DESK Exposing Server Kit : A framework for web-based medical image display and processing

Purpose and context

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.

(old) Video demo

Interactive demos

Click here to try a live generic demonstration

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

Publication

H. Jacinto, R. K├ęchichan, M. Desvignes, R. Prost, and S. Valette, "A Web Interface for 3D Visualization and Interactive Segmentation of Medical Images", 17th International Conference on 3D Web Technology (Web 3D 2012), Los-Angeles, USA, pp. 51-58, 2012.

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. [Preprint]

Source Code

Our programm makes extensive use of javascript. The most important libraries we use are :

Source code is available here on github . This code is distributed under the CECILL-B license (BSD-compatible) CNRS, INSA-Lyon, UCBL, INSERM.

Design: HTML5 UP.