmentation prior for the fetal lung from this information for two different MRI field strengths. The spinal cord can be segmented with a DICE coefficient of 0.89 and the automatic lung segmentation has been evaluated with a DICE coefficient of 0.87. We evaluate our method on 29 fetuses with a gestational age (GA) between 20 and 38 weeks and show that our computed segmentations and the manual ground truth correlate well with the recorded values in literature.

Structured Decision Forests for Multi-modal Ultrasound Image Registration

Interventional procedures in cardiovascular diseases often require ultrasound (US) image guidance. These US images must be combined with pre-operatively acquired tomographic images to provide a roadmap for the intervention. Spatial alignment of pre-operative images with intra-operative US images can provide valuable clinical information. Existing multi-modal US registration techniques often do not achieve reliable registration due to low US image quality. To address this problem, a novel medical image representation based on a trained decision forest named probabilistic edge map (PEM) is proposed in this paper. PEMs are generic and modality-independent. They generate similar anatomical representations from different imaging modalities and can thus guide a multi-modal image registration algorithm more robustly and accurately. The presented image registration framework is evaluated on a clinical dataset consisting of 10 pairs of 3D US-CT and 7 pairs of 3D US-MR cardiac images. The experiments show that a registration based on PEMs is able to estimate more reliable and accurate inter-modality correspondences compared to other state-of-the-art US registration methods.

Automated Localization of Fetal Organs in MRI Using Random Forests with Steerable Features

Fetal MRI is an invaluable diagnostic tool complementary to ultrasound thanks to its high contrast and resolution. Motion artifacts and the arbitrary orientation of the fetus are two main challenges of fetal MRI. In this paper, we propose a method based on Random Forests with steerable features to automatically localize the heart, lungs and liver in fetal MRI. During training, all MR images are mapped into a standard coordinate system that is defined by landmarks on the fetal anatomy and normalized for fetal age. Image features are then extracted in this coordinate system. During testing, features are computed for different orientations with a search space constrained by previously detected landmarks. The method was tested on healthy fetuses as well as fetuses with intrauterine growth restriction (IUGR) from 20 to 38 weeks of gestation. The detection rate was above 90% for all organs of healthy fetuses in the absence of motion artifacts. In the presence of motion, the detection rate was 83% for the heart, 78% for the lungs and 67% for the liver. Growth restriction did not decrease the performance of the heart detection but had an impact on the detection of the lungs and liver. The proposed method can be used to initialize subsequent processing steps such as segmentation or motion correction, as well as automatically orient the 3D volume based on the fetal anatomy to facilitate clinical examination.

Adaptive scan strategies for fetal MRI imaging using slice to volume techniques

In this paper several novel methods to account for fetal movements during fetal Magnetic Resonance Imaging (fetal MRI) are explored. We show how slice-to-volume reconstruction methods can be used to account for motion adaptively during the scan. Three candidate methods are tested for their feasibility and integrated into a computer simulation of fetal MRI. The first alters the main orientation of the stacks used for reconstruction, the second stops if too much motion occurs during slice acquisition and the third steers the orientation of each slice individually. Reconstruction informed adaptive scanning can provide a peak signal-to-noise ratio (PSNR) improvement of up to 2 dB after only two stacks of scanned slices and is more efficient with respect to the uncertainty of the final reconstruction.

Automatic Brain Localization in Fetal MRI Using Superpixel Graphs

Fetal MRI is emerging as an effective, non-invasive tool in prenatal diagnosis and pregnancy follow-up. However, there is a significant variability of the position and orientation of the fetus in the MR images. This makes these images more difficult to analyze and interpret compared to standard adult MR imaging, which standardized anatomical imaging aligned planes. We address this issue by automatic localization of the fetal anatomy, in particular, the brain which is a structure of interest for many fetal MRI studies. We first extract superpixels followed by the computation of a histogram of features for each superpixel using bag of words based on dense scale invariant feature transform DSIFT descriptors. We construct a graph of superpixels and train a random forest classifier to distinguish between brain and non-brain superpixels. The localization framework has been tested on 55 MR datasets at gestational ages between 20---38 weeks. The proposed method was evaluated using 5-fold cross validation achieving a