Differentiation of benign and malignant skeletal lesions with quantitative diffusion weighted MRI at 3T

Objectives: To investigate the accuracy of quantitative diffusion-weighted imaging with apparent diffusion coefficient (ADC) mapping for characterizing bone lesions as benign or malignant. Methods: At 3 T, 31 subjects with intramedullary lesions imaged by DWI (b-values 50, 400, 800 s/mm(2)) were included. ADC values (minimum, mean, maximum) were recorded by three observers independently. Interobserver variability and differences between ADC values in benign and malignant lesions were assessed (unpaired t-test, receiver operating characteristic (ROC) analysis). Results: Of 31 lesions, 18 were benign (osteoblastic (n = 1), chondroid (n = 6), cysts (n = 4), hemangiomatosis (n = 1), fibrous (n = 3), eosinophilic granuloma (n = 1), giant cell tumor (n = 1), osteomyelitis (n = 1)) and 13 were malignant (primary (n = 5), metastases (n = 8)). Overall, there were higher minimum (1.27 x 10(-3) mm(2)/s vs 0.68 x 10(-3) mm(2)/s, p < 0.001), mean (1.68 x 10(-3) mm(2)/s vs 1.13 x 10(-3) mm(2)/s, p < 0.001), and maximum (2.09 x 10(-3) mm(2)/s vs 1.7 x 10(-3) mm(2)/s, p = 0.03). ADC values in benign lesions compared with those in malignancies. ROC analysis revealed areas under the curve for minimum, mean, and maximum ADC values of 0.91, 0.85, and 0.71, respectively. ADC measurements were made with high inter-observer concordance (rho = 0.83-0.96). Conclusion: Quantitative ADC maps may have predictive value for the characterization of bone lesions. Benign lesions generally have higher minimum, mean, and maximum ADC values than malignancies, with the minimum value offering the highest accuracy for characterization. (C) 2015 Elsevier Ireland Ltd. All rights reserved.