An automatic framework for evaluating the vascular permeability of bone metastases from prostate cancer.

OBJECTIVES Vascular permeability can reflect tumorigenesis and metastasis. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can assess microvascular permeability by pharmacokinetic parameter estimation. Most estimation methods require manually selected arterial input function (AIF) or reference regions (RR). However, the result will be unstable due to the annotation, which relies on personal experience. In this study, we propose an automatic framework for evaluating vascular permeability of bone metastases from prostate cancer without selecting AIF. MATERIALS AND METHODS This retrospective study comprised of 15 prostate cancer patients with bone metastases. Based on clinical consensus for three typical DCE-MRI curve patterns, three characteristic curves as regularization constraints were introduced to the extended Tofts model (ETM) using clustering strategy, and the Clustering-based Blind identification of Multichannel (CBM) framework was then proposed for pharmacokinetic parameter estimation. With automatic segmentation of the whole bone area, we obtained the estimation of the pharmacokinetic parameters in the bone area and quantified for bone metastases. Two experienced radiologists compared the CBM estimations with the diagnostic results and we compared the estimations with those of the ETM in bone metastasis regions to evaluate the feasibility of the CBM framework. RESULTS The higher signal regions of Ktransand Kepindicated the metastasis of prostate cancer, which is consistent with the cancer area marked by the radiologists. In addition, the Ktransand Kepin bone metastasis regions were significantly higher than in normal bone regions (P<0.001, P<0.001). The consistency of estimation by using the CBM framework and conventional ETM method was confirmed by Bland-Altman analysis. CONCLUSION The proposed CBM framework can provide a fully automatic and reliable quantitative estimation of vascular permeability for bone metastases in prostate cancer patients. Key words: DCE-MRI, Prostate bone metastases, Pharmacokinetic parameters, Clustering-based Blind identification of Multichannel framework (CBM framework).