In manufacturing, the monitoring of the fabrication process is crucial in order to be sure that objects are compliant. For nano-objects, most of this monitoring is done manually. In this paper, we propose a method to segment different materials in a manufactured object. The method uses design information which represent the ideal object to manufacture. This representation visually gathers information about materials, shapes and relationships between these shapes. In our segmentation method we choose to encode this information in the tree of shapes to enforce the design characteristics into a real image of the object. To achieve such segmentation, we perform graph cuts on this particular tree structure using additional information such as the position in the design or the order of inclusion of the shapes.

In digital radiography imaging, the anti-scatter grid is usually employed to reduce scattered radiation and to enhance contrast. The shadow of this grid cause irregular stripes artifacts in the x-ray image. To remove these artifacts, most image processing methods adopt a band stop filter which leaves ringing artifact or degrades the clinical contain. In this paper, we propose a new anti-scatter grid suppression method based on spectral estimation and on a physical image formation model of the grid, of the clinical content and of the noise. Patch processing preserve the stationarity assumption and assume high accuracy of the model. The new method was applied on synthetic grid and on clinical images where it suppressed grid-lines artifacts while maintaining the image details and avoiding ringing artifacts. It produced better results compared to the conventional filtering approaches, especially when the metallic materials present in or on the patients.

In dynamic planar imaging, extraction of signals specific to structures is complicated by structures superposition. Due to overlapping, signals extraction with classic regions of interest (ROIs) methods suffers from inaccuracy, as extracted signals are a mixture of targeted signals. Partial volume effect raises the same issue in dynamic tomography. Source separation methods, such as factor analysis of dynamic sequences, have been developed to unmix such data. However, the underlying problem is underdetermined and the model used is not relevant in the whole image. This non-uniqueness issue was overcome by introducing prior knowledge, such as sparsity or smoothness, in the separation model. In practice, these methods are barely used because of the lack of reliability of their results. Previously developed methods aimed to be fully automatic, but efficiency can be improved with additional prior knowledge. Some methods using ROIs knowledge in a straightforward way have been proposed. In this paper, we propose an unmixing method, based on an objective function minimization and integrating these ROIs in a different and robust manner. The objective function promotes consistent solutions regarding ROIs while relaxing the model outside ROIs. In order to reduce user-dependent effects, ROIs are used as soft constraints in a robust way through the use of a distance matrix. Consistency, effectiveness, and robustness to the ROIs selection are demonstrated on a toy example, a highly realistic simulated renography data set and a clinical data set. Performance is compared with the competitive methods.

We propose an automatic multiorgan segmentation method for 3-D radiological images of different anatomical contents and modalities. The approach is based on a simultaneous multilabel graph cut optimization of location, appearance, and spatial configuration criteria of target structures. Organ location is defined by target-specific probabilistic atlases (PA) constructed from a training dataset using a fast (2+1)D SURF-based multiscale registration method involving a simple four-parameter transformation. PAs are also used to derive target-specific organ appearance models represented as intensity histograms. The spatial configuration prior is derived from shortest-path constraints defined on the adjacency graph of structures. Thorough evaluations on Visceral project benchmarks and training dataset, as well as comparisons with the state-of-the-art confirm that our approach is comparable to and often outperforms similar approaches in multiorgan segmentation, thus proving that the combination of multiple suboptimal but complementary information sources can yield very good performance.

In the past 20 years, a wide range of complex fluoroscopically guided procedures have shown considerable growth. Biologic effects of the exposure (radiation induced burn, cancer) lead to reduce the dose during the intervention, for the safety of patients and medical staff. However, when the dose is reduced, image quality decreases, with a high level of noise and a very low contrast. Efficient restoration and denoising algorithms should overcome this drawback. We propose a spatio-temporal filter operating in a multi-scales space. This filter relies on a first order, motion compensated, recursive temporal denoising. Temporal high frequency content is first detected and then matched over time to allow for a strong denoising in the temporal axis. We study this filter in the curvelet domain and in the dual-tree complex wavelet domain, and compare those results to state of the art methods. Quantitative and qualitative analysis on both synthetic and real fluoroscopic sequences demonstrate that the proposed filter allows a great dose reduction.

We propose a temporal motion-compensated filter operating on dual-tree complex wavelet coefficients to denoise low-dose X-ray sequences. This filter allows for a great noise reduction while preserving moving objects and structures. We take advantage of the properties of multi-scale spaces to perform a fast and robust motion tracking. The result of this step is then used in the temporal filter for denoising purpose. Quantitative and qualitative analysis on real fluoroscopic sequences show that our method outperforms state-of-the-art VBM3D method and allows for a dose reduction as high as 80%.

This paper presents a segmentation process of the myocardium, endocardium and epicardium surfaces of the heart from 3D SPECT images to compute a heterogeneity index. This index represents the distribution of the activity in the myocardium. Because of the low resolution of SPECT images, the thickness of the myocardium is 1 to 4 voxels and a sub-voxel accuracy is therefore needed. The segmentation process is based on the minimization of an energy by dynamic programming after a coarse segmentation to define the center surface of the myocardium. A Gaussian mixture is fitted on the data to ensure subvoxel accuracy. The heterogeneity index is compared to the reference index on 58 SPECT images and the segmentation is visually validated on 300 SPECT images by a clinician.

Image guided interventions have seen growing interest in recent years. The use of X-rays for the procedure impels limiting the dose over time. Image sequences obtained thereby exhibit high levels of noise and very low contrasts. Hence, the development of efficient methods to enable optimal visualization of these sequences is crucial. We propose an original denoising method based on the curvelet transform. First, we apply a recursive temporal filter to the curvelet coefficients. As some residual noise remains, a spatial filtering is performed in the second step, which uses a magnitude-based classification and a contextual comparison of curvelet coefficients. This procedure allows to denoise the sequence while preserving low-contrasted structures, but does not improve their contrast. Finally, a third step is carried out to enhance the features of interest. For this, we propose a line enhancement technique in the curvelet domain. Indeed, thin structures are sparsely represented in that domain, allowing a fast and efficient detection. Quantitative and qualitative evaluations performed on synthetic and real low-dose sequences demonstrate that the proposed method enables a 50% dose reduction.

We propose an image denoising method which takes curvelet domain inter-scale, inter-location and inter-orientation dependencies into account in a maximum a posteriori labeling of the curvelet coefficients of a noisy image. The rationale is that generalized neighborhoods of curvelet coefficients contain more reliable information on the true image than individual coefficients. Based on the labeling of coefficients and their magnitudes, a smooth thresholding functional produces denoised coefficients from which the denoised image is reconstructed. We also outline a faster approach to labeling and thresholding, relying on contextual comparisons of coefficients. Quantitative and qualitative evaluations on natural and X-ray images show that our method outperforms related multiscale approaches and compares favorably to the state-of-art BM3D method on X-ray data while executing faster.

We propose a new data model for graph-cut image segmentation, defined according to probabilities learned by a classification process. Unlike traditional graph-cut methods, the data model takes into account not only color but also texture and shape information. For melanoma images, we also introduce skin chromophore features and automatically derive “seed” pixels used to train the classifier from a coarse initial segmentation. On natural images, our method successfully segments objects having similar color but different texture. Its application to melanoma delineation compares favorably to manual delineation and related graph-cut segmentation methods.

Accurate skin lesion segmentation is critical for automated early skin cancer detection and diagnosis. We present a novel method to detect skin lesion borders in multispectral dermoscopy images. First, hairs are detected on infrared images and removed by inpainting visible spectrum images. Second, skin lesion is pre-segmented using a clustering of a superpixel partition. Finally, the pre-segmentation is globally regularized at the superpixel level and locally regularized in a narrow band at the pixel level.

We derive shortest-path constraints from graph models of structure adjacency relations and introduce them in a joint centroidal Voronoi image clustering and Graph Cut multiobject semiautomatic segmentation framework. The vicinity prior model thus defined is a piecewise-constant model incurring multiple levels of penalization capturing the spatial configuration of structures in multiobject segmentation. Qualitative and quantitative analyses and comparison with a Potts prior-based approach and our previous contribution on synthetic, simulated, and real medical images show that the vicinity prior allows for the correct segmentation of distinct structures having identical intensity profiles and improves the precision of segmentation boundary placement while being fairly robust to clustering resolution. The clustering approach we take to simplify images prior to segmentation strikes a good balance between boundary adaptivity and cluster compactness criteria furthermore allowing to control the trade-off. Compared with a direct application of segmentation on voxels, the clustering step improves the overall runtime and memory footprint of the segmentation process up to an order of magnitude without compromising the quality of the result.

This paper describes a videosonde designed for providing shape and size of raindrops. It makes use of a single CCD camera and image processing to detect raindrops, to segment and measure shape and size of each detected particle. Depth is obtained by one fixed camera with 2 lights, which is a key feature of the video sonde. Raindrops are detected by their 2 shadows. As no model are accurate to represent raindrops, image processing uses a-contrario method for detection, and constraint filtering for matching. Results are evaluated on glass ball and real rain simulator.

In this paper, we propose and compare four different approaches for quantification of hemoglobin and melanin in skin color images. The first method is to extract erythema/melanin indices based on skin absorbance theories. The second method is based on independent component analysis (ICA) assuming that hemoglobin and melanin absorbance spectra are independent. The third method is based on non-negative matrix factorization (NMF) with multiplicative update algorithm. The fourth method is a Beer-Lambert law based model-fitting technique. Quantitative evaluation through graph-cut segmentation on melanoma indicates that model-fitting method outperforms the other three methods.

We propose an application of multi-label “Graph Cut” optimization algorithms to the simultaneous segmentation of multiple anatomical structures, initialized via an over-segmentation of the image computed by a fast centroidal Voronoi diagram (CVD) clustering algorithm. With respect to comparable segmentations computed directly on the voxels of image volumes, we demonstrate performance improvements on both execution speed and memory footprint by, at least, an order of magnitude, making it possible to process large volumes on commodity hardware which could not be processed pixel-wise.

This paper proposes a novel approach to estimate the parameters of motion blur (orientation and extension) simultaneously from the observed image. The motion blur estimation would be used in a standard non blind deconvolution algorithm, thus yielding a blind motion deblurring scheme. Our algorithm is based on the correlation between the modified logarithm power spectrum from natural image model and the blur kernel. The local minima of the modified spectrum are closer to the horizontal line, and thus more similar to the sinc function. Compared to previous estimation algorithm, the results are more accurate in noisy images.

A method for detecting people in video streams is presented for the context of a front view monocular camera. This paper describes the proposed human model, which combines skin color and foreground probability maps by defining the spatial relationships that exist between them. The detection is performed with a Monte Carlo simulation for the defined Bayesian framework, in order to estimate the model parameters. The detected people are then associated with signatures, that are compared between consecutive frames in order to achieve tracking. Promising results are obtained for the detection and matching of multiple people, as presented for a transportation vehicle application.

In this paper, a minimal cost approach is used for contour tracking with a good robustness. Dynamic programming was chosen for its efficiency. This general method is applied to the extraction of the cranial contour on high-resolution X-Ray images. As a first step for automated localization of cephalometric points, an ellipse is then fitted on the extracted contour. This method was tested on 424 X-Ray images, with different acquisition parameters.

The spatial resolution of Magnetic Resonance Angiography (MRA) makes it a powerful tool for diagnosis and surgical planning. However, image interpretation and visualization tools are missing, and three-dimensional measurements are not usually accessible. Flexible visualization of the whole vascular tree and precise quantification of phenomena like carotid stenosis are applications of an automated processing of MRA. Building an accurate model of a tubular objects network such as bronchi or blood vessels can provide a substantial help for 3D visualization and quantification. The authors present a tracking algorithm of centrelines that makes very few assumptions on the structure grey-level profile. The main originality of this work is the accurate 3D centreline tracking process which provides subvoxel accuracy and deals with bifurcations. This approach has been successfully applied to the cerebral vasculature in MRA images.

Automatic labelling and identification of cerebral structure, such as cortical sulci, are useful in neurology, surgery planning, etc... In this paper, a method to detect the valley of the cortical sulci is presented. The aim of the method is to achieve the sulci medial surface. The method, applied on MRI data, is based on geometrical features (curvature) and doesn't require accurate segmentation of the cerebral cortex. We use sub-voxel precision tracking. The minimum curvature vector in each point allows successive displacement along the valley of sulci. Partial derivatives provide the differential characteristics.

We address the problem of locating some anatomical bone structures on lateral cranial X-ray images. These structures are landmarks used in orthodontic therapy. The main problem in this pattern recognition application is that the landmarks are difficult to distinguish on images even for the human expert, because of lateral projection of the X-ray process. We propose a 3 steps approach: the first step provides a statistical estimation of the landmarks, using an adaptive coordinates space; the second step computes a region of interest around the estimated landmark; and in the third step, each landmark is precisely located using its anatomical definition. This paper describes the two first generic steps and gives examples of the last step for two anatomical points.