TU-A-BRC-08: Impact of Deformable Image Registration on Determining Phenotype Correlations through the Course of Therapy

Abstract

Purpose: Image registration is important for determining correlations of tumor phenotypes to assess and to modify biologically‐guided therapies. Such correlations may vary significantly with different registration algorithms. The sensitivity of phenotype correlations to rigid versus deformable registrations was investigated. Methods: PET/CT images often canine patients with sinonasal cancer were acquired using [F‐18]FDG, [F‐ 18]FLT, and [Cu‐61]Cu‐ATSM prior to and 2–3 fractions into radiotherapy. Post‐treatment FDG‐PET/CT images were acquired 3 months after therapy. CTimages were registered to the planning CT using rigid and fast‐free‐form deformable registrations. The resulting transformations/deformation fields were applied to corresponding PET images. Correlation coefficients between FDG, FLT, Cu‐ATSM were calculated over the GTV at different imaging timepoints (pre:pre, pre:mid, and pre:post treatment). Paired t‐test and the relative differences of Pearson's R were used to investigate the sensitivity of the phenotype correlations to rigid and deformable registrations. Results: The difference between rigid and deformable registrations for pre:pre (Diff=2%, p>0.05) and pre:mid (Diff=−6%, p>0.05) phenotype correlations was insignificant. However, pre:pre phenotype correlations were observed to be very sensitive in dogs with osteoscarcinoma (Diff= 46%) or small tumors (Diff=−20%) due to errors in bony deformations and partial volume effects. Despite not reaching statistical significant, the relative difference in pre:post [18F]FDG correlation of more than −50% indicated that the correlation is very sensitive to registration algorithms. Conclusions: The study demonstrated that canine sinonasal tumors do not deform severely in the early treatment, while substantial variation between the registration algorithms was observed in pre:post phenotype correlation. Therefore, rigid registration is sufficient for determining the phenotype correlations in early treatment assessment. Deformable registration should be considered for correlations with the post‐ treatment imaging data. Future works include repeating the study on human patients and using different deformable registration algorithms to fully investigate the sensitivity of phenotype correlations.