Quantitative Analysis of MR Imaging to Assess Treatment Response for Patients with Multiple Myeloma by Using Dynamic Intensity Entropy Transformation: A Preliminary Study.

PURPOSE: To develop a quantitative measure of bone marrow changes in magnetic resonance (MR) images and investigate its capability for assessment of treatment response for patients with multiple myeloma (MM).
MATERIALS AND METHODS: This study was retrospective, institutional review board approved, and HIPAA compliant. Informed consent was waived. Patients (n = 64; mean age, 58.8 years [age range, 27-75 years]) who were diagnosed with MM and underwent autologous bone marrow stem cell transplantation (BMT) were evaluated. A pair of spinal MR examinations performed before and after BMT was collected from each patient's records. A three-dimensional dynamic intensity entropy transformation (DIET) method was developed to transform MR T1-weighted signal voxel by voxel to a quantitative entropy enhancement value (qEEV), from which predictor variables were derived to train a linear discriminant analysis classifier by using a leave-one-out method. The output of the linear discriminant analysis provided a qEEV-based response index for quantitative assessment of treatment response. The performance of quantitative response index for the discrimination of responder and nonresponder patients was evaluated by receiver operating characteristic curve analysis.
RESULTS: Among the 46 and 18 clinically diagnosed responder and nonresponder patients, the quantitative response index at a chosen decision threshold correctly identified 42 responder and 17 nonresponder patients. The agreement between the DIET method and the clinical outcome reached 0.922 (59 of 64; κ = 0.816; area under the receiver operating characteristic curve, 0.886 ± 0.042).
CONCLUSION: This study demonstrated the feasibility of quantitative response index to differentiate responder and nonresponder patients and had substantial agreement with clinical outcomes, which indicated that this quantitative measure has the potential to be an image biomarker to assess MM treatment response. © RSNA, 2015.