The overall goal of our parent award (R01MH112748) is to manually label 200 magnetic resonance (MR) images from the Human Connectome Project (HCP) into a set of neuroanatomical structures that are more refined and accurate than current MR atlases. One important component of our software contribution efforts has been the development of a custom neurosegmentation module in 3D Slicer, a desktop-based open source image analysis platform with a wide user base and 20-year history. While the desktop solution is efficient for a single user storing all data locally, it is not well-suited for collaborative work on data stored in the cloud (in our case data from the HCP). We thus propose to refactor the custom 3D Slicer module into a web-based editor with a centralized access-controlled database of images that can be deployed on cloud infrastructures. One added feature will be to codify our manual segmentation process into a computerized workflow. These workflows will allow us to more easily adapt and scale the software. Additionally, we will be able to record and publish image segmentation workflows, as well as provenance information for all files generated by these segmentation processes, thereby improving our compliance with open and rigorous science best practices. The project will consist of four aims (i) refactoring core functionalities into web-based tools, (ii) description of our interactive segmentation workflows into a computerized language, (iii) integration of the tools and workflows into SPINE, a web-based virtual laboratory platform, and (iv) deployment on commercial cloud services with proper communication protocols to interact with public data repositories.
The goal of this administrative supplement is to refactor a custom manual neurosegmentation desktop application into a web-based editor with a centralized access-controlled database of images that can be deployed on cloud infrastructures. Refactoring our desktop-based platform into a collaborative cloud- and web-based solution would ?enhance the design, implementation, and ?cloud-readiness? of our editing software and greatly facilitate the scalability of annotation projects not only for the parent award but also for the large community of medical image data annotators.
