Share Email Print

Proceedings Paper

Automated segmentation of mucosal change in rhinosinusitis patients
Author(s): William F. Sensakovic; Jayant M. Pinto; Faud M. Baroody; Adam Starkey; Samuel G. Armato
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Rhinosinusitis is a sinonasal disease affecting 16% of the population. Volumetric segmentation can provide objective data that is useful when determining stage and therapeutic response. An automated volumetric segmentation method was developed and tested. Four patients underwent baseline and follow-up CT scans. For each patient, five sections were outlined by two otolaryngologists and the automated method. The median Dice coefficient between otolaryngologists was 0.74. The otolaryngologist and automated segmentations demonstrated acceptable agreement with a median Dice coefficient of 0.61. This automated method represents the first step in the creation of a computerized system for the quantitative 3D analysis of rhinosinusitis.

Paper Details

Date Published: 9 March 2010
PDF: 7 pages
Proc. SPIE 7624, Medical Imaging 2010: Computer-Aided Diagnosis, 76243N (9 March 2010); doi: 10.1117/12.844282
Show Author Affiliations
William F. Sensakovic, The Univ. of Chicago (United States)
Jayant M. Pinto, The Univ. of Chicago (United States)
Faud M. Baroody, The Univ. of Chicago (United States)
Adam Starkey, The Univ. of Chicago (United States)
Samuel G. Armato, The Univ. of Chicago (United States)

Published in SPIE Proceedings Vol. 7624:
Medical Imaging 2010: Computer-Aided Diagnosis
Nico Karssemeijer; Ronald M. Summers, Editor(s)

© SPIE. Terms of Use
Back to Top