An advanced intelligent ELISA test for bovine tuberculosis diagnosis

A computer-aided method based on geometrical texture features for a precocious detection of fetal Hydrocephalus in ultrasound images

BACKGROUD

Hydrocephalus is the most common anomaly of the fetal head characterized by an excessive accumulation of fluid in the brain processing. The diagnostic process of fetal heads using traditional evaluation techniques are generally time consuming and error prone. Usually, fetal head size is computed using an ultrasound (US) image around 20-22 weeks, which is the gestational age (GA). Biometrical measurements are extracted and compared with ground truth charts to identify normal or abnormal growth.

METHODS

In this paper, an attempt has been made to enhance the Hydrocephalus characterization process by extracting other geometrical and textural features to design an efficient recognition system. The superiority of this work consists of the reduced time processing and the complexity of standard automatic approaches for routine examination. This proposed method requires practical insidiousness of the precocious discovery of fetuses' malformation to alert the experts about the existence of abnormal outcome. The first task is devoted to a proposed pre-processing model using a standard filtering and a segmentation scheme using a modified Hough transform (MHT) to detect the region of interest. Indeed, the obtained clinical parameters are presented to the principal component analysis (PCA) model in order to obtain a reduced number of measures which are employed in the classification stage.

RESULTS

Thanks to the combination of geometrical and statistical features, the classification process provided an important ability and an interesting performance achieving more than 96% of accuracy to detect pathological subjects in premature ages.

CONCLUSIONS

The experimental results illustrate the success and the accuracy of the proposed classification method for a factual diagnostic of fetal head malformation.

Distribution of seroprevalence and risk factors for bovine tuberculosis in east Algeria

Despite the difficulties and the absence of credible scientific information concerning bovine tuberculosis in Algeria, our cross-sectional and inferential study, which is estimated to be a first in Algeria, affected three major semi-intensive regions in East of Algeria, by analyzing 21 holdings which grouped 516 cattle in an intensive and semi-intensive breeding character over a period of 12 months, in order to estimate the seroprevalence and the risk factors those influence the emergence of the disease in these regions. A serological test (ELISA) was carried out on all collected sera, after a stratified two-level sampling. A generalized linear mixed model was used to identify risk factors associated with animal-level positivity. A multivariate descriptive analysis (MCA) was used to identify farm clusters associated with bTB seroprevalence. The results obtained allow us to classify Algeria on the epidemiological level in the field of bovine tuberculosis, in an intermediate situation with a seroprevalence rate of 3.49 % (95 % CI : 1,91, 507); between industrialized countries where the seroprevalence is mostly very low below 0,1% and developing countries with very high seroprevalence such as African-Asian countries. This intermediate epidemiological position is influenced by certain risk factors that are integrated into the three mechanisms commonly known by the scientific community: "contamination by the introduction of an animal"; "neighborhood contamination"; "recurrence". But what characterizes this study is the obtaining of a "Animals purchased from a country listed as not OTF" factor that has returned as a highly protective factor and contributed to the decrease in this seroprevalence, and put Algeria in an intermediate epidemiological situation according to our study, and this is due to a purchase channeled by the state which is exclusive of the countries certified OTF by the OIE.

Supervised classification approach of biometric measures for automatic fetal defect screening in head ultrasound images

This paper presents an advanced approach for foetal brain abnormalities diagnostic by integrating significant biometric features in the identification process. In foetal anomaly diagnosis, manual evaluation of foetal behaviour in ultrasound images is a subjective, slow and error-prone task, especially in the preliminary treatment phases. The effectiveness of this appearance is strictly subject to the attention and the experience of gynaecologists. In this case, automatic methods of image analysis offer the possibility of obtaining a homogeneous, objective and above all fast diagnosis of the foetal head in order to identify pregnancy behaviour. Indeed, we propose a computerised diagnostic method based on morphological characteristics and a supervised classification method to categorise subjects into two groups: normal and affected cases. The presented method is validated on a real integrated microcephaly and dolichocephaly cases. The studied database contains the same gestational age of both normal and abnormal foetuses. The results show that the use of a support vector machine (SVM) classifier is an effective way to enhance recognition and detection for rapid and accurate foetal head diagnostic.