C. Roux

Mixed Reversible and RONI Watermarking for Medical Image Reliability Protection

By attaching image authenticity and integrity proofs directly at the pixels level of an image, watermarking can help to raise up medical image protection. However, because of the induced distortions, specific schemes like lossless data hiding or watermarking regions of non interest (RONI) have been proposed to guarantee the preservation of the image interpretation. In this article, we propose an image reliability protection mechanism which combines advantages of both lossless and RONI approaches in order to provide a better and continuous protection. The proposed system was applied to magnetic resonance images of the head. Experimental results illustrate the overall functionality of the system.

A Low Distorsion and Reversible Watermark: Application to Angiographic Images of the Retina

Medical image security can be enhanced using watermarking, which allows embedding the protection information as a digital signature, by modifying the pixel gray levels of the image. In this paper we propose a reversible watermarking scheme which guarantees that once the embedded message is read, alterations introduced during the insertion process can be removed from the image. Thereafter, original pixel gray levels of the image are restored. The proposed approach relies on estimation of image signal that is invariant to the insertion process, and permits to introduce a very slight watermark within the image. In fact, the insertion process adds or subtracts at least one gray level to the pixels of the original image. Depending on the image to be watermarked, in our case angiographic images of the retina, it is expected that such image alteration will not have any impact on the diagnosis quality, and consequently that the watermark can be kept within the image while this one is interpreted

Computer-assisted diagnosis system in digestive endoscopy

The purpose of this paper is to present an intelligent atlas of indexed endoscopic lesions that could be used in computer-assisted diagnosis as reference data. The development of such a system requires a mix of medical and engineering skills for analyzing and reproducing the cognitive processes that underlie the medical decision-making process. The analysis of both endoscopists experience and endoscopic terminologies developed by professional associations shows that diagnostic reasoning in digestive endoscopy uses a scene-object approach. The objects correspond to the endoscopic findings and the medical context of examination and the scene to the endoscopic diagnosis. According to expert assessment, the classes of endoscopic findings and diagnoses, their primitive characteristics (or indices), and their relationships have been listed. Each class describes an endoscopic finding or diagnosis in an intensive way. The retrieval method is based on a similarity metric that estimates the membership value of the case under investigation and the prototype of the class. A simulation test with randomized objects demonstrates a good classification of endoscopic findings. The correct class is the unique response in 68% of the tested objects, the first of multiple responses in 28%. Four descriptors are shown to be of major importance in the classification algorithm: anatomic location, shape, color, and relief. At the present time, the application database contains approximately 150 endoscopic images and is accessible via Internet. Experiments are in progress with endoscopists for the validation of the system and for the understanding of the similarity between images. The next step will integrate the system in a learning tool for junior endoscopists.

Medical image compression using region-of-interest vector quantization

In this paper, we propose a region based image compression approach for medical applications. We use a vector quantization scheme, combined with regions-of-interest. The image to be compressed is first segmented into regions and a separate codebook is used for each specified region. Codeword size and number of codewords by codebooks may be different according to the diagnostic importance of the corresponding image region. This permits to create appropriate codebooks with representative codewords, and to obtain good reconstruction quality in relevant zones, while reinforcing compression in less important regions. The proposed approach is tested on ultrasound esophagus images and is shown to be very promising.

Content-Based Medical Video Retrieval Based on Region Motion Trajectories

In this paper, we address the problem of content-based medical video retrieval. We propose to use motion tracking to generate video features. First, we extract motion vectors derived from the standard ’MPEG-4 AVC/H.264’ video stream. Second, the image sequence motion based segmentation is performed by a combination of k-means clustering and motion consistency verification. Third, we used the well-known Kalman filter to track region displacement between consecutive frames, and build region’s motion trajectories. Finally, to compare videos, we adopted an extension of dynamic time warping (EDTW) to multidimensional time series. Results are promising: a retrieval precision at 5 of 62 % was achieved.

Ellipsoid-Constrained Robust Fitting of Quadrics with Application to the 3D Morphological Characterization of Articular Surfaces

This paper addresses the ellipsoid-type-specified fitting of quadratic surfaces, in the scope of model-based global feature extraction within scattered 3D point clouds. At characterizing articular bone surfaces, the quadrics estimated indicate useful overall-symmetry-related intrinsic centers and axes in joints. A constrained weighted least-squares minimization of algebraic residuals is used, with a robust and bias-corrected metric. With only one quadratic constraint involved, every step produces closed-form eigenvector solutions. To guarantee that an ellipsoid is output, we originally exploit a 2D representation called the quadric shape map (QSM) by carrying out a visual study of the influence of shape constraints. The identified ellipsoid guarantee is needed to extract the center and axes in a wrist joint data stemming from 3D medical images.

Novel approach to stationary transmission scanning using Compton scattered radiation

Transmission scanning-based estimation of the attenuation map plays a crucial role in quantitative radionuclide imaging. X-ray computed tomography (CT) reconstructs directly the attenuation coefficients map from data transmitted through the object. This paper proposes an alternative route for reconstructing the object attenuation map by exploiting Compton scatter of transmitted radiation from an externally placed radionuclide source. In contrast to conventional procedures, data acquisition is realized as a series of images parameterized by the Compton scattering angle and registered on a stationary gamma camera operating without spatial displacement. Numerical simulation results using realistic voxel-based phantoms are presented to illustrate the efficiency of this new transmission scanning approach for attenuation map reconstruction. The encouraging results presented in this paper may suggest the possibility of proposing a new concept for emission/transmission imaging using scattered radiation, which has many advantages compared to conventional technologies.

Human gait simulation using virtual reality

The modelization of 3D forms is imperative to progress in the clinical study of anatomical structures. 3D modelization has contributed to the development of new methods solving particular problems concerning anatomical structures analysis. Virtual reality presents itself as a promising alternative in the visualization of medical images, it permits a specialist to work in interactive sessions that simulate real conditions. Programming languages like VRML helps in the creation of 3D simulation tools for the clinical diagnosis of associated anatomical problems. Such tools make the analysis and quantification of the anatomical structure and its movements more accurate. In this work, a 3D model of the human lower limbs has been integrated with the VRML programming platform. This 3D simulation, coupled with the distinct interactive parametric curves, provides a mechanism for the advanced analysis of the movements of human gait.

Esophageal wall detection using endosonographic imaging systems

An endosonographic imaging system permitting esophageal neoplasm evaluation is presented. Several 2D processing methods applied on these images are presented. The architecture of a new imaging system including the existing one is shown. This new system permits 3D studies and consequently improves the interpretation stage.

Medical image indexing and compression based on vector quantization: image retrieval efficiency evaluation

Addresses the problem of efficient image retrieval from a compressed image database, using information derived from the compression process. Images in the database are compressed applying two approaches: vector quantization (VQ) and quadtree image decomposition. Both are based on Konohens self-organizing feature maps (SOFM) for creating vector quantization codebooks. However, while VQ uses one codebook of one resolution to compress the images, Quadtree decomposition uses simultaneously 4 codebooks of four different resolutions. Image indexing is implemented by generating a feature vector (FV) for each compressed image. Accordingly, images are retrieved by means of FVs similarity evaluation between the query image and the images in the database, depending on a distance measure. Three distance measures have been analyzed to assess FV index similarity: Euclidean, intersection and correlation distances. Distance measures efficiency retrieval is evaluated for different VQ resolutions and different quadtree image descriptors. Experimental results using real data, esophageal ultrasound and eye angiography images, are presented.