Abstract

We propose a web-accessible image visualization and processing framework well-suited for medical applications. Exploiting client-side HTML5 and WebGL technologies, our proposal allows the end-user to efficiently browse and visualize volumic images in an Out-Of-Core (OOC) manner, annotate and apply server-side image processing algorithms and interactively visualize 3D medical models. Server-side implementation is driven by a file-based, simple, robust and flexible Remote Procedure Call (RPC) scheme well suited for heterogeneous applications. We demonstrate the efficiency of our approach with both an interactive medical image segmentation and a 3D rendering of segmented anatomical structures. As a secondary contribution, we improve the segmentation algorithm with the introduction of user-defined anatomical priors. More info in the papers  [1]  [2] :

Demos

Click here to see a live generic demonstration

Demo for [3] :

Click here to see an example of big data registration (200 CT volumes):

Source code

Source code under CeCILL-B license (BSD-compatible) available here

References