Share Email Print
cover

Proceedings Paper

Automated detection and quantification of micronodules in thoracic CT scans to identify subjects at risk for silicosis
Author(s): C. Jacobs; S.H.T. T. Opdam; E. M. van Rikxoort; O. M. Mets; J. Rooyackers; P. A. de Jong; M. Prokop; B. van Ginneken
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Silica dust-exposed individuals are at high risk of developing silicosis, a fatal and incurable lung disease. The presence of disseminated micronodules on thoracic CT is the radiological hallmark of silicosis but locating micronodules, to identify subjects at risk, is tedious for human observers. We present a computer-aided detection scheme to automatically find micronodules and quantify micronodule load. The system used lung segmentation, template matching, and a supervised classification scheme. The system achieved a promising sensitivity of 84% at an average of 8.4 false positive marks per scan. In an independent data set of 54 CT scans in which we defined four risk categories, the CAD system automatically classified 83% of subjects correctly, and obtained a weighted kappa of 0.76.

Paper Details

Date Published: 18 March 2014
PDF: 6 pages
Proc. SPIE 9035, Medical Imaging 2014: Computer-Aided Diagnosis, 90351I (18 March 2014); doi: 10.1117/12.2043536
Show Author Affiliations
C. Jacobs, Radboud Univ. Nijmegen Medical Ctr. (Netherlands)
S.H.T. T. Opdam, Technische Univ. Eindhoven (Netherlands)
E. M. van Rikxoort, Radboud Univ. Nijmegen Medical Ctr. (Netherlands)
O. M. Mets, Univ. Medical Ctr. Utrech (Netherlands)
J. Rooyackers, Utrecht Univ. (Netherlands)
P. A. de Jong, Univ. Medical Ctr. Utrecht (Netherlands)
M. Prokop, Radboud Univ. Nijmegen Medical Ctr. (Netherlands)
B. van Ginneken, Radboud Univ. Nijmegen Medical Ctr. (Netherlands)


Published in SPIE Proceedings Vol. 9035:
Medical Imaging 2014: Computer-Aided Diagnosis
Stephen Aylward; Lubomir M. Hadjiiski, Editor(s)

© SPIE. Terms of Use
Back to Top