Among hepatocellular carcinoma (HCC), early HCC such as well-differentiated hepatocellular carcinoma is more difficult to distinguish from non-cancer than other cancers. In particular, very well-differentiated hepatoc...
详细信息
ISBN:
(纸本)9798350324471
Among hepatocellular carcinoma (HCC), early HCC such as well-differentiated hepatocellular carcinoma is more difficult to distinguish from non-cancer than other cancers. In particular, very well-differentiated hepatocellular carcinoma is even more difficult to distinguish, and it is difficult for pathologists to distinguish between cancer and non-cancer from a single nucleus image. If a function to distinguish cancer with a single cell nucleus image is realized, it may be possible to find new features related to nuclei that are useful for differentiating early HCC. The function will also be very helpful in needle biopsy where the area that can be observed is limited. In this study, we investigated the potential to discriminate cancer/non-cancer from an image of a single hepatocyte nucleus using CNN. The results indicated that discrimination was achievable with a correct rate of around 70%. The probability of cancer/non-cancer was visualized on WSI. The visualization results indicated a difference between cancerous and non-cancerous areas in 71% of the cases, which will help pathologists distinguish region of interest. Grouping sections with similar features also proved useful in improving accuracy and visualization results.
We present two techniques that make document collection visualizations more informative. Icon abacus uses the horizontal position of icon groups to communicate document attributes. Ghost icons show linked documents by...
详细信息
ISBN:
(纸本)1581138768
We present two techniques that make document collection visualizations more informative. Icon abacus uses the horizontal position of icon groups to communicate document attributes. Ghost icons show linked documents by adding temporary icons and by highlighting or dimming existing ones.
Deep learning is actively used in a wide range of fields for scientific discovery. To effectively apply deep learning to a particular problem, it is important to select an appropriate network architecture and other hy...
详细信息
ISBN:
(纸本)9781728108582
Deep learning is actively used in a wide range of fields for scientific discovery. To effectively apply deep learning to a particular problem, it is important to select an appropriate network architecture and other hyper-parameters (at each layer). Evolving architectures and hyper-parameters using a genetic algorithm is one current approach to search the huge space of all possible configurations to find those more optimal for the problem. However, examining an evolutionary process and tuning the genetic algorithm are challenging, pushing most users to treat the process as a black box. To address this challenge, we propose a visualization system for evolutionary neural networks for deep learning. The key feature of our visualization system is to provide a visual analytics environment for evaluating a genetic algorithm in order to improve the underlying operations to reduce time to find good solutions. Our system is able to not only visualize how a genetic algorithm traverses its search space but also allows users to examine evolving networks in-depth to get insights to improve performance through interactive visualization components.
We address the task of visualizing machine-readable natural language parser output in a graphical form, convenient for users. While there are numerous available tools implementing similar functionality, their resultin...
详细信息
ISBN:
(纸本)9781538622018
We address the task of visualizing machine-readable natural language parser output in a graphical form, convenient for users. While there are numerous available tools implementing similar functionality, their resulting diagrams are typically aimed at language specialists, and are arguably difficult to understand for inexperienced second language learners. In contrast, our system uses a specialized language learning system (WordBricks) as a visualization module, and is deliberately designed to help language learners to understand the structure of natural language sentences. We hope that the resulting software tool (available for the Android mobile platform) will be beneficial for regular use in a variety of language learning scenarios.
With the increasing amount of Automatic Identification System, AIS data, an effective analysis method and technology for large-scale data are a challenge. informationvisualization is a suitable technology for people ...
详细信息
ISBN:
(纸本)9781509011025
With the increasing amount of Automatic Identification System, AIS data, an effective analysis method and technology for large-scale data are a challenge. informationvisualization is a suitable technology for people without professional data mining knowledge, such as navigation managers and ship drivers, for understanding mass AIS data. We implement direct and summary visualization of AIS information. Visual graphs can assist in real-time monitoring of key areas, including dense areas, high-speed areas, extreme slow-down areas as well as other areas. Furthermore, visual graphs can provide identification and vessel behavior understanding and are conducive in regularizing driving behavior, recognizing key areas and improving navigation safety.
This paper presents an image processing algorithm simulating a sub-pixel evolution of an image by mean curvature motion or by affine curvature motion. The sub-pixel algorithm computes the image curvature directly on t...
详细信息
ISBN:
(纸本)9781424479948
This paper presents an image processing algorithm simulating a sub-pixel evolution of an image by mean curvature motion or by affine curvature motion. The sub-pixel algorithm computes the image curvature directly on the smoothed level lines, and yields a microscopic visualization of the curvature map revealing many image details, and getting rid of aliasing effects. This "curvature microscope" showing curvatures in false colors runs on line on any image proposed by users at http://***/pub/algo/cmmm_image_curvature_microscope/.
A pusher-plate vortex blood pump has been developed with the objective to prevent thrombus formation on blood-contacting surfaces. Flow visualization experiments with an in-vitro model indicates strong vortex motions ...
详细信息
ISBN:
(纸本)0780320506
A pusher-plate vortex blood pump has been developed with the objective to prevent thrombus formation on blood-contacting surfaces. Flow visualization experiments with an in-vitro model indicates strong vortex motions throughout the cardiac cycle induced with the use of a hemofoil inlet valve.
Virtual reality (VR) environments are typically designed so users feel present in a single virtual world at a time, but this creates a problem for applications that require visual comparisons (e.g., forest scientists ...
详细信息
ISBN:
(纸本)9781728113777
Virtual reality (VR) environments are typically designed so users feel present in a single virtual world at a time, but this creates a problem for applications that require visual comparisons (e.g., forest scientists comparing multiple data-driven virtual forests). To address this, we present Worlds-in-Wedges, a 3D user interface and visualization technique that supports comparative immersive visualization by dividing the virtual space surrounding the user into volumetric wedges. There are three visual/interactive levels. The first, worlds-in-context, visualizes high-level relationships between the worlds (e.g., a map for worlds that are related in space). The second level, worlds-in-miniature, is a multi-instance implementation of the World-in-Miniature technique extended to support mutlivariate glyph visualization. The third level, worlds-in-wedges, displays multiple large-scale worlds in wedges that act as volumetric portals. The interface supports navigation, selection, and view manipulation. Since the techniques were inspired directly by problems facing forest scientists, the interface was evaluated by building a complete multivariate data visualization of the US Forest Service Forest Inventory and Analysis public dataset. Scientist user feedback and lessons from iterative design are reported.
Effective application of Augmented Reality user interfaces is one of the challenging trends of industrial cyber-physical systems development and implementation. Despite reach functionality of modern AR devices (like g...
详细信息
暂无评论