LAUSR

PURPOSE To identify parametrial infiltration (PMI) in cervical cancer with voxel-based segmentation of integrated PET/MRI images. METHOD This retrospective study enrolled 79 cervical cancer patients confirmed by pathology (FIGO stage IB to IIB) who underwent 18F-FDG PET/MRI prior to surgery. Region of interest (ROI) at the largest tumor level was delineated on the T2W-MR image, and the ROI was applied to PET image of the corresponding layer. Then, these images were postprocessed with segmentation and gray level calculations in the parauterine area. RESULTS In total, 37 patients (46.8%) had postoperative pathology-confirmed PMI, and 42 patients (53.2%) showed no PMI. There was a moderate correlation between pathological results and the gray level values of each region (rs > 0.5, P < 0.001). According to FIGO stage, as the cervical lesions became more malignant, the gray level values gradually increased. The diagnostic results of MRI and PET/MRI were in good agreement (kappa = 0.693, P < 0.001); the accuracy (78.5%), sensitivity (64.9%) and NPV (74.5%) of PET/MRI were slightly higher than those of MRI (74.7%,59.5%,71.2%, respectively), with no statistically significant difference (P = 1.000). The diagnostic results of MRI and PET/MRI+gray level values were generally consistent (kappa = 0.475, P < 0.001); the accuracy (87.3%), sensitivity(83.8%) and NPV(86.4%) of PET/MRI+gray level values were higher than those of MRI, with statistically significant differences (all P values < 0.05). CONCLUSIONS It is feasible to evaluate PMI based on PET/T2W-MRI voxel segmentation and to obtain quantitative and visual indicators. PET/MRI and gray level values considered together can also improve the accuracy, sensitivity and NPV of PMI diagnosis.