Biomedical subjects

Farida Cheriet

Publications and source records attributed to Farida Cheriet.

8 recordsLinked to original sources

PubMed2006

Multistage graph-based segmentation of thoracoscopic images.

This paper presents a graph-based segmentation method using multiple criteria in successive stages to segment thoracoscopic images acquired during a diskectomy procedure commonly used for thoracoscopic anterior release and fusion for scoliosis treatment. Starting with image pre-processing, including Gaussian smoothing, brightness and contrast enhancement, and histogram thresholding, a standard graph-based method is applied to produce a coarse segmentation of thoracoscopic images. Next, regions are further merged in a multistage graph-based process based on features like grey-level similarity, region size and common edge length. Experimental results show that our approach achieves good spatial coherence, accurate edge location and appropriate segmentation of the regions of interest from a sequence of thoracoscopic images.

Algorithms↗

PubMed2006

Three-dimensional classification of spinal deformities using fuzzy clustering.

STUDY DESIGN: A prospective study of a large set of three-dimensional (3D) reconstructions of spinal deformities in adolescent idiopathic scoliosis (AIS). OBJECTIVES: To determine the value of fuzzy clustering techniques to automatically detect clinically relevant 3D curve patterns within this set of 3D spine models. SUMMARY OF BACKGROUND DATA: Classification is important for the assessment of AIS and has been mainly used to guide surgical treatment. Current classification systems are based on visual curve pattern identification using two-dimensional radiologic measurements but remain controversial because of their low interobserver and intraobserver reliability. A clinically useful 3D classification remains to be found. METHODS: An unsupervised learning algorithm, fuzzy k-means clustering, was applied on 409 3D spine models. Analysis of data distribution using clinical parameters was performed by studying similar curve patterns, near each cluster center identified. RESULTS: The algorithm determined that the entire sample of models could be segmented in five easily differentiated curve patterns similar to those of the Lenke and King classifications. Furthermore, a system with 12 classes made possible the identification of subpatterns of spinal deformity with true 3D components. CONCLUSIONS: Automatic and clinically relevant 3D classification of AIS is possible using an unsupervised learning algorithm. This approach can now be used to build a relevant 3D classification of AIS using appropriate key features of 3D models selected by a panel of expert spinal deformity surgeons.

Adolescent↗

PubMed2006

Scoliotic progression patterns in prognostic factors and future prediction of spinal deformity progression.

This study investigated how an adolescent idiopathic scoliosis progresses with time. 154 consecutive measurements from 26 consecutive AIS patients were analyzed. Each subject had at least four successive scans at six-month intervals. Progression patterns of Cobb angle and apex lateral deviation were extracted from 34 serial data sets of the most common AIS type RT-LL, in the format of four serial data sets, by using the fuzzy c-means clustering technique. Progression of spinal deformity was predicted with previous serial data of Cobb angle and apex lateral deviation by using a GCV extrapolating technique alone and in conjunction with progression patterns. Our results showed that scoliotic progression appears to follow progression patterns. Progression of spinal deformity has potential to be accurately predicted with previous serial spinal deformities by using GCV extrapolating technique with assistance of progression patterns.

Adolescent↗

PubMed2006

A novel framework for the 3D analysis of spine deformation modes.

Three-dimensional classification of scoliosis is important. However, analyzing large databases of 3D spine models is a difficult and time consuming task. To facilitate this task a method that automatically extracts the most important deformation modes from a set of 3D spine models is proposed. The 3D spine models are first converted into vertebrae relative positions and orientations. Then, a variability model composed of the Fréchet mean and of a generalized covariance is computed. A principal component analysis is applied to that variability model and the extracted components are converted into deformation modes. Those modes are visualized by animating a 3D spine model where the deformation strength varies (for a given mode). The proposed method was applied to a group of 307 scoliotic patients and meaningful deformation modes were successfully extracted. For example, patients' growth, double curves, simple thoracic curves and lumbar lordosis were extracted in the first four deformation modes. Moreover, the obtained deformation modes are not disconnected from conventional surgical classifications since a logistic regression confirmed that there is a statistically significant relation between King's classification and the first four principal deformation modes. The proposed method successfully extracted important deformation modes from a set of 3D spine models and can be used to refine arbitrary classes (King's or Lenke's classes, for instance), thus helping the design of new clinically relevant 3D classifications.

Databases, Factual↗

PubMed2006

Assessment of brace local action on vertebrae relative poses.

Bracing is a widely used treatment of scoliosis, but there is still no consensus about its actual effect. Previous studies were based on global descriptors of the spine shape (Cobb angle, plane of maximal deformity, etc.). We present a new method to analyze braces effects at a finer scale and to find which vertebral levels are significantly affected by this treatment. The proposed method compares a group of patients treated with a brace and a control group. The 3D spine geometry of the patients from the two groups was digitized on two separate occasions: with and without brace (first group) or two times without brace (control group). The modifications of the vertebrae relative poses (combination of relative translation and rotation between consecutive vertebrae) were then extracted from 3D reconstructions. Centrality and dispersion measures of the relative poses modifications were computed using a method that take into account the non-linearity of the rotation matrix. Then, finally, multivariate hypothesis tests were used to compare the centrality and dispersion of the two groups. The method was applied to 28 untreated scoliotic patients and 41 patients treated with a Boston brace. Significant differences (p<0.01) between the centrality and dispersion measures of the relative poses modifications were respectively found from T1 to T6 and from T8 to L1. Those significant differences concords with the back flattening effect and the spatially limited correction found in other studies; however the proposed method offers a more specific evaluation of the localization of those effects.

Braces↗

PubMed2006

Towards an automatic classification of spinal curves from x-ray images.

The objective of this research was to describe a multi-resolution technique for segmentation of the spinal curve on postero-anterior radiograph. Global features from the radiographs were first identified. From this approximate region, local regions of the spine curvature were iteratively filtered using diffusion and shock filters to enhance the boundaries of each vertebral body from radiographic noise. The spine curve going through the centroid of the vertebral bodies was successively identified for clinical classification of spinal deformities.

Adolescent↗

PubMed2004

Three-dimensional (3-D) reconstruction of the spine from a single X-ray image and prior vertebra models.

The lateral bending test is routinely used by clinicians for the preoperative assessment of spinal mobility. The evaluation of bending motion is usually based on the qualitative analysis of a two-dimensional (2-D) antero-posterior X-ray image. The aim of this paper is to introduce a novel three-dimensional (3-D) reconstruction technique that is a prerequisite for the quantitative 3-D analysis of lateral bending motion. An algorithm was developed for the 3-D reconstruction of the spine from a single X-ray image. The X-ray is calibrated using a small calibration object and an explicit calibration algorithm. The information contained in the single X-ray is completed by registering a priori 3-D geometric models of individual vertebrae. Part of the error yielded by the 3-D/2-D registration is corrected by a vertebral alignment constraint that aims to minimize intervertebral dislocations. Three-dimensional models of 15 different scoliosis patients, obtained from a standard stereo-radiographic 3-D reconstruction, were used in simulation and validation experiments. Experimental results show that the new method is robust and accurate. With pessimistic levels of simulated noise, the average root mean square reconstruction error is 2.89 mm, which is appropriate for common clinical applications.

Algorithms↗

PubMed2002

3D reconstruction and analysis of the whole trunk surface for non-invasive follow-up of scoliotic deformities.

The purpose of this study was to evaluate the 3D reconstruction accuracy of a new technology that allows the acquisition of the whole trunk and to develop a software to analyse the trunk surface asymmetry. A non-invasive active vision system provides a 3D textured reconstruction of the whole trunk. The analysis system provides the clinician with quantitative indices that characterize the whole external trunk asymmetry.

Artificial Intelligence↗