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.

Ethnography of a Land-Deal. Local Perceptions and Vertical Perspectives of a Large Scale Land Acquisition Project in Northern Sierra Leone

Despite an increased scientific interest in the relatively new phenomenon of large-scale land acquisition (LSLA), data on processes on the local level remain sparse and superficial. However, knowledge about the concrete implementation of LSLA projects and the different impacts they have on the heterogeneous group of project affected people is indispensable for a deepened understanding of the phenomenon. In order to address this research gap, a team of two anthropologists and a human geographer conducted in-depth fieldwork on the LSLA project of Swiss based Addax Bioenergy in Sierra Leone. After the devastating civil war, the Sierra Leonean government created favourable conditions for foreign investors willing to lease large areas of land and to bring “development” to the country. Being one of the numerous investing companies, Addax Bioenergy has leased 57’000 hectares of land to develop a sugarcane plantation and an ethanol factory to produce biofuel for the export to the European market. Based on participatory observation, qualitative interview techniques and a network analysis, the research team aimed a) at identifying the different actors that were necessary for the implementation of this project on a vertical level and b) exploring various impacts of the project in the local context of two villages on a horizontal level. The network analysis reveals a complex pattern of companies, institutions, nongovernmental organisations and prominent personalities acting within a shifting technological and discursive framework linking global scales to a unique local context. Findings from the latter indicate that affected people initially welcomed the project but now remain frustrated since many promises and expectations have not been fulfilled. Although some local people are able to benefit from the project, the loss of natural resources that comes along with the land lease affects livelihoods of vulnerable groups – especially women and land users – considerably. However, this research doesn’t only disclose impacts on local people’s previous lives but also addresses strategies they adopt in the newly created situation that has opened up alternative spaces for renegotiations of power and legitimatisation. Therewith, this explorative study reveals new aspects of LSLA that have not been considered adequately by the investing company nor by the general academic discourse on LSLA.

Multi-Environment Model Estimation for Motility Analysis of Caernorhabditis elegans

The nematode Caenorhabditis elegans is a well-known model organism used to investigate fundamental questions in biology. Motility assays of this small roundworm are designed to study the relationships between genes and behavior. Commonly, motility analysis is used to classify nematode movements and characterize them quantitatively. Over the past years, C. elegans' motility has been studied across a wide range of environments, including crawling on substrates, swimming in fluids, and locomoting through microfluidic substrates. However, each environment often requires customized image processing tools relying on heuristic parameter tuning. In the present study, we propose a novel Multi-Environment Model Estimation (MEME) framework for automated image segmentation that is versatile across various environments. The MEME platform is constructed around the concept of Mixture of Gaussian (MOG) models, where statistical models for both the background environment and the nematode appearance are explicitly learned and used to accurately segment a target nematode. Our method is designed to simplify the burden often imposed on users; here, only a single image which includes a nematode in its environment must be provided for model learning. In addition, our platform enables the extraction of nematode ‘skeletons’ for straightforward motility quantification. We test our algorithm on various locomotive environments and compare performances with an intensity-based thresholding method. Overall, MEME outperforms the threshold-based approach for the overwhelming majority of cases examined. Ultimately, MEME provides researchers with an attractive platform for C. elegans' segmentation and ‘skeletonizing’ across a wide range of motility assays.