Gamma distribution model in breast cancer diffusion-weighted imaging

Abstract

Summary form only given. Many diffusion models have been proposed in order to obtain more information from breast tumor tissues through Magnetic Resonance Imaging (MRI) (1). The Gamma distribution (GD) may model MRI signal decay based on a statistical approach. This model considers the Theta parameter, which indicates the statistical dispersion of the distribution, and the k parameter, which is responsible for the probability distribution shape. If Theta shows higher values, then there will be a more spread out distribution and if k shows lower values the distribution shape will be more affected, which would be expected in malignant tumors due to tissue heterogeneity (1). The purpose of this study was to evaluate if GD model is capable of distinguishing between different breast tumors. Materials and Methods: In this study 85 breast tumor lesions were analyzed, including 17 benign lesions (Fibroadenoma, FA) and 68 malignant lesions (43 Invasive Ductal Carcinomas, IDC 19 Invasive Lobular Carcinomas, ILC and 6 Ductal Carcinoma in situ, CDIS). Informed consent was obtained for all patients. Data were acquired using a 3T MRI scanner with a dedicated breast coil and a DWI sequence with 3 orthogonal diffusion gradient directions and 8 b values between 0 and 3000s/mm2. Theta and k parameters were acquired from fitting data to the GD model, and mean values were obtained to compare between benign and malignant lesions, and between histological types. Non-parametric statistics were used (α=0.05). Results and Discussion: Significantly lower Theta and higher k values were observed in benign lesions ((0.65±0.43)×10-3mm2/s, 4.29±1.90, respectively) when compared to malignant lesions ((0.97±0.50)×10-3mm2/s, 1.23±0.52, respectively). It was also possible to differentiate FA from IDC lesions with both Theta and k probably due to IDC heterogeneity, which restricts diffusion. Unlike other diffusion model parameters, these were able to differentiate FA and ILC, and FA and CDIS lesions, suggesting that the GD model could bring advantages over other diffusion models in characterizing breast tumors. This study was partly funded by Fundação para a Ciência e Tecnologia (FCT) under the grant PEst-OE/SAU/UI0645/2014.