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.

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.

Measurement of the neutrino-oxygen neutral-current interaction cross section by observing nuclear deexcitation γ rays

We report the first measurement of the neutrino-oxygen neutral-current quasielastic (NCQE) cross section. It is obtained by observing nuclear deexcitation γ rays which follow neutrino-oxygen interactions at the Super-Kamiokande water Cherenkov detector. We use T2K data corresponding to 3.01 × 1020 protons on target. By selecting only events during the T2K beam window and with well-reconstructed vertices in the fiducial volume, the large background rate from natural radioactivity is dramatically reduced. We observe 43 events in the 4–30 MeV reconstructed energy window, compared with an expectation of 51.0, which includes an estimated 16.2 background events. The background is primarily nonquasielastic neutral-current interactions and has only 1.2 events from natural radioactivity. The flux-averaged NCQE cross section we measure is 1.55 × 10−38 cm2 with a 68% confidence interval of ð1.22; 2.20Þ × 10−38 cm2 at a median neutrino energy of 630 MeV, compared with the theoretical prediction of 2.01 × 10−38 cm2.

Cosmic-ray exposure ages of pallasites

We analyzed cosmogenic nuclides in metal and/or silicate (primarily olivine) separated from the main-group pallasites Admire, Ahumada, Albin, Brahin, Brenham, Esquel, Finmarken, Glorieta Mountain, Huckitta, Imilac, Krasnojarsk, Marjalahti, Molong, Seymchan, South Bend, Springwater, and Thiel Mountains and from Eagle Station. The metal separates contained an olivine fraction which although small, <1 wt% in most cases, nonetheless contributes significantly to the budgets of some nuclides (e.g., up to 35% for Ne-21 and Al-26). A correction for olivine is therefore essential and was made using model calculations and/or empirical relations for the production rates of cosmogenic nuclides in iron meteoroids and/or measured elemental concentrations. Cosmic-ray exposure (CRE) ages for the metal phases of the main-group pallasites range from 7 to 180 Ma, but many of the ages cluster around a central peak near 100 Ma. These CRE ages suggest that the parent body of the main-group pallasites underwent a major break-up that produced most of the meteorites analyzed. The CRE age distribution for the pallasites overlaps only a small fraction of the distribution for the IIIAB iron meteorites. Most pallasites and IIIAB irons originated in different collisions, probably on different parent bodies; a few IIIABs and pallasites may have come out of the same collision but a firm conclusion requires further study. CRE ages calculated from noble gas and radionuclide data of the metal fraction are higher on average than the Ne-21 exposure ages obtained for the olivine samples. As the metal and olivine fractions were taken in most cases from different specimens, the depth-dependency of the production rate ratio Be-10/Ne-21 in metal, not accounted for in our calculations, may explain the difference.