Associations of Forest Type, Parasitism and Body Condition of Two European Passerines, Fringilla coelebs and Sylvia atricapilla

Human-induced forest modification can alter parasite-host interactions and might change the persistence of host populations. We captured individuals of two widespread European passerines (Fringilla coelebs and Sylvia atricapilla) in southwestern Germany to disentangle the associations of forest types and parasitism by haemosporidian parasites on the body condition of birds. We compared parasite prevalence and parasite intensity, fluctuating asymmetries, leukocyte numbers, and the heterophil to lymphocyte ratio (H/L-ratio) among individuals from beech, mixed-deciduous and spruce forest stands. Based on the biology of bird species, we expected to find fewer infected individuals in beech or mixed-deciduous than in spruce forest stands. We found the highest parasite prevalence and intensity in beech forests for F. coelebs. Although, we found the highest prevalence in spruce forests for S. atricapilla, the highest intensity was detected in beech forests, partially supporting our hypothesis. Other body condition or health status metrics, such as the heterophil to lymphocyte ratio (H/L-ratio), revealed only slight differences between bird populations inhabiting the three different forest types, with the highest values in spruce for F. coelebs and in mixed-deciduous forests for S. atricapilla. A comparison of parasitized versus non-parasitized individuals suggests that parasite infection increased the immune response of a bird, which was detectable as high H/L-ratio. Higher infections with blood parasites for S. atricapilla in spruce forest indicate that this forest type might be a less suitable habitat than beech and mixed-deciduous forests, whereas beech forests seem to be a suboptimal habitat regarding parasitism for F. coelebs.

Robust Proximal Femur Segmentation in Conventional X-Ray Images via Random Forest Regression on Multi-resolution Gradient Features

In this paper, we propose a fully automatic, robust approach for segmenting proximal femur in conventional X-ray images. Our method is based on hierarchical landmark detection by random forest regression, where the detection results of 22 global landmarks are used to do the spatial normalization, and the detection results of the 59 local landmarks serve as the image cue for instantiation of a statistical shape model of the proximal femur. To detect landmarks in both levels, we use multi-resolution HoG (Histogram of Oriented Gradients) as features which can achieve better accuracy and robustness. The efficacy of the present method is demonstrated by experiments conducted on 150 clinical x-ray images. It was found that the present method could achieve an average point-to-curve error of 2.0 mm and that the present method was robust to low image contrast, noise and occlusions caused by implants.

Fully Automatic Segmentation of AP Pelvis X-rays via Random Forest Regression and Hierarchical Sparse Shape Composition

Knowledge of landmarks and contours in anteroposterior (AP) pelvis X-rays is invaluable for computer aided diagnosis, hip surgery planning and image-guided interventions. This paper presents a fully automatic and robust approach for landmarking and segmentation of both pelvis and femur in a conventional AP X-ray. Our approach is based on random forest regression and hierarchical sparse shape composition. Experiments conducted on 436 clinical AP pelvis x-rays show that our approach achieves an average point-to-curve error around 1.3 mm for femur and 2.2 mm for pelvis, both with success rates around 98%. Compared to existing methods, our approach exhibits better performance in both the robustness and the accuracy.

Classification of interstitial lung disease patterns using local DCT features and random forest.

Over the last decade, a plethora of computer-aided diagnosis (CAD) systems have been proposed aiming to improve the accuracy of the physicians in the diagnosis of interstitial lung diseases (ILD). In this study, we propose a scheme for the classification of HRCT image patches with ILD abnormalities as a basic component towards the quantification of the various ILD patterns in the lung. The feature extraction method relies on local spectral analysis using a DCT-based filter bank. After convolving the image with the filter bank, q-quantiles are computed for describing the distribution of local frequencies that characterize image texture. Then, the gray-level histogram values of the original image are added forming the final feature vector. The classification of the already described patches is done by a random forest (RF) classifier. The experimental results prove the superior performance and efficiency of the proposed approach compared against the state-of-the-art.

Fully automatic segmentation of AP pelvis X-rays via random forest regression with efficient feature selection and hierarchical sparse shape composition

In clinical practice, traditional X-ray radiography is widely used, and knowledge of landmarks and contours in anteroposterior (AP) pelvis X-rays is invaluable for computer aided diagnosis, hip surgery planning and image-guided interventions. This paper presents a fully automatic approach for landmark detection and shape segmentation of both pelvis and femur in conventional AP X-ray images. Our approach is based on the framework of landmark detection via Random Forest (RF) regression and shape regularization via hierarchical sparse shape composition. We propose a visual feature FL-HoG (Flexible- Level Histogram of Oriented Gradients) and a feature selection algorithm based on trace radio optimization to improve the robustness and the efficacy of RF-based landmark detection. The landmark detection result is then used in a hierarchical sparse shape composition framework for shape regularization. Finally, the extracted shape contour is fine-tuned by a post-processing step based on low level image features. The experimental results demonstrate that our feature selection algorithm reduces the feature dimension in a factor of 40 and improves both training and test efficiency. Further experiments conducted on 436 clinical AP pelvis X-rays show that our approach achieves an average point-to-curve error around 1.2 mm for femur and 1.9 mm for pelvis.

Impact of the Ebola epidemic on general and HIV care in Macenta, Forest Guinea, 2014.

OBJECTIVE The current Ebola epidemic massively affected the Macenta district in Forest Guinea. We aimed at investigating its impact on general and HIV care at the only HIV care facility in the district. DESIGN Prospective observational single-facility study. METHODS Routinely collected data on use of general hospital services and HIV care were linked to Ebola surveillance data published by the Guinea Ministry of Health. In addition, we compared retention among HIV-infected patients enrolled into care in the first semesters of 2013 and 2014. RESULTS Throughout 2014, service offer was continuous and unaltered at the facility. During the main epidemic period (August-December 2014), compared with the same period of 2013, there were important reductions in attendance at the primary care outpatient clinic (-40%), in HIV tests done (-46%), in new diagnoses of tuberculosis (-53%) and in patients enrolled into HIV care (-47%). There was a smaller reduction in attendance at the HIV follow-up clinic (-11%). Kaplan-Meier estimates of retention were similar among the patients enrolled into care in 2014 and 2013. In a multivariable Cox regression analysis, the year of enrolment was not associated with attrition (hazard ratio 1.02; 95% confidence interval: 0.72-1.43). CONCLUSION The Ebola epidemic resulted in an important decrease in utilization of the facility despite unaltered service offer. Effects on care of HIV-positive patients enrolled prior to the epidemic were limited. HIV care in such circumstances is challenging, but not impossible.

On the Edge of the Primeval Forest. Accounts and reflections of a medical Doctor in French Equatorial Africa

Reading for 4th-year students