Safe "cloudification" of large images through picker APIs.

Autor: Bremer E; Dept Biomedical Informatics, Stony Brook University (SUNY), NY 11794., Kurc T; Dept Biomedical Informatics, Stony Brook University (SUNY), NY 11794., Gao Y; Dept Biomedical Informatics, Stony Brook University (SUNY), NY 11794., Saltz J; Dept Biomedical Informatics, Stony Brook University (SUNY), NY 11794., Almeida JS; Dept Biomedical Informatics, Stony Brook University (SUNY), NY 11794.
Jazyk: angličtina
Zdroj: AMIA ... Annual Symposium proceedings. AMIA Symposium [AMIA Annu Symp Proc] 2017 Feb 10; Vol. 2016, pp. 342-351. Date of Electronic Publication: 2017 Feb 10 (Print Publication: 2016).
Abstrakt: The "Box model" allows users with no particular training in informatics, or access to specialized infrastructure, operate generic cloud computing resources through a temporary URI dereferencing mechanism known as "drop-file-picker API" ("picker API" for sort). This application programming interface (API) was popularized in the web app development community by DropBox, and is now a consumer-facing feature of all major cloud computing platforms such as Box.com, Google Drive and Amazon S3. This reports describes a prototype web service application that uses picker APIs to expose a new, "cloudified", API tailored for image analysis, without compromising the private governance of the data exposed. In order to better understand this cross-platform cloud computing landscape, we first measured the time for both transfer and traversing of large image files generated by whole slide imaging (WSI) in Digital Pathology. The verification that there is extensive interconnectivity between cloud resources let to the development of a prototype software application that exposes an image-traversing REST API to image files stored in any of the consumer-facing "boxes". In summary, an image file can be upload/synchronized into a any cloud resource with a file picker API and the prototype service described here will expose an HTTP REST API that remains within the safety of the user's own governance. The open source prototype is publicly available at sbu-bmi.github.io/imagebox. Availability The accompanying prototype application is made publicly available, fully functional, with open source, at http://sbu-bmi.github.io/imagebox://sbu-bmi.github.io/imagebox. An illustrative webcasted use of this Web App is included with the project codebase at https://github.com/SBU-BMI/imageboxs://github.com/SBU-BMI/imagebox.
Databáze: MEDLINE