13197 research outputs found
Sort by
Decomposition of musculoskeletal structures from radiographs using an improved CycleGAN framework
No full textThis paper presents methods of decomposition of musculoskeletal structures from radiographs into multiple individual muscle and bone structures. While existing solutions require dual-energy scan for the training dataset and are mainly applied to structures with high-intensity contrast, such as bones, we focused on multiple superimposed muscles with subtle contrast in addition to bones. The decomposition problem is formulated as an image translation problem between (1) a real X-ray image and (2) multiple digitally reconstructed radiographs, each of which contains a single muscle or bone structure, and solved using unpaired training based on the CycleGAN framework. The training dataset was created via automatic computed tomography (CT) segmentation of muscle/bone regions and virtually projecting them with geometric parameters similar to the real X-ray images. Two additional features were incorporated into the CycleGAN framework to achieve a high-resolution and accurate decomposition: hierarchical learning and reconstruction loss with the gradient correlation similarity metric. Furthermore, we introduced a new diagnostic metric for muscle asymmetry directly measured from a plain X-ray image to validate the proposed method. Our simulation and real-image experiments using real X-ray and CT images of 475 patients with hip diseases suggested that each additional feature significantly enhanced the decomposition accuracy. The experiments also evaluated the accuracy of muscle volume ratio measurement, which suggested a potential application to muscle asymmetry assessment from an X-ray image for diagnostic and therapeutic assistance. The improved CycleGAN framework can be applied for investigating the decomposition of musculoskeletal structures from single radiographs.journal articl
A Simple and Effective Method for Injecting Word-level Information into Character-aware Neural Language Models
No full textIn this study, we propose a simple and effective method to inject word-level information into character-aware neural language models. Unlike previous approaches, which typically inject word-level information as input to a long short-term memory (LSTM) network, we inject such information into the softmax function. The resultant model can be considered a combination of a character-aware language model and a simple word-level language model. Our injection method can be used in conjunction with previous methods. The results of experiments on 14 typologically diverse languages are provided to empirically show that our injection method performed better than previous methods that inject word-level information at the input, including a gating mechanism, averaging, and concatenation of word vectors. Our method can also be used together with previous injection methods. Finally, we provide a comprehensive comparison with previous injection methods and analyze the effectiveness of word-level information in character-aware language models and the properties of our injection method in detail.journal articl
Enhancing Semantic Correlation between Instances and Relations for Zero-Shot Relation Extraction
No full textZero-shot relation extraction aims to recognize (new) unseen relations that cannot be observed during training. Due to this point, recognizing unseen relations with no corresponding labeled training instances is a challenging task. Recognizing an unseen relation between two entities in an input instance at the testing time, a model needs to grasp the semantic relationship between the instance and all unseen relations to make a prediction. This study argues that enhancing the semantic correlation between instances and relations is key to effectively solving the zero-shot relation extraction task. A new model entirely devoted to this goal through three main aspects was proposed: learning effective relation representation, designing purposeful mini-batches, and binding two-way semantic consistency. Experimental results on two benchmark datasets demonstrate that our approach significantly improves task performance and achieves state-of-the-art results. Our source code and data are publicly available.journal articl
In-Depth Quantification of Cell Division and Elongation Dynamics at the Tip of Growing Arabidopsis Roots Using 4D Microscopy, AI-Assisted Image Processing and Data Sonification
No full textOne of the fundamental questions in plant developmental biology is how cell proliferation and cell expansion coordinately determine organ growth and morphology. An amenable system to address this question is the Arabidopsis root tip, where cell proliferation and elongation occur in spatially separated domains, and cell morphologies can easily be observed using a confocal microscope. While past studies revealed numerous elements of root growth regulation including gene regulatory networks, hormone transport and signaling, cell mechanics and environmental perception, how cells divide and elongate under possible constraints from cell lineages and neighboring cell files has not been analyzed quantitatively. This is mainly due to the technical difficulties in capturing cell division and elongation dynamics at the tip of growing roots, as well as an extremely labor-intensive task of tracing the lineages of frequently dividing cells. Here, we developed a motion-tracking confocal microscope and an Artificial Intelligence (AI)-assisted image-processing pipeline that enables semi-automated quantification of cell division and elongation dynamics at the tip of vertically growing Arabidopsis roots. We also implemented a data sonification tool that facilitates human recognition of cell division synchrony. Using these tools, we revealed previously unnoted lineage-constrained dynamics of cell division and elongation, and their contribution to the root zonation boundaries.journal articl
Complexation study of a 1,3-phenylene-bridged cyclic hexa-naphthalene with fullerenes C60 and C70 in solution and 1D-alignment of fullerenes in the crystals
No full textTo investigate the host ability of a simple macrocycle, 1,3-phenylene-bridged naphthalene hexamer N6, we evaluated the complexation of N6 with fullerenes in toluene and in the crystals. The complexes in the solid-state demonstrate the one-dimensional alignment of fullerenes. The single-crystals of the C60@N6 composite have semiconductive properties revealed by photoconductivity measurements.journal articl
Analysis and Experiments of Parallel Line Feeders as a Practical Inductive Power Transfer System
Get PDF奈良先端科学技術大学院大学博士(工学)doctoral thesi
Modeling hand-scaling skill of dental hygienist and its application to skill training
Get PDF奈良先端科学技術大学院大学博士(工学)doctoral thesi