Browsing by Subject "Knowledge graph"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Knowledge graph applications in medical imaging analysis : a scoping review(2021-12-03) Wang, Song, M.S. in Engineering; Ghosh, Joydeep; Ding, YingThere is an increasing trend to represent domain knowledge in structured graphs, which provide efficient knowledge representations for many downstream tasks. Knowledge graphs are widely used to model prior knowledge in the form of nodes and edges to represent semantically connected knowledge entities, which several works have adopted into different medical imaging applications. We systematically search over five databases to find relevant articles that apply knowledge graphs to medical imaging analysis. After screening, evaluating, and reviewing the selected articles, we performed a systematic analysis. We look at four applications in medical imaging analysis, including disease classification, disease localization and segmentation, report generation, and image retrieval. We also identify limitations of current work, such as the limited amount of available annotated data and weak generalizability to other tasks. We further identify the potential future directions according to the identified limitations, including employing semi-supervised frameworks to alleviate the need for annotated data and exploring task-agnostic models to provide better generalizability. We hope that our article will provide the readers with aggregated documentation of the state-of-the-art knowledge graph applications for medical imaging.Item Survey on graph databases and their applications(2020-08-17) Kanberoglu, Ayberk; Ding, Ying (Information scientist); Acker, AmeliaThe idea of representing information or logic through graphs extends back to 18th century by Leonard Euler. The graph theory is one of the fundamentals of mathematics but it hasn’t been until the recent years where the graph-based data models started to get applied to various aspects of the information world. The relational database models have dominated the database industry for the last fifty years. The precedence of relational models can be attributed to their storage space efficiency, reliability and the created abstraction between the database and the user. Even though relational databases have succeeded for a long time, with the rise of web, big data and unstructured data, the need for new data storage models became apparent. Graph based database models solve most of the shortcomings of relational models and they are quickly gaining popularity among various industries. In this report I will analyze the history of database models starting from the relational models and compare these models to the newer NoSQL storage models focusing on graph-based storage. I will give examples of successful implementation of such storage models and finally I will talk about unique applications of these graph databases