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.

Validation of a modified AVHRR aerosol optical depth retrieval algorithm over Central Europe

The Advanced Very High Resolution Radiometer (AVHRR) carried on board the National Oceanic and Atmospheric Administration (NOAA) and the Meteorological Operational Satellite (MetOp) polar orbiting satellites is the only instrument offering more than 25 years of satellite data to analyse aerosols on a daily basis. The present study assessed a modified AVHRR aerosol optical depth τa retrieval over land for Europe. The algorithm might also be applied to other parts of the world with similar surface characteristics like Europe, only the aerosol properties would have to be adapted to a new region. The initial approach used a relationship between Sun photometer measurements from the Aerosol Robotic Network (AERONET) and the satellite data to post-process the retrieved τa. Herein a quasi-stand-alone procedure, which is more suitable for the pre-AERONET era, is presented. In addition, the estimation of surface reflectance, the aerosol model, and other processing steps have been adapted. The method's cross-platform applicability was tested by validating τa from NOAA-17 and NOAA-18 AVHRR at 15 AERONET sites in Central Europe (40.5° N–50° N, 0° E–17° E) from August 2005 to December 2007. Furthermore, the accuracy of the AVHRR retrieval was related to products from two newer instruments, the Medium Resolution Imaging Spectrometer (MERIS) on board the Environmental Satellite (ENVISAT) and the Moderate Resolution Imaging Spectroradiometer (MODIS) on board Aqua/Terra. Considering the linear correlation coefficient R, the AVHRR results were similar to those of MERIS with even lower root mean square error RMSE. Not surprisingly, MODIS, with its high spectral coverage, gave the highest R and lowest RMSE. Regarding monthly averaged τa, the results were ambiguous. Focusing on small-scale structures, R was reduced for all sensors, whereas the RMSE solely for MERIS substantially increased. Regarding larger areas like Central Europe, the error statistics were similar to the individual match-ups. This was mainly explained with sampling issues. With the successful validation of AVHRR we are now able to concentrate on our large data archive dating back to 1985. This is a unique opportunity for both climate and air pollution studies over land surfaces.

Assessing vegetation cover and biomass in restored erosion areas in Iceland using SPOT satellite data

Due to highly erodible volcanic soils and a harsh climate, livestock grazing in Iceland has led to serious soil erosion on about 40% of the country's surface. Over the last 100 years, various revegetation and restoration measures were taken on large areas distributed all over Iceland in an attempt to counteract this problem. The present research aimed to develop models for estimating percent vegetation cover (VC) and aboveground biomass (AGB) based on satellite data, as this would make it possible to assess and monitor the effectiveness of restoration measures over large areas at a fairly low cost. Models were developed based on 203 vegetation cover samples and 114 aboveground biomass samples distributed over five SPOT satellite datasets. All satellite datasets were atmospherically corrected, and digital numbers were converted into ground reflectance. Then a selection of vegetation indices (VIs) was calculated, followed by simple and multiple linear regression analysis of the relations between the field data and the calculated VIs. Best results were achieved using multiple linear regression models for both %VC and AGB. The model calibration and validation results showed that R2 and RMSE values for most VIs do not vary very much. For percent VC, R2 values range between 0.789 and 0.822, leading to RMSEs ranging between 15.89% and 16.72%. For AGB, R2 values for low-biomass areas (AGB < 800 g/m2) range between 0.607 and 0.650, leading to RMSEs ranging between 126.08 g/m2 and 136.38 g/m2. The AGB model developed for all areas, including those with high biomass coverage (AGB > 800 g/m2), achieved R2 values between 0.487 and 0.510, resulting in RMSEs ranging from 234 g/m2 to 259.20 g/m2. The models predicting percent VC generally overestimate observed low percent VC and slightly underestimate observed high percent VC. The estimation models for AGB behave in a similar way, but over- and underestimation are much more pronounced. These results show that it is possible to estimate percent VC with high accuracy based on various VIs derived from SPOT satellite data. AGB of restoration areas with low-biomass values of up to 800 g/m2 can likewise be estimated with high accuracy based on various VIs derived from SPOT satellite data, whereas in the case of high biomass coverage, estimation accuracy decreases with increasing biomass values. Accordingly, percent VC can be estimated with high accuracy anywhere in Iceland, whereas AGB is much more difficult to estimate, particularly for areas with high-AGB variability.

Explosive speciation rates and unusual species richness in haplochromine cichlid fishes: Effects of sexual selection

Ancient lakes are often unusually species rich, mostly as a result of radiation and species-flock formation having taken place in only one or a few of many taxa present. Understanding why some taxa radiate and others do not is at the heart of understanding biodiversity. In this chapter I discuss possible explanations for disproportionally large species numbers in some cichlid fish lineages in East African Great Lakes: the halochromine cichlid fishes in Lakes Victoria and Malawi. I show that speciation rates in this group are higher than in any other lacustrine fish radiation. Against this background, I review hypotheses put forward to explain diversity in cichlid species flocks. The evolution of species diversity requires three processes: speciation, ecological radiation and anatomical diversification, and it is wrong to consider hypotheses that are relevant to different processes as alternatives to each other. The African cichlid species flocks show unusually high ecological species packing in several phylogenetic groups and unusually high speciation rates in haplochromines. Therefore, it maybe concluded that at least two evolutionary models are required to explain the difference between cichlid diversity and other fish diversity in East African Lakes: one for speciation in haplochromines and one for coexistence. Subsequently I review work on speciation in haplochromines, and in particular studies aimed at testing the hypothesis of speciation by sexual selection. Haplochromines have a polygynous mating system, conducive to sexual selection, but other polygynous cichlids are not particularly species rich. This suggests that more than just strong sexual selection is required to explain haplochromine species richness. Recent palaeoecological evidence undermines the previously popular hypotheses that explained the species richness of Lake Victoria in terms of speciation under varying natural or sexual selection regimes in satellite lakes or in isolated lake basins. I summarize experimental and comparative studies, which provide evidence for two mechanisms of sympatric speciation by disruptive sexual selection on polymorphic coloration. Such modes of speciation may explain (i) the high speciation rates in colour polymorphic lineages of haplochromine cichlids under conditions where colour variation is visible in clear water, and (ii) in combination with factors that affect population survival, the unusual species richness in haplochromine species flocks. I argue that sexual selection, if disruptive, can accelerate the pace of adaptive radiation because the resultant genetic population fragmentation allows a much increased rate of differential response to disruptive natural selection. Hence, the ecological pattern of diversity resembles that produced by disruptive natural selection, with the difference that disruptive sexual selection continues to cause (gross) speciation even after niche space is saturated. This may explain the unusually high numbers of very closely related and ecologically similar species in haplochromine species flocks. The role of disruptive sexual selection is twofold: it not only causes speciation, but also maintains reproductive isolation in sympatry between species that have evolved in sympatry or allopatry. Therefore, the maintenance of diversity in species flocks that originated through sexual selection depends on the persistence of the selection regime within the environmental signal space under which that diversity evolved.

Streak detection algorithm for space debris detection on optical images.

Any image processing object detection algorithm somehow tries to integrate the object light (Recognition Step) and applies statistical criteria to distinguish objects of interest from other objects or from pure background (Decision Step). There are various possibilities how these two basic steps can be realized, as can be seen in the different proposed detection methods in the literature. An ideal detection algorithm should provide high recognition sensitiv ity with high decision accuracy and require a reasonable computation effort . In reality, a gain in sensitivity is usually only possible with a loss in decision accuracy and with a higher computational effort. So, automatic detection of faint streaks is still a challenge. This paper presents a detection algorithm using spatial filters simulating the geometrical form of possible streaks on a CCD image. This is realized by image convolution. The goal of this method is to generate a more or less perfect match between a streak and a filter by varying the length and orientation of the filters. The convolution answers are accepted or rejected according to an overall threshold given by the ackground statistics. This approach yields as a first result a huge amount of accepted answers due to filters partially covering streaks or remaining stars. To avoid this, a set of additional acceptance criteria has been included in the detection method. All criteria parameters are justified by background and streak statistics and they affect the detection sensitivity only marginally. Tests on images containing simulated streaks and on real images containing satellite streaks show a very promising sensitivity, reliability and running speed for this detection method. Since all method parameters are based on statistics, the true alarm, as well as the false alarm probability, are well controllable. Moreover, the proposed method does not pose any extraordinary demands on the computer hardware and on the image acquisition process.

Treatment allocation in hepatocellular carcinoma: Assessment of the BCLC algorithm

BACKGROUND AND AIMS The Barcelona Clinic Liver Cancer (BCLC) staging system is the algorithm most widely used to manage patients with hepatocellular carcinoma (HCC). We aimed to investigate the extent to which the BCLC recommendations effectively guide clinical practice and assess the reasons for any deviation from the recommendations. MATERIAL AND METHODS The first-line treatments assigned to patients included in the prospective Bern HCC cohort were analyzed. RESULTS Among 223 patients included in the cohort, 116 were not treated according to the BCLC algorithm. Eighty percent of the patients in BCLC stage 0 (very early HCC) and 60% of the patients in BCLC stage A (early HCC) received recommended curative treatment. Only 29% of the BCLC stage B patients (intermediate HCC) and 33% of the BCLC stage C patients (advanced HCC) were treated according to the algorithm. Eighty-nine percent of the BCLC stage D patients (terminal HCC) were treated with best supportive care, as recommended. In 98 patients (44%) the performance status was disregarded in the stage assignment. CONCLUSION The management of HCC in clinical practice frequently deviates from the BCLC recommendations. Most of the curative therapy options, which have well-defined selection criteria, were allocated according to the recommendations, while the majority of the palliative therapy options were assigned to patients with tumor stages not aligned with the recommendations. The only parameter which is subjective in the algorithm, the performance status, is also the least respected.

SOP: Parallel surrogate global optimization with Pareto center selection for computationally expensive single objective problems

This paper presents a parallel surrogate-based global optimization method for computationally expensive objective functions that is more effective for larger numbers of processors. To reach this goal, we integrated concepts from multi-objective optimization and tabu search into, single objective, surrogate optimization. Our proposed derivative-free algorithm, called SOP, uses non-dominated sorting of points for which the expensive function has been previously evaluated. The two objectives are the expensive function value of the point and the minimum distance of the point to previously evaluated points. Based on the results of non-dominated sorting, P points from the sorted fronts are selected as centers from which many candidate points are generated by random perturbations. Based on surrogate approximation, the best candidate point is subsequently selected for expensive evaluation for each of the P centers, with simultaneous computation on P processors. Centers that previously did not generate good solutions are tabu with a given tenure. We show almost sure convergence of this algorithm under some conditions. The performance of SOP is compared with two RBF based methods. The test results show that SOP is an efficient method that can reduce time required to find a good near optimal solution. In a number of cases the efficiency of SOP is so good that SOP with 8 processors found an accurate answer in less wall-clock time than the other algorithms did with 32 processors.

CHEOPS Performance for Exomoons: The Detectability of Exomoons by Using Optimal Decision Algorithm

Many attempts have already been made to detect exomoons around transiting exoplanets, but the first confirmed discovery is still pending. The experiences that have been gathered so far allow us to better optimize future space telescopes for this challenge already during the development phase. In this paper we focus on the forthcoming CHaraterising ExOPlanet Satellite (CHEOPS), describing an optimized decision algorithm with step-by-step evaluation, and calculating the number of required transits for an exomoon detection for various planet moon configurations that can be observable by CHEOPS. We explore the most efficient way for such an observation to minimize the cost in observing time. Our study is based on PTV observations (photocentric transit timing variation) in simulated CHEOPS data, but the recipe does not depend on the actual detection method, and it can be substituted with, e.g., the photodynamical method for later applications. Using the current state-of-the-art level simulation of CHEOPS data we analyzed transit observation sets for different star planet moon configurations and performed a bootstrap analysis to determine their detection statistics. We have found that the detection limit is around an Earth-sized moon. In the case of favorable spatial configurations, systems with at least a large moon and a Neptune-sized planet, an 80% detection chance requires at least 5-6 transit observations on average. There is also a nonzero chance in the case of smaller moons, but the detection statistics deteriorate rapidly, while the necessary transit measurements increase quickly. After the CoRoT and Kepler spacecrafts, CHEOPS will be the next dedicated space telescope that will observe exoplanetary transits and characterize systems with known Doppler-planets. Although it has a smaller aperture than Kepler (the ratio of the mirror diameters is about 1/3) and is mounted with a CCD that is similar to Kepler's, it will observe brighter stars and operate with larger sampling rate; therefore, the detection limit for an exomoon can be the same as or better, which will make CHEOPS a competitive instruments in the quest for exomoons.