Thoracic hybrid PET/CT registration using improved hybrid feature intensity multimodal demon

PET/CT images are commonly used for cancer detection and management. In order to obtain high accuracy of tumour interpretation as well as the following treatment planning, accurate registration of these two is highly important. The use of hybrid PET/CT scanner to physically co-register these images does not fully solve the nonlinear misregistration problem due to physiological motions such as breathing and cardiac motions. This paper proposes an improved hybrid feature intensity multimodal demon registration algorithm to register PET/CT images acquired from hybrid PET/CT scanner. In basis, the method comprises of 3 major steps: PET sinogram filtering based on 3D hybrid mean-median filter; segmentation of structures from both PET/CT images (the lungs, the heart and the tumour) and registration of PET/CT images using feature intensity multimodal demon method. The segmented structures acted as “features” to be integrated in the registration process in which an improved intensity based multimodal demon registration was used. The improved multimodal demon used a combination of sum of conditional variations (SCV) and multimodality independent neighbourhood descriptive (MIND) similarity measures. Overall, the proposed hybrid feature intensity multimodal registration method was tested on the simulated NCAT PET/CT images and 21 clinical hybrid PET/CT datasets. Experimental results showed that the combination of SCV and MIND similarity measures produced the best registration result for PET/CT misregistration problem. The success of the registration of the patient datasets was validated through improved lung volume overlap between the PET and the CT lung post registration according to Dice coefficient as well as Hausdorff distance score. The registration method increased the Dice and the Hausdorff distance measures by 4.46% and 22.38% in average respectively after registration in which the registration improvement is more than double as achieved by FFD and previous method. It is concluded that our proposed PET/CT registration algorithm is better than the standard FFD registration technique; thus has the potential to be utilised in clinical application.