Validation of nonrigid registration in pretreatment and follow-up PET/CT scans for quantification of tumor residue in lung cancer patients.

Nonrigid registrations of pre- and postradiotherapy (RT) PET/CT scans of NSCLC patients were performed with different algorithms and validated tracking internal landmarks. Dice overlap ratios (DR) of high FDG-uptake areas in registered PET/CT scans were then calculated to study patterns of relapse. For 22 patients, pre- and post-RT PET/CT scans were registered first rigidly and then nonrigidly. For three patients, two types (based on Demons or Morphons) of nonrigid registration algorithms each with four different parameter settings were applied and assessed using landmark validation. The two best performing methods were tested on all patients, who were then classified into three groups: large (Group 1), minor (Group2) or insufficient improvement (Group 3) of registration accuracy. For Group 1 and 2, DRs between high FDG-uptake areas in pre- and post-RT PET scans were determined. Distances between corresponding landmarks on deformed pre-RT and post-RT scans decreased for all registration methods. Differences between Demons and Morphons methods were smaller than 1 mm. For Group 1, landmark distance decreased from 9.5 ± 2.1 mm to 3.8 ± 1.2 mm (mean ± 1 SD, p < 0.001), and for Group 3 from 13.6 ± 3.2 mm to 8.0 ± 2.2 mm (p = 0.025). No significant change was observed for Group 2 where distances decreased from 5.6± 1.3 mm to 4.5 ± 1.1 mm (p = 0.093). DRs of high FDG-uptake areas improved significantly after nonrigid registration for most patients in Group 1. Landmark validation of nonrigid registration methods for follow-up CT imaging in NSCLC is necessary. Nonrigid registration significantly improves matching between pre- and post-RT CT scans for a subset of patients, although not in all patients. Hence, the quality of the registration needs to be assessed for each patient individually. Successful nonrigid registration increased the overlap between pre- and post-RT high FDG-uptake regions.