Share Email Print
cover

Proceedings Paper

Multi-stage osteolytic spinal bone lesion detection from CT data with internal sensitivity control
Author(s): M. Wels; B. M. Kelm; A. Tsymbal; M. Hammon; G. Soza; M. Sühling; A. Cavallaro; D. Comaniciu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Spinal bone lesion detection is a challenging and important task in cancer diagnosis and treatment monitoring. In this paper we present a method for fully-automatic osteolytic spinal bone lesion detection from 3D CT data. It is a multi-stage approach subsequently applying multiple discriminative models, i.e., multiple random forests, for lesion candidate detection and rejection to an input volume. For each detection stage an internal control mechanism ensures maintaining sensitivity on unseen true positive lesion candidates during training. This way a pre-defined target sensitivity score of the overall system can be taken into account at the time of model generation. For a lesion not only the center is detected but also, during post-processing, its spatial extension along the three spatial axes defined by the surrounding vertebral body's local coordinate system. Our method achieves a cross-validated sensitivity score of 75% and a mean false positive rate of 3.0 per volume on a data collection consisting of 34 patients with 105 osteolytic spinal bone lesions. The median sensitivity score is 86% at 2.0 false positives per volume.

Paper Details

Date Published: 23 February 2012
PDF: 8 pages
Proc. SPIE 8315, Medical Imaging 2012: Computer-Aided Diagnosis, 831513 (23 February 2012); doi: 10.1117/12.911169
Show Author Affiliations
M. Wels, Siemens AG (Germany)
B. M. Kelm, Siemens AG (Germany)
A. Tsymbal, Siemens AG (Germany)
M. Hammon, Univ. Hospital Erlangen (Germany)
G. Soza, Siemens AG (Germany)
M. Sühling, Siemens AG (Germany)
A. Cavallaro, Univ. Hospital Erlangen (Germany)
D. Comaniciu, Siemens Corporate Research (United States)


Published in SPIE Proceedings Vol. 8315:
Medical Imaging 2012: Computer-Aided Diagnosis
Bram van Ginneken; Carol L. Novak, Editor(s)

© SPIE. Terms of Use
Back to Top