Medical image segmentation is an important task in medical imaging and diagnosis. Data augmentation can substantially improve the accuracy of medical image segmentation when the dataset has a small amount of medical images. However, the data augmentation methods for medical image are usually based on big models that require extensive search space. Furthermore, excessively complex models often have a heavy burden for the general healthcare organization or researcher. To address this problem, we propose a method of data augmentation that is simple to implement even for the general researcher and simple to transplant across various models. Here we introduce our new methods called KeepMask and KeepMix, which can be simply ported to a variety of models and provide high performance. These methods allow data augmentation without any effect on the target organ or lesion and can also be adapted to multi-class segmentation. KeepMask and KeepMix can not only perturb the background of an existing medical image but also add target organs that are not present to it and generate new images based on the image. In this paper, we performed our methods on both binary class datasets and multi-class datasets and obtained better performance. We conducted numerous experiments showing the predicted segmentation images using our proposed methods obtained more accurate boundaries.

Rapid advances in high-throughput sequencers have made it possible to obtain large amounts of whole genome data quickly and inexpensively. As the amount of data increases, the increase in computation time has become a serious problem. One of the main causes of this problem is file I/O performance. Most pipelines do not implement file I/O suitable for distributed file systems, which are common storage systems in parallel computers used for large-scale analysis. In this study, we developed an I/O system adapted to distributed file systems. In the proposed system, storage access frequency was suppressed by I/O buffers, and thread parallelization by OpenMP was employed. We tested the developed system and a high parallel speedup was achieved. Availability: The developed system is freely available from https://github.com/SatoshiITO/GAPS

The objective of this work is to develop error-bounded lossy compression methods to preserve topological features in 2D and 3D vector fields. Specifically, we explore the preservation of critical points in piecewise linear and bilinear vector fields. We define the preservation of critical points as, without any false positive, false negative, or false type in the decompressed data, (1) keeping each critical point in its original cell and (2) retaining the type of each critical point (e.g., saddle and attracting node). The key to our method is to adapt a vertex-wise error bound for each grid point and to compress input data together with the error bound field using a modified lossy compressor. Our compression algorithm can be also embarrassingly parallelized for large data handling and in situ processing. We benchmark our method by comparing it with existing lossy compressors in terms of false positive/negative/type rates, compression ratio, and various vector field visualizations with several scientific applications.

The objective of this work is to develop error-bounded lossy compression methods to preserve topological features in 2D and 3D vector fields. Specifically, we explore the preservation of critical points in piecewise linear vector fields. We define the preservation of critical points as, without any false positive, false negative, or false type change in the decompressed data, (1) keeping each critical point in its original cell and (2) retaining the type of each critical point (e.g., saddle and attracting node). The key to our method is to adapt a vertex-wise error bound for each grid point and to compress input data together with the error bound field using a modified lossy compressor. Our compression algorithm can be also embarrassingly parallelized for large data handling and in situ processing. We benchmark our method by comparing it with existing lossy compressors in terms of false positive/negative/type rates, compression ratio, and various vector field visualizations with several scientific applications.

ChOWDER is an open-source, web-based scalable display system that consists of multiple display devices on which a web browser operates in cooperation to construct a single large pixel space. Newly introduced functionality of displaying 3D geographic information systems allows us to show large 3D geographic information on ultra-high-resolution tiled display system. This paper describes the method of implementation, use cases, and related works of this functionality.

In the present paper, we propose an efficient direct-iterative hybrid solver for sparse matrices that can derive the scalability of the latest multi-core, many-core, and vector architectures and examine the execution performance of the proposed SLOR-PCR method. We also present an efficient implementation of the PCR algorithm for SIMD and vector architectures so that it is easy to output instructions optimized by the compiler. The proposed hybrid method has high cache reusability, which is favorable for modern low B/F architecture because efficient use of the cache can mitigate the memory bandwidth limitation. The measured performance revealed that the SLOR-PCR solver showed excellent scalability up to 352 cores on the cc-NUMA environment, and the achieved performance was higher than that of the conventional Jacobi and Red-Black ordering method by a factor of 3.6 to 8.3 on the SIMD architecture. In addition, the maximum speedup in computation time was observed to be a factor of 6.3 on the cc-NUMA architecture with 352 cores.

In this paper, we present a study on the available open-source software (OSS) for large-scale data visualization on the SPARC64fx based HPC systems, such as the K computer and also the Fujitsu PRIMEHPC FX family of supercomputers (FX10 and FX100), which are commonly available throughout Japan. It is widely known that these HPC systems have been generating a vast amount of simulation results in a wide range of science and engineering fields. However, there was no much information regarding the large-scale data visualization software and approaches in such HPC infrastructure. In this work, we focused on the visualization approaches where the HPC hardware resources are directly used for the visualization processing, which can be helpful to minimize the large data transfer issue for the visualization and analysis purposes. This study includes both OpenGL (Open Graphics Library) and non-OpenGL based visualization approaches, and also the availability of the GLSL (OpenGL Shading Language) handling functionalities. Although it is a short survey focusing only on the post-processing issue, we expect that this study can be useful and helpful for the current and future potential users of the SPARC64fx CPU based HPC systems, which are still in active use throughout Japan.

An increasing volume of data is produced by computational science applications executing on flagship-class supercomputers, such as the K computer. Most of these huge datasets would later pass through post-processing for visualization and analysis in order to derive meaningful information. Particular characteristics of the computing environment, application, and the dataset itself, can make efficiently exploring the performance capabilities of large-scale storage systems supporting these supercomputer a challenging task. This paper presents a characterization of the I/O and storage activity of jobs executed on the K computer focusing on post-processing purposes, based upon nine months of production operation recorded. Results demonstrate the intensive data demand of K computer applications, both in terms of volume of file I/O carried out during job execution, amount of data staged-in and staged-out, and number of files produced per job. These aspects shed light on challenges and opportunities for specialized data management libraries for posthoc data visualization and analysis.

Due to the continuous increase in the scale of numerical simulations, research on visualization has shifted to in-situ/in-transit approaches. The interactivity of largescale visualization has also become increasingly important. In order to observe largescale visualization data in detail, high-resolution displays, such as those with 8K or 16K resolutions, give an opportunity to inspire new discovery. With the commoditization of high-resolution displays, tiled display walls (TDWs) have facilitated their use for the collaborative research, where a large screen size is required for sharing the content among multiple sites. In this paper, we propose a remote collaboration method that utilizes a TDW driver (ChOWDER), which enables content sharing among multiple sites even with different display configurations, and a visualization application (HIVE) for dynamic content sharing of interactive visualization results.

The development of supercomputers has successfully helped us to carry on complicated simulation with exploded size of dataset. For visualizing such kind of large-scale dataset, reducing the data size by using compression methods is one of the most useful approach. Moreover, parallelization of compression algorithm can greatly improve the efficiency and resolve the limitation of memory size. However, in parallel compression algorithm, interprocessor communication is indispensable, while it is also a bottleneck problem, especially for the general cases that the number of processors is not power-of-two. Parallel POD (proper orthogonal decomposition) compression algorithm is such an example, the number of time steps must be power-of-two for the binary swap scheme. A method that can fully resolve this problem with low computational cost will be very popular. In this paper, we proposed such an approach called 2-3-4 combination approach, which can be simply implemented and also reach high performance of parallel computing algorithms. Furthermore, our method can obtain the best balance among all parallel computing processors. This is achieved by transferring the non-power-of-two problem into power-of-two problem to fully use the best balance feature of binary swap method. We evaluate our approach through applying it to the parallel POD compression algorithm on the K computer.

It is difficult to carry out visualization of the large-scale time-varying data directly, even with the supercomputers. Data compression and ROI (Region of Interest) detection are often used to improve efficiency of the visualization of numerical data. It is well known that the Run Length encoding is a good technique to compress the data where the same sequence appeared repeatedly, such as an image with little change, or a set of smooth fluid data. Another advantage of Run Length encoding is that it can be applied to every dimension of data separately. Therefore, the Run Length method can be implemented easily as a parallel processing algorithm. We proposed two different Run Length based methods. When using the Run Length method to compress a data set, its size may increase after the compression if the data does not contain many repeated parts. We only apply the compression for the case that the data can be compressed effectively. By checking the compression ratio, we can detect ROI. The effectiveness and efficiency of the proposed methods are demonstrated through comparing with several existing compression methods using different sets of fluid data.

Machine-Translation of news headlines is difficult since the sentences are fragmentary and abbreviations and acronyms of proper names are frequently used. Another difficulty is that, since the headline comes at the top of a news article, the context information useful to disambiguate the sense of words and to determine their translation(target word) is not available. This paper proposes a new approach to translating English news headline. In this approach, the abbreviations and acronyms in the headlines are complemented with their coreference in the lead of the article. Moreover, the target word selection is performed by referring to the translation of similar news articles retrieved from a parallel corpus. In the experiment, 100 English headlines are translated into Japanese using a corpus containing 30,000 English-Japanese article pairs, resulting in a 17 % improvement in the target words and a 21 % improvement in the style of translation.