External radiotherapy is a major clinical treatment for localized prostate cancer. Currently, computed tomography (CT) is used to delineate the prostate and to plan the radiotherapy treatment. However, CT images suffer from a poor soft tissue contrast and do not allow an accurate organ delineation. On the contrary, Magnetic resonance imaging (MRI) provides rich details and high soft tissue contrast, allowing tumor detection. Thus, the intra-individual propagation of MRI delineations towards the planning CT may improve tumor targeting. In this paper we introduce a new method to propagate MRI prostate delineations to the planning CT. In a first step, a random forest (RF) classification is performed to coarsely detect the prostate in the CT images, yielding a prostate probability membership for each voxel and a prostate hard segmentation. Then the registration is performed using a new similarity metric which maximizes the probability and the collinearity between the normals of the MR existing contour and the contour resulting from the CT classification. A first study on synthetic data was performed to analyze the influence of the metric parameters with different levels of noise. Then, the method was also evaluated on real MR-CT data using manual alignments and intraprostatic fiducial markers and compared to a classically used mutual information (MI) approach. The proposed metric outperformed MI by 7% in terms of Dice score coefficient (DSC), by 3.14 mm the Hausdorff Distance (HD) and 2.13 mm the markers position errors (MPE). Finally, the impact of registration uncertainties on the treatment planning was evaluated, demonstrating the potential advantage of the proposed approach in a clinical setup to define a precise target.
IEEE journal of biomedical and health informatics. 2016 Jun 16 [Epub ahead of print]
Frederic Commandeur, Antoine Simon, Romain Mathieu, Mohamed Nassef, Juan David Ospina, Yan Rolland, Pascal Haigron, Renaud De Crevoisier, Oscar Acosta