Learn More
With the widespread dissemination of picture archiving and communication systems (PACSs) in hospitals, the amount of imaging data is rapidly increasing. Effective image retrieval systems are required to manage these complex and large image databases. The authors reviewed the past development and the present state of medical image retrieval systems including(More)
PURPOSE To assess the usefulness of (18)F-fluorodeoxyglucose PET/CT in the detection of bone marrow (BM) involvement of high-grade non-Hodgkin's lymphoma (NHL). METHODS One hundred twenty patients with newly diagnosed diffuse large B-cell lymphoma or peripheral T-cell lymphoma between January 2007 and June 2011, who received BM trephine biopsy and(More)
Code repositories of the version control systems have been used as important raw material in lots of developer behavior studies. In such research, commits are usually considered as a unit of development phases, even though they contain limited information over development process. Unlike former source code management systems, Git provides branching, which(More)
The most significant obstacle to multi-hop communications in wireless sensor networks is high link error rate. Thus, an efficient hop-by-hop reliability support scheme is highly required. In this paper, we identify the characteristics of two typical communication patterns in wireless sensor networks and address the problems of previous end-to-end sequence(More)
Quotes, or quotations, are well known phrases or sentences that we use for various purposes such as emphasis, elaboration, and humor. In this paper, we introduce a task of recommending quotes which are suitable for given dialogue context and we present a deep learning recommender system which combines recurrent neural network and convolutional neural(More)
PURPOSE The aim of this study was to investigate the relationship between the maximum standardized uptake values (SUVmax) of primary renal cancers with and without metastatic lesions, if any. We also studied the relationship between the size of primary renal cancers and their SUVmax, and tried to find a clinical value of (18)F-FDG PET-CT for the initial(More)
As the use of positron emission tomography-computed tomography (PET-CT) has increased rapidly, there is a need to retrieve relevant medical images that can assist image interpretation. However, the images themselves lack the explicit information needed for query. We constructed a semantically structured database of nuclear medicine images using the(More)
Language models for agglutinative languages have always been hindered in past due to myriad of agglutinations possible to any given word through various affixes.We propose a method to diminish the problem of out-of-vocabulary words by introducing an embedding derived from syllables and morphemes which leverages the agglutinative property. Our model(More)
PURPOSE To determine whether treatment response in patients with knee pain could be predicted using uptake patterns on single-photon emission computed tomography/computed tomography (SPECT/CT) images. METHODS Ninety-five patients with knee pain who had undergone SPECT/CT were included in this retrospective study. Subjects were divided into three groups:(More)
Recent developments in deep learning with application to language modeling have led to success in tasks of text processing, summarizing and machine translation. However, deploying huge language models for mobile device such as on-device keyboards poses computation as a bottleneck due to their puny computation capacities. In this work we propose an embedded(More)
  • 1