Share Email Print

Proceedings Paper

Validating automatic semantic annotation of anatomy in DICOM CT images
Author(s): Sayan D. Pathak; Antonio Criminisi; Jamie Shotton; Steve White; Duncan Robertson; Bobbi Sparks; Indeera Munasinghe; Khan Siddiqui
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In the current health-care environment, the time available for physicians to browse patients' scans is shrinking due to the rapid increase in the sheer number of images. This is further aggravated by mounting pressure to become more productive in the face of decreasing reimbursement. Hence, there is an urgent need to deliver technology which enables faster and effortless navigation through sub-volume image visualizations. Annotating image regions with semantic labels such as those derived from the RADLEX ontology can vastly enhance image navigation and sub-volume visualization. This paper uses random regression forests for efficient, automatic detection and localization of anatomical structures within DICOM 3D CT scans. A regression forest is a collection of decision trees which are trained to achieve direct mapping from voxels to organ location and size in a single pass. This paper focuses on comparing automated labeling with expert-annotated ground-truth results on a database of 50 highly variable CT scans. Initial investigations show that regression forest derived localization errors are smaller and more robust than those achieved by state-of-the-art global registration approaches. The simplicity of the algorithm's context-rich visual features yield typical runtimes of less than 10 seconds for a 5123 voxel DICOM CT series on a single-threaded, single-core machine running multiple trees; each tree taking less than a second. Furthermore, qualitative evaluation demonstrates that using the detected organs' locations as index into the image volume improves the efficiency of the navigational workflow in all the CT studies.

Paper Details

Date Published: 25 February 2011
PDF: 11 pages
Proc. SPIE 7967, Medical Imaging 2011: Advanced PACS-based Imaging Informatics and Therapeutic Applications, 796704 (25 February 2011); doi: 10.1117/12.878355
Show Author Affiliations
Sayan D. Pathak, Microsoft Corp. (United States)
Antonio Criminisi, Microsoft Research Cambridge (United Kingdom)
Jamie Shotton, Microsoft Research Cambridge (United Kingdom)
Steve White, Microsoft Corp. (United States)
Duncan Robertson, Microsoft Research Cambridge (United Kingdom)
Bobbi Sparks, Microsoft Corp. (United States)
Indeera Munasinghe, Microsoft Research Cambridge (United Kingdom)
Khan Siddiqui, Microsoft Corp. (United States)

Published in SPIE Proceedings Vol. 7967:
Medical Imaging 2011: Advanced PACS-based Imaging Informatics and Therapeutic Applications
William W. Boonn M.D.; Brent J. Liu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?