TY - GEN
T1 - Automatic lesion detection and volume measurement in MR imaging of plexiform neurofibromas
AU - Solomon, Jeffrey
AU - Widemann, Brigitte
AU - Warren, Kathy
AU - Balis, Frank
AU - Patronas, Nicholas
N1 - Publisher Copyright:
© 2002 IEEE.
Copyright:
Copyright 2015 Elsevier B.V., All rights reserved.
PY - 2002
Y1 - 2002
N2 - Conventional response criteria (RECIST [1], WHO [2]) are inadequate for plexiform neurofibromas (PN) due to their size and complex shapes. An automated method was developed to detect and quantify the volume of PN on STIR MR images. The automated algorithm implements heuristics derived from human' based recognition of lesions (pixel intensity contrast and edge detection/following). A connected component analysis distinguishes multiple non-contiguous lesions and removes lesions considered too small, and an edge following algorithm defines the border of the lesion. This method was validated by two observers, who performed automated volume calculations and manual tracings to estimate tumor volume. The method was reproducible (C.V., 0.6% to 5.6%), and the inter-observer difference in the average tumor volume ranged from 6%±3.8 to -5.2%±5.4. The automated and manual methods of volume determination yielded similar results (R=0.999). The automated method will likely improve the reproducibility and sensitivity of response assessment in clinical trials for patients with PN.
AB - Conventional response criteria (RECIST [1], WHO [2]) are inadequate for plexiform neurofibromas (PN) due to their size and complex shapes. An automated method was developed to detect and quantify the volume of PN on STIR MR images. The automated algorithm implements heuristics derived from human' based recognition of lesions (pixel intensity contrast and edge detection/following). A connected component analysis distinguishes multiple non-contiguous lesions and removes lesions considered too small, and an edge following algorithm defines the border of the lesion. This method was validated by two observers, who performed automated volume calculations and manual tracings to estimate tumor volume. The method was reproducible (C.V., 0.6% to 5.6%), and the inter-observer difference in the average tumor volume ranged from 6%±3.8 to -5.2%±5.4. The automated and manual methods of volume determination yielded similar results (R=0.999). The automated method will likely improve the reproducibility and sensitivity of response assessment in clinical trials for patients with PN.
UR - http://www.scopus.com/inward/record.url?scp=17144425257&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=17144425257&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2002.1029235
DO - 10.1109/ISBI.2002.1029235
M3 - Conference contribution
AN - SCOPUS:17144425257
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 229
EP - 232
BT - 2002 IEEE International Symposium on Biomedical Imaging, ISBI 2002 - Proceedings
PB - IEEE Computer Society
T2 - IEEE International Symposium on Biomedical Imaging, ISBI 2002
Y2 - 7 July 2002 through 10 July 2002
ER -