3D freehand ultrasound without external tracking using deep learning.

This work aims at creating 3D freehand ultrasound reconstructions from 2D probes with image-based tracking, therefore not requiring expensive or cumbersome external tracking hardware. Existing model-based approaches such as speckle decorrelation only partially capture the underlying complexity of ultrasound image formation, thus producing reconstruction accuracies incompatible with current clinical requirements. Here, we introduce an alternative approach that relies on a statistical analysis rather than physical models, and use a convolutional neural network (CNN) to directly estimate the motion of successive ultrasound frames in an end-to-end fashion. We demonstrate how this technique is related to prior approaches, and derive how to further improve its predictive capabilities by incorporating additional information such as data from inertial measurement units (IMU). This novel method is thoroughly evaluated and analyzed on a dataset of 800 in vivo ultrasound sweeps, yielding unprecedentedly accurate reconstructions with a median normalized drift of 5.2%. Even on long sweeps exceeding 20 cm with complex trajectories, this allows to obtain length measurements with median errors of 3.4%, hence paving the way toward translation into clinical routine.

Tagged template deformation.

Model-based approaches are very popular for medical image segmentation as they carry useful prior information on the target structure. Among them, the implicit template deformation framework recently bridged the gap between the efficiency and flexibility of level-set region competition and the robustness of atlas deformation approaches. This paper generalizes this method by introducing the notion of tagged templates. A tagged template is an implicit model in which different subregions are defined. In each of these subregions, specific image features can be used with various confidence levels. The tags can be either set manually or automatically learnt via a process also hereby described. This generalization therefore greatly widens the scope of potential clinical application of implicit template deformation while maintaining its appealing algorithmic efficiency. We show the great potential of our approach in myocardium segmentation of ultrasound images.

Registration of free-breathing 3D+t abdominal perfusion CT images via co-segmentation.

Dynamic contrast-enhanced computed tomography (DCE-CT) is a valuable imaging modality to assess tissues properties, particularly in tumours, by estimating pharmacokinetic parameters from the evolution of pixels intensities in 3D+t acquisitions. However, this requires a registration of the whole sequence of volumes, which is challenging especially when the patient breathes freely. In this paper, we propose a generic, fast and automatic method to address this problem. As standard iconic registration methods are not robust to contrast intake, we rather rely on the segmentation of the organ of interest. This segmentation is performed jointly with the registration of the sequence within a novel co-segmentation framework. Our approach is based on implicit template deformation, that we extend to a co-segmentation algorithm which provides as outputs both a segmentation of the organ of interest in every image and stabilising transformations for the whole sequence. The proposed method is validated on 15 datasets acquired from patients with renal lesions and shows improvement in terms of registration and estimation of pharmacokinetic parameters over the state-of-the-art method.

Incorporating shape variability in image segmentation via implicit template deformation.

Implicit template deformation is a model-based segmentation framework that was successfully applied in several medical applications. In this paper, we propose a method to learn and use prior knowledge on shape variability in such framework. This shape prior is learnt via an original and dedicated process in which both an optimal template and principal modes of variations are estimated from a collection of shapes. This learning strategy requires neither a pre-alignment of the training shapes nor one-to-one correspondences between shape sample points. We then generalize the implicit template deformation formulation to automatically select the most plausible deformation as a shape prior. This novel framework maintains the two main properties of implicit template deformation: topology preservation and computational efficiency. Our approach can be applied to any organ with a possibly complex shape but fixed topology. We validate our method on myocardium segmentation from cardiac magnetic resonance short-axis images and demonstrate segmentation improvement over standard template deformation.

Joint co-segmentation and registration of 3D ultrasound images.

Contrast-enhanced ultrasound (CEUS) allows a visualization of the vascularization and complements the anatomical information provided by conventional ultrasound (US). However, these images are inherently subject to noise and shadows, which hinders standard segmentation algorithms. In this paper, we propose to use simultaneously the different information coming from 3D US and CEUS images to address the problem of kidney segmentation. To that end, we introduce a generic framework for joint co-segmentation and registration that seeks objects having the same shape in several images. From this framework, we derive both an ellipsoid co-detection and a model-based co-segmentation algorithm. These methods rely on voxel-classification maps that we estimate using random forests in a structured way. This yields a fast and fully automated pipeline, in which an ellipsoid is first estimated to locate the kidney in both US and CEUS volumes and then deformed to segment it accurately. The proposed method outperforms state-of-the-art results (by dividing the kidney volume error by two) on a clinically representative database of 64 images.

Real-time 3D image segmentation by user-constrained template deformation.

We describe an algorithm for 3D interactive image segmentation by non-rigid implicit template deformation, with two main original features. First, our formulation incorporates user input as inside/outside labeled points to drive the deformation and improve both robustness and accuracy. This yields inequality constraints, solved using an Augmented Lagrangian approach. Secondly, a fast implementation of non-rigid template-to-image registration enables interactions with a real-time visual feedback. We validated this generic technique on 21 Contrast-Enhanced Ultrasound images of kidneys and obtained accurate segmentation results (Dice > 0.93) in less than 3 clicks in average.

Automatic detection and segmentation of kidneys in 3D CT images using random forests.

Kidney segmentation in 3D CT images allows extracting useful information for nephrologists. For practical use in clinical routine, such an algorithm should be fast, automatic and robust to contrast-agent enhancement and fields of view. By combining and refining state-of-the-art techniques (random forests and template deformation), we demonstrate the possibility of building an algorithm that meets these requirements. Kidneys are localized with random forests following a coarse-to-fine strategy. Their initial positions detected with global contextual information are refined with a cascade of local regression forests. A classification forest is then used to obtain a probabilistic segmentation of both kidneys. The final segmentation is performed with an implicit template deformation algorithm driven by these kidney probability maps. Our method has been validated on a highly heterogeneous database of 233 CT scans from 89 patients. 80% of the kidneys were accurately detected and segmented (Dice coefficient > 0.90) in a few seconds per volume.