Fabian Lecron

A framework of vertebra segmentation using the active shape model-based approach

We propose a medical image segmentation approach based on the Active Shape Model theory. We apply this method for cervical vertebra detection. The main advantage of this approach is the application of a statistical model created after a training stage. Thus, the knowledge and interaction of the domain expert intervene in this approach. Our application allows the use of two different models, that is, a global one (with several vertebrae) and a local one (with a single vertebra). Two modes of segmentation are also proposed: manual and semiautomatic. For the manual mode, only two points are selected by the user on a given image. The first point needs to be close to the lower anterior corner of the last vertebra and the second near the upper anterior corner of the first vertebra. These two points are required to initialize the segmentation process. We propose to use the Harris corner detector combined with three successive filters to carry out the semiautomatic process. The results obtained on a large set of X-ray images are very promising.

GPU-based segmentation of cervical vertebra in X-Ray images

The segmentation of cervical vertebra in X-Ray radiographs can give valuable information for the study of the vertebral mobility. One particular characteristic of the X-Ray images is that they present very low grey level variation and makes the segmentation difficult to perform. In this paper, we propose a segmentation procedure based on the Active Shape Model to deal with this issue. However, this application is seriously hampered by its considerable computation time. We present how vertebra extraction can efficiently be performed in exploiting the vast processing power of the Graphics Processing Units (GPU). We propose a CUDA-based GPU implementation of the most intensive processing steps enabling to boost performance. Experimentations have been conducted using a set of high resolution X-Ray medical images, showing a global speedup ranging from 15 to 21, by comparison with the CPU implementation.

Heterogeneous computing for vertebra detection and segmentation in x-ray images

The context of this work is related to the vertebra segmentation. The method we propose is based on the active shape model (ASM). An original approach taking advantage of the edge polygonal approximation was developed to locate the vertebra positions in a X-ray image. Despite the fact that segmentation results show good efficiency, the time is a key variable that has always to be optimized in a medical context. Therefore, we present how vertebra extraction can efficiently be performed in exploiting the full computing power of parallel (GPU) and heterogeneous (multi-CPU/multi-GPU) architectures. We propose a parallel hybrid implementation of the most intensive steps enabling to boost performance. Experimentations have been conducted using a set of high-resolution X-ray medical images, showing a global speedup ranging from 3 to 22, by comparison with the CPU implementation. Data transfer times between CPU and GPU memories were included in the execution times of our proposed implementation.

Fully automatic vertebra detection in x-ray images based on multi-class SVM

Automatically detecting vertebral bodies in X-Ray images is a very complex task, especially because of the noise and the low contrast resulting in that kind of medical imagery modality. Therefore, the contributions in the literature are mainly interested in only 2 medical imagery modalities: Computed Tomography (CT) and Magnetic Resonance (MR). Few works are dedicated to the conventional X-Ray radiography and propose mostly semi-automatic methods. However, vertebra detection is a key step in many medical applications such as vertebra segmentation, vertebral morphometry, etc. In this work, we develop a fully automatic approach for the vertebra detection, based on a learning method. The idea is to detect a vertebra by its anterior corners without human intervention. To this end, the points of interest in the radiograph are firstly detected by an edge polygonal approximation. Then, a SIFT descriptor is used to train an SVM-model. Therefore, each point of interest can be classified in order to detect if it belongs to a vertebra or not. Our approach has been assessed by the detection of 250 cervical vertebræ on radiographs. The results show a very high precision with a corner detection rate of 90.4% and a vertebra detection rate from 81.6% to 86.5%.

Fast 3d spine reconstruction of postoperative patients using a multilevel statistical model

Severe cases of spinal deformities such as scoliosis are usually treated by a surgery where instrumentation (hooks, screws and rods) is installed to the spine to correct deformities. Even if the purpose is to obtain a normal spine curve, the result is often straighter than normal. In this paper, we propose a fast statistical reconstruction algorithm based on a general model which can deal with such instrumented spines. To this end, we present the concept of multilevel statistical model where the data are decomposed into a within-group and a between-group component. The reconstruction procedure is formulated as a second-order cone program which can be solved very fast (few tenths of a second). Reconstruction errors were evaluated on real patient data and results showed that multilevel modeling allows better 3D reconstruction than classical models.

Points of interest detection in cervical spine radiographs by polygonal approximation

In this paper, we introduce a robust approach to detect points of interest in cervical spine radiographs. The perspective of this work is to segment the vertebrae on X-Ray images for the analysis of the vertebral mobility. In previous work, we proposed a segmentation technique based on Active Shape Model. The extraction and the detection of the vertebra corners can contribute to the automatic initialization of the Active Shape Model search and can give valuable information about the spine curvature. Here, we present the benefits of the polygonal approximation dedicated to the points of interest detection. The methodology developed here is composed of 3 stages: a contrast limited adaptive histogram equalization, a Canny edge detection filter and an edge polygonal approximation. The first histogram equalization step is a pretraitment needed to improve the image quality in order to perform a better contour detection. The Canny operator detects the edges in the radiograph which are used as an input to the polygonal approximation. The edges become segment lines whose intersections define corners. We compare the results obtained with our approach based on the polygonal approximation to results coming from the Harris corner detector.

Weighting strategies for a recommender system using item clustering based on genres

An original clustering approach for recommender systems.The approach is based on item metadata informations (item genres).Items are clustered in several clusters.Weighting strategies are used to combine clusters evaluations.MAE is improved between 0.3 and 1.8% and RMSE between 4.7 and 9.8%. Recommender systems are effective to identify items that could interest clients on e-commerce web sites or predict evaluations that people could give to items such as movies. In this context, clustering can be used to improve predictions or to reduce computational time. In this paper, we present a clustering approach based on item metadata informations. Evaluations are clustered according to item genre. As items can have several genres, evaluations can be placed in several clusters. Each cluster provides its own rating prediction and weighting strategies are then used to combine these results in one evaluation. Coupled with an existing collaborative filtering recommender system and applied on Yahoo! and MovieLens datasets, our method improves the MAE between 0.3 and 1.8%, and the RMSE between 4.7 and 9.8%.

Multilevel statistical shape models: A new framework for modeling hierarchical structures

Statistical shape models are commonly used in various applications of computer vision. Nevertheless, these models are not well adapted to hierarchical structures. This paper proposes a solution to this problem by presenting a general framework to build multilevel statistical shape models. Based on multilevel component analysis, the idea is to decompose the data into a within-individual and a between-individual component. As a result, several sub-models are deduced and can be treated separately, each level characterizing one sub-model. In this paper, we present a multilevel model of the human spine. The results show that such a modelization offers more flexibility and allows deformations that classical statistical models can simply not generate.

Three-Dimensional Spine Model Reconstruction Using One-Class SVM Regularization

Statistical shape models have become essential for medical image registration or segmentation and are used in many biomedical applications. These models are often based on Gaussian distributions learned from a training set. We propose in this paper a shape model which does not rely on the estimation of a Gaussian distribution, but on similarities computed with a kernel function. Our model takes advantage of the one-class support vector machine (OCSVM) to do so. In this context, we propose in this paper a method for reconstructing the spine of scoliotic patients using OCSVM regularization. Current state-of-the-art methods use conventional statistical shape models, and the reconstruction is commonly processed by minimizing a Mahalanobis distance. Nevertheless, when a shape differs significantly from the statistical model, the associated Mahalanobis distance often overstates the need for statistical regularization. We show that OCSVM regularization is more robust and is less sensitive to weak landmarks definition and is hardly influenced by the presence of outliers in the training data. The proposed OCSVM model applied to 3-D spine reconstruction was evaluated on real patient data, and results showed that our approach allows precise reconstruction.

Cervical Spine Mobility Analysis on Radiographs: a Fully Automatic Approach

Conventional X-ray radiography remains nowadays the most common method to analyze spinal mobility in two dimensions. Therefore, the objective of this paper is to develop a framework dedicated to the fully automatic cervical spine mobility analysis on X-ray images. To this aim, we propose an approach based on three main steps: fully automatic vertebra detection, vertebra segmentation and angular measurement. The accuracy of the method was assessed for a total of 245 vertebræ. For the vertebra detection, we proposed an adapted version of two descriptors, namely Scale-invariant Feature Transform (SIFT) and Speeded-up Robust Features (SURF), coupled with a multi-class Support Vector Machine (SVM) classifier. Vertebræ are successfully detected in 89.8% of cases and it is demonstrated that SURF slightly outperforms SIFT. The Active Shape Model approach was considered as a segmentation procedure. We observed that a statistical shape model specific to the vertebral level improves the results. Angular errors of cervical spine mobility are presented. We showed that these errors remain within the inter-operator variability of the reference method.