Recent advances in deep learning, like 3D fully convolutional networks (FCNs), have improved the state-of-the-art in dense semantic segmentation of medical images. However, most network architectures require severely downsampling or cropping the images to meet the memory limitations of today's GPU cards while still considering enough context in the images for accurate segmentation. In this work, we propose a novel approach that utilizes auto-context to perform semantic segmentation at higher resolutions in a multi-scale pyramid of stacked 3D FCNs. We train and validate our models on a dataset of manually annotated abdominal organs and vessels from 377 clinical CT images used in gastric surgery, and achieve promising results with close to 90% Dice score on average. For additional evaluation, we perform separate testing on datasets from different sources and achieve competitive results, illustrating the robustness of the model and approach.

A new time projection chamber (TPC) was developed for neutron lifetime measurement using a pulsed cold neutron spallation source at the Japan Proton Accelerator Research Complex (J-PARC). Managing considerable background events from natural sources and the beam radioactivity is a challenging aspect of this measurement. To overcome this problem, the devel- oped TPC has unprecedented features such as the use of polyether-etherketone plates in the support structure and internal surfaces covered with 6 Li-enriched tiles to absorb outlier neutrons. In this paper, the design and performance of the new TPC are reported in detail.

ABSTRACT:Enantiomer-selective polymerization of (RS)-IX-methylbenzyl methacrylate [(RS)-MBMA] was investigated in toluene at -30oc. Reaction products between cyclohexylmagnesium bromide (cHexMgBr) and axially dissymmetric 2,2 '-diamino-6,6' -dimethylbiphenyl (AMB) in the mole ratio of 1.5: I were used as a chiral initiating system. The polymer produced a biphenyl group from the catalyst fragment. The polymerization proceeded in an anionic coordination mechanism and the racemic monomer was kinetically resolved during the course of the reaction. The enantiomer selectivity ratio when using (R)-AMB was estimated to be r

The neutron lifetime (τ n ) is one of the basic parameters in the weak interaction, and is used for predicting the light element abundance in the early universe. Our group developed a new setup to measure τ n with the goal precision of 0.1% at the polarized beam branch BL05 of MLF, J-PARC. The commissioning data was acquired in 2014 and 2015, and the first set of data to evaluate τ n in 2016, which is expected to yield a statistical uncertainty of O(1)%. This paper presents the current analysis results and the future plans to achieve our goal precision.

We developed a method to enable a time-series comparative analysis of surgical processes based on the surgical data from the navigation system. This method can allow surgeons to identify differences between their procedures and reference procedures such as experts' procedures.

Brain structure segmentation on magnetic resonance (MR) images is important for various clinical applications. It has been automatically performed by using fully convolutional networks. However, it suffers from the class imbalance problem. To address this problem, we investigated how loss weighting strategies work for brain structure segmentation tasks with different class imbalance situations on MR images. In this study, we adopted segmentation tasks of the cerebrum, cerebellum, brainstem, and blood vessels from MR cisternography and angiography images as the target segmentation tasks. We used a U-net architecture with cross-entropy and Dice loss functions as a baseline and evaluated the effect of the following loss weighting strategies: inverse frequency weighting, median inverse frequency weighting, focal weighting, distance map-based weighting, and distance penalty term-based weighting. In the experiments, the Dice loss function with focal weighting showed the best performance and had a high average Dice score of 92.8% in the binary-class segmentation tasks, while the cross-entropy loss functions with distance map-based weighting achieved the Dice score of up to 93.1% in the multi-class segmentation tasks. The results suggested that the distance map-based and the focal weightings could boost the performance of cross-entropy and Dice loss functions in class imbalanced segmentation tasks, respectively.

No abstract

Surgical task analysis developed for quantitative assessment of surgical procedures and surgical performance may provide practical methods and metrics for objective evaluation of surgical expertise.