ObjectiveTo evaluate the diagnostic utility of fat (hydroxyapatite) density [DFat (HAP)] on dual-energy computed tomography (DECT) for identifying clinical diagnosed multiple myeloma without bone disease (MNBD) that is not visible on conventional CT scans. Material and MethodsIn this age-gender-examination sites matched case control prospective study, Chest and/or abdominal images on Revolution CT of MNBDs and control subjects were consecutive enrolled in a 1:2 ratio from October 2022 to November 2023. Multiple myeloma was clinical diagnosed according to criteria of the International Myeloma Working Group. Regions of interest (ROIs) were drawn separately for all thoracolumbar vertebrae in the scanning range by two radiologists. Additionally, a radiologist specializing in musculoskeletal imaging supervised the process. DFat (HAP) was extracted from each ROI. The spine was divided into upper thoracic (UPT), middle and lower thoracic (MLT), thoracolumbar (TL), and middle and lower lumbar (MLL) vertebrae. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the diagnostic performance of DFat (HAP) in diagnosing multiple myeloma, and the sensitivity, specificity, and accuracy under the optimal cut-off were determined by Youden index (sensitivity + specificity −1). ResultsA total of 32 and MNBD patients and 64 control patients were included. The total number of ROIs outlined included MNBD group (n = 493) and control group (n = 986). For all vertebrae, DFat(HAP) got average performance in the diagnosis of MNBD (AUC = 0.733, p < 0.001) with a cut-off value of 958 (mg/cm3); the sensitivity, specificity, and accuracy were 58.8 %, 77.8 %, and 71.7 %, respectively. Regarding segment analysis, the diagnostic performance was good for all (AUC, 0.803–0.837; p < 0.001) but the UPT segment (AUC = 0.692, p = 0.002). The optimal diagnostic cut-off values for the MLT, TL, and MLL vertebrae were 955 mg/cm3, 947 mg/cm3, and 947 mg/cm3, respectively; the sensitivity, specificity, and accuracy were 80.0 %-87.5 %, 71.9 %-82.6 %, and 77.1 %-81.6 %, respectively. ConclusionDECT was effective for detecting MNBD, and better diagnostic results can be obtained by grouping different spine segments.
Read full abstract