Thin client architecture in support of remote radiology learning

Florian F. Schmitzberger, Justus Roos, Sandy Napel, Geoffrey D. Rubin, David Paik

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We implemented a system for remote radiology learning which provides immediate feedback to the learner. Using a thin remote client, expert readers are asked to answer questions about specified radiological findings. These scans are presented as realtime 2D and 3D presentations which allow the user to freely manipulate them using a thin Java client with all 3D rendering performed on the server side. Answers are stored on the server and are used to provide feedback to learners who are presented with the same questions, using the remote client. Learners can practice on real datasets while receiving immediate feedback on their diagnosis and measurements. Novel concepts introduced are (1) the use of server-side rendering in radiology learning, (2) providing immediate and specific feedback to trainees, (3) the ability to provide useful feedback when a definitive gold standard does not exist and (4) a thin, highly compatible client that runs on common, existing hardware which allows to have more people participating in very complex radiological evaluations, even if there are not at the same site.

Original languageEnglish (US)
Title of host publication24th Annual ACM Symposium on Applied Computing, SAC 2009
Number of pages5
StatePublished - 2009
Externally publishedYes
Event24th Annual ACM Symposium on Applied Computing, SAC 2009 - Honolulu, HI, United States
Duration: Mar 8 2009Mar 12 2009

Publication series

NameProceedings of the ACM Symposium on Applied Computing


Other24th Annual ACM Symposium on Applied Computing, SAC 2009
Country/TerritoryUnited States
CityHonolulu, HI


  • Computed tomography
  • Healthcare applications
  • Learning
  • Radiology
  • Teleradiology

ASJC Scopus subject areas

  • Software


Dive into the research topics of 'Thin client architecture in support of remote radiology learning'. Together they form a unique fingerprint.

Cite this