• 대한의용생체공학회:의공학회지
• /
• 제44권4호
• /
• pp.255-263
• /
• 2023

Clinical ultrasound (US) is a widely used imaging modality with various clinical applications. However, capturing a large field of view often requires specialized transducers which have limitations for specific clinical scenarios. Panoramic imaging offers an alternative approach by sequentially aligning image sections acquired from freehand sweeps using a standard transducer. To reconstruct a 3D volume from these 2D sections, an external device can be employed to track the transducer's motion accurately. However, the presence of optical or electrical interferences in a clinical setting often leads to incorrect measurements from such sensors. In this paper, we propose a deep learning (DL) framework that enables the prediction of scan trajectories using only US data, eliminating the need for an external tracking device. Our approach incorporates diverse data types, including correlation volume, optical flow, B-mode images, and rawer data (IQ data). We develop a DL network capable of effectively handling these data types and introduce an attention technique to emphasize crucial local areas for precise trajectory prediction. Through extensive experimentation, we demonstrate the superiority of our proposed method over other DL-based approaches in terms of long trajectory prediction performance. Our findings highlight the potential of employing DL techniques for trajectory estimation in clinical ultrasound, offering a promising alternative for panoramic imaging.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제7권2호
• /
• pp.43-50
• /
• 2018

생체정보 컴퓨팅은 생체신호 센서와 컴퓨터 정보처리를 융합한 정보시스템에 기초하여 컴퓨팅시스템 뿐만 아니라 빅데이터 시스템에 크게 영향을 미치고 있다. 이러한 생체정보는 지금까지의 텍스트, 이미지, 동영상 등의 전통적인 데이터 형식과는 달리 생체신호의 의미를 부여하는 값은 텍스트 기반으로 표현되고, 중요한 이벤트 순간은 이미지 형식으로 저장하며, 시계열 분석을 통한 데이터 변화 예측 및 분석을 위해서는 동영상 형식 등 비정형데이터를 포함하는 복합적인 데이터 형식을 구성한다. 이러한 복합적인 데이터 구성은 개별 생체정보 응용서비스에서 요구하는 데이터의 특징에 따라 텍스트, 이미지, 영상 형식 등으로 각각 분리되어 요청되거나, 상황에 따라 복잡 데이터 형식을 동시에 요구할 수 있다. 기존 생체정보 컴퓨팅 시스템들은 전통적인 컴퓨팅 구성요소, 컴퓨팅 구조, 데이터 처리 방법 등에 의존하므로 데이터 처리성능, 전송능력, 저장효율성, 시스템안전성 등의 측면에서 많은 비효율성을 내포하고 있다. 본 연구에서는 생체정보 처리 컴퓨팅을 효과적으로 지원하는 생체정보 빅데이터 플랫폼을 구축하기 위해 개선된 바이오센싱 융합 빅데이터 컴퓨팅 아키텍처를 제안한다. 제안 아키텍처는 생체신호관련 데이터의 저장 및 전송 효율성, 컴퓨팅 성능, 시스템 안정성 등을 효과적으로 지원하며, 향후 생체정보 컴퓨팅에 최적화된 시스템 구현 및 생체정보 서비스 구축을 위한 기반을 제공할 수 있다.

• Genomics & Informatics
• /
• 제3권2호
• /
• pp.52-54
• /
• 2005

Visualization of the homology information is an important method to analyze the evolutionary and functional meanings of genes. With a database containing model genomes of Homo sapiens, Mus muculus, and Rattus norvegicus, we constructed a web­based comparative analysis tool, BioCovi, to visualize the homology information of mammalian sequences on a very large scale. The user interface has several features: it marks regions whose identity is greater than that specified, it shows or hides gaps from the result of global sequence alignment, and it inverts the graph when total identity is higher than the threshold specified.

• 원예과학기술지
• /
• 제29권4호
• /
• pp.336-344
• /
• 2011

Using the abundant available information about the tomato genome, we developed DNA markers that are linked to disease resistant loci and performed marker-assisted selection (MAS) to construct multi-disease resistant lines and varieties. Resistance markers of Ty-1, T2, and I2, which are linked to disease resistance to Tomato yellow leaf curl virus (TYLCV), Tomato mosaic virus (ToMV), and Fusarium wilt, respectively, were developed in a co-dominant fashion. DNA sequences near the resistance loci of TYLCV, ToMV, and Fusarium wilt were used for primer design. Reported candidate markers for powdery mildew-resistance were screened and the 32.5Cla marker was selected. All four markers (Ty-1, T2, I2, and 32.5Cla) were converted to cleavage amplification polymorphisms (CAPS) markers. Then, the CAPS markers were applied to 96 tomato lines to determine the phenetic relationships among the lines. This information yielded clusters of breeding lines illustrating the distribution of resistant and susceptible characters among lines. These data were utilized further in a MAS program for several generations, and a total of ten varieties and ten inbred lines were constructed. Among four traits, three were introduced to develop varieties and breeding lines through the MAS program; several cultivars possessed up to seven disease resistant traits. These resistant trait-related markers that were developed for the tomato MAS program could be used to select early stage seedlings, saving time and cost, and to construct multi-disease resistant lines and varieties.

• Bioinformatics and Biosystems
• /
• 제2권1호
• /
• pp.33-36
• /
• 2007

Scientific literature is the most reliable and comprehensive source of knowledge for scientific and biomedical information. Citation information in the literature is also reliable source for linking between literatures. We proposed CiNet, a graphic user interface based tool that extracts the trend of the research using citation information. We can navigate related literatures and extract keywords from the linked literature using this tool. These extracted keywords will be helpful to researchers who want to survey the information.

• 한국콘텐츠학회논문지
• /
• 제10권4호
• /
• pp.98-105
• /
• 2010

사람들의 건강에 관련된 혈당, 혈압, 활동량 등을 생체 센서를 이용하여서 생체 정보를 획득하고, 건강상태를 모니터링하기 위한 시스템을 개발하기 위한 연구가 많이 되고 있다. 본 논문에서 생체 정보를 모니터링하여 분석하는 u-헬스 케어 에이전트 시스템을 개발하였다. 활동량 측정은 3축 가속도계 센서 기술을 이용한다. 3축 가속도 센서에서 획득되는 정보를 이용하여 활동량을 분석하여 정확한 활동량을 계산하는 알고리즘을 개발하였다. 기존 시스템들 보다 더 정확한 소모 칼로리를 계산하고, 이를 데이터베이스에 저장 관리한다. 또한 활동량과 생체 정보를 활용하여 건강 상태를 점검할 수 있다.

• Interdisciplinary Bio Central
• /
• 제4권3호
• /
• pp.7.1-7.8
• /
• 2012

With the development of many methods of studying the brain, the field of neuroscience has generated large amounts of information obtained from various techniques: imaging techniques, electrophysiological techniques, techniques for analyzing brain connectivity, techniques for getting molecular information of the brain, etc. A plenty of neuroinformatics databases have been made for storing and sharing this useful information and those databases can be publicly accessed by researchers as needed. However, since there are too many neuroinformatics databases, it is difficult to find the appropriate database depending on the needs of researcher. Moreover, many researchers in neuroscience fields are unfamiliar with using neuroinformatics databases for their studies because data is too diverse for neuroscientists to handle this and there is little precedent for using neuroinformatics databases for their research. Therefore, in this article, we review databases in the field of neuroscience according to both their methods for obtaining data and their objectives to help researchers to use databases properly. We also introduce major neuroinformatics databases for each type of information. In addition, to show examples of novel uses of neuroinformatics databases, we represent several studies that combine neuroinformatics databases of different information types and discover new findings. Finally, we conclude our paper with the discussion of potential applications of neuroinformatics databases.

• 한국생물공학회:학술대회논문집
• /
• 한국생물공학회 2005년도 생물공학의 동향(XVI)
• /
• pp.529-529
• /
• 2005

• 한국생물공학회:학술대회논문집
• /
• 한국생물공학회 2005년도 생물공학의 동향(XVII)
• /
• pp.965-965
• /
• 2005

• Bulletin of the Korean Chemical Society
• /
• 제27권2호
• /
• pp.325-328
• /
• 2006