Share Email Print

Proceedings Paper

Quantitative MRI biomarker for treatment response assessment of multiple myeloma: robustness evaluation using independent test set of prospective cases
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We are developing quantitative radiomic biomarkers for treatment response assessment of multiple myeloma (MM) in MRI. In our previous study, we have developed a 3D dynamic intensity entropy transformation (DIET) method with MRI for deriving a radiomic biomarker for differentiating responders from non-responders in treatment of MM. DIET transforms MR signal voxel by voxel to a quantitative entropy enhancement value (qEEV), from which predictor variables are extracted and combined into a qEEV-based response index (qERI) for quantitative assessment of treatment response. We developed the qERI in a previous retrospective data set of 64 MRI cases. This study evaluated the performance of the qERI-based MRI biomarker using an independent test set of 15 MRI cases collected from an ongoing prospective study, in which 10 and 5 patients were clinically diagnosed as responders and non-responders. The results showed that the agreement between the qERI prediction and the clinical outcome reached 0.80 with a kappa value of 0.57. The area under the ROC curve (AUC) achieved 0.78.

Paper Details

Date Published: 13 March 2019
PDF: 8 pages
Proc. SPIE 10950, Medical Imaging 2019: Computer-Aided Diagnosis, 1095047 (13 March 2019); doi: 10.1117/12.2511898
Show Author Affiliations
Chuan Zhou, Univ. of Michigan (United States)
Qian Dong, Univ. of Michigan (United States)
Heang-Ping Chan, Univ. of Michigan (United States)
Erica L. Campagnaro, Univ. of Michigan (United States)
Jun Wei, Univ. of Michigan (United States)
Lubomir M. Hadjiiski, Univ. of Michigan (United States)

Published in SPIE Proceedings Vol. 10950:
Medical Imaging 2019: Computer-Aided Diagnosis
Kensaku Mori; Horst K. Hahn, 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?