A. Pinti

Fatigability of back extensor muscles and low back pain during pregnancy

BACKGROUNDnBack pain is the most frequently reported musculo-skeletal problem during pregnancy. High muscle fatigability has been associated with back pain in the general population. During pregnancy, the gradual increase in loads may have a training effect, increasing strength and endurance of back muscles. This adaptation however may be too slow, or insufficient to be significant in light of other changes during pregnancy.nnnMETHODSnThirty-two pregnant women performed a fatigue test which consisted of maintaining a fixed load of 70 Nm for 60 s while the surface EMG of the longissimus lumborum and multifidus muscles were recorded bilaterally at 14, 24 and 34 weeks of pregnancy. The measure of fatigability was the highest absolute slope of the median frequency of the power spectrum of the EMG of the four muscles. Occurrence and severity of back pain were reported on questionnaires at 14, 19, 24, 29 and 34 weeks. Binomial logistic regressions between back pain occurrence and the median frequency slopes were calculated.nnnFINDINGSnNone of the five logistic analyses demonstrated an improvement of the one-predictor model over the constant-only model, which indicates that the degree of fatigability of back extensor muscles did not predict the occurrence of back pain in our sample.nnnINTERPRETATIONnFatigability of back extensor muscles was not found to be a predictor of back pain during pregnancy. This result should be taken with caution due to the small number of participants and broad definition of back pain used, and should be confirmed by studies with a larger number of participants.

Improvements of Adaptive Filtering by Optimal Projection to filter different artifact types on long duration EEG recordings

Adaptive Filtering by Optimal Projection (AFOP) is an automatic method for reducing ocular and muscular artifacts on electro-encephalographic (EEG) recordings. This paper presents two additions to this method: an improvement of the stability of ocular artifact filtering and an adaptation of the method for filtering electrode artifacts. With these improvements, it is possible to reduce almost all the current types of artifacts, while preserving brain signals, particularly those characterising epilepsy. This generalised method consists of dividing the signal into several time-frequency windows, and in applying different spatial filters to each. Two steps are required to define one of these spatial filters: the first step consists of defining artifact spatial projection using the Common Spatial Pattern (CSP) method and the second consists of defining EEG spatial projection via regression. For this second step, a progressive orthogonalisation process is proposed to improve stability. This method has been tested on long-duration EEG recordings of epileptic patients. A neurologist quantified the ratio of removed artifacts and the ratio of preserved EEG. Among the 330 artifacted pages used for evaluation, readability was judged better for 78% of pages, equal for 20% of pages, and worse for 2%. Artifact amplitudes were reduced by 80% on average. At the same time, brain sources were preserved in amplitude from 70% to 95% depending on the type of waves (alpha, theta, delta, spikes, etc.). A blind comparison with manual Independent Component Analysis (ICA) was also realised. The results show that this method is competitive and useful for routine clinical practice.

Back pain during pregnancy and living conditions: a comparison between Beninese and Canadian women.

OBJECTIVEnThe objective of this exploratory study was to investigate and underline the contrasts between African and Canadian pregnant women, and their living conditions. We also intended to evaluate how they compared on low back pain, a condition that seems common across all pregnant women everywhere in the world.nnnSUBJECTS AND METHODnThirty Beninese and 50 Canadian women were surveyed with demographic disability questionnaires O.D.I at approximately 25 weeks of pregnancy.nnnRESULTSnThere were large differences between the two groups due to the differences between the life style. Beninese women were more likely to be self-employed or housewives, while Canadian women were more likely to be employed. Beninese women worked for 18hours more per week, and had on average one more child at home. A higher percentage of Beninese women reported back pain, 83% versus 58% for Canadian women, but the disability scores were in the moderate disability range for both groups. A higher percentage of Beninese women also reported at least severe disability, 33% versus 14% for Canadian women.nnnCONCLUSIONnThe results suggest that the higher percentages of Beninese women affected by back pain and by severe back pain is related to the longer hours worked and more strenuous physical work performed.

An intelligent generalized system for tissue classification on MR images by integrating qualitative medical knowledge

Abstract In the diagnosis using MRI images, image segmentation techniques play a key role. Existing segmentation methods are generally based on basic image features such as grey level and texture. However, these methods cannot effectively identify physical significance of segmented objects from image because these basic image features such as grey level cannot take into consideration specialized medical knowledge, which is important when doctors study them manually using their own vision and experience. To deal with this problem, many tissue classification systems have been developed by integrating specific medical knowledge. All of these systems focus on specific applications and cannot be normalized and structured. Therefore, adaption of such systems to other contexts is rather difficult. In this paper, we propose an intelligent generalized tissue classification system which combines both the Fuzzy C-Means algorithm and the qualitative medical knowledge on geometric properties of different tissues. In this system, a general geometric model is proposed for formalizing non-structured and non-normalized medical knowledge from various medical images. This system has been successfully applied to the classification of human thigh, crus, arm, forearm, and brain in MRI images.

A tool developed in Matlab for multiple correspondence analysis of fuzzy coded data sets: Application to morphometric skull data

Multiple Correspondence factorial Analysis is a multivariate method for the exploratory study of multidimensional contingency tables. Its use can be extended to the analysis of a table of fuzzy coded data resulting from a distribution into fuzzy windows defined by linguistic properties. There are few existing software tools that allow performing this type of analysis on a data table; furthermore these tools are not interactive and do not allow defining and representing fuzzy windowing. This paper presents a software tool, developed with Matlab, to compute and represent results from multiple correspondence factorial analyses. Pre-defined membership functions can be selected by the user according to the distribution histograms of the data. This paper presents an application example of this program onto a data table of morphometric parameters of 150 male skulls throughout 5 periods of Egyptian civilization. The results are compared to those of a principal component analysis, which is more often used for the study of experimental data. Our program allows a rapid description of the morphological evolution of skulls over time, notably thanks to a linguistic description of each variable, whereas the results of the latter method are less obvious to observe and require a deeper analysis in order to arrive at the same conclusions.

Unsupervised texture segmentation using active contours driven by the Chernoff gradient flow

We present a new unsupervised segmentation of textural images based on integration of a texture descriptor in the formulation of active contour. The proposed texture descriptor intrinsically describes the geometry of textural regions using the shape operator defined in Beltrami framework. We use the Chernoff distance to define an active contours model which discriminates textures by maximizing the distance between the probability density functions which leads to distinguish textural objects of interest and background described by texture descriptor. We prove the existence of a solution to the new formulated active contours based segmentation model and we propose a fast and easy algorithm based on the dual formulation of the Total Variation norm. Finally, we show results on challenging images to illustrate accurate segmentations that are possible.

A Geometrical Active Contour Based on Statistical Shape Prior Model

A new geometric active contour based level-sets model combining gradient, region and shape knowledge information cues is proposed to robust object detection boundaries in presence of occlusions and cluttered background. The gradient, region and shape knowledge information are incorporated as energy terms. The a priori shape model is based on statistical learning of the training data distribution where the structure of data distribution is approximated by a probability density model. The obtained probability is treated as Kernel Principal Component Analysis (KPC) by allowing the shapes that are close to the training data as energy term and incorporated a prior knowledge about shapes in a more robust manner into evolving equation model to constrain the further segmentation evolution process. We applied successfully the proposed model to synthetic and real MR images. The results drawn by the newer model are compared to expert segmentation and evaluated in terms of F-mesure.

An automated pixel classification method using surface expansion Application to MRI image sequence

This paper describes an automated pixel classification method using surface expansion. The originality of this work resides in the definition and use of small pictures (called imagelet) of increasing size centered on the pixel of interest. This allows for the extraction of a set of local and global parameters associated to the pixel investigated. This set of parameters then permits body tissue separation. Classification was obtained using a multilayer artificial neural network. The new approach proposed was applied to main lower limb tissue classification in MRI image sequences. Four kinds of body tissue were taken into consideration in this study (muscle, adipose tissue, cortical bone and spongy bone). A database consisting of 1400 prototypes was created in order to evaluate this methods performances. The classification success rate was found to be 87%. This method therefore proved to be reliable and robust to analyze MRI image sequences in 20 lower limbs, representing about 2000 pictures

Fast Unsupervised Texture Segmentation Using Active Contours Model Driven by Bhattacharyya Gradient Flow

We present a new unsupervised segmentation based active contours model and texture descriptor. The proposed texture descriptor intrinsically describes the geometry of textural regions using the shape operator defined in Beltrami framework. We use Bhattacharyya distance to discriminate textures by maximizing distance between the probability density functions which leads to distinguish textural objects of interest and background. We propose a fast Bregman split implementation of our segmentation algorithm based on the dual formulation of the Total Variation norm. Finally, we show results on some challenging images to illustrate segmentations that are possible.

Use of Support Vector Machines for Color Image Segmentation

We present in this document the first results of our work concerning the implementation of a non-supervised classification algorithm based on support vector machines (SVM) for color image segmentation. The principle of the technique consists in submitting the RGB color attributes (red, green and blue) of the picture to the algorithm of classification to determine the zones that have the same color and therefore determine the different present objects in the image. Our main contribution is the use of a classification algorithm based on support vector machines for image segmentation