Purpose The aim was to quantify inter- and intra-observer variability in manually delineated hepatocellular carcinoma (HCC) lesion contours and the resulting impact on radioembolization (RE) dosimetry. Methods Ten patients with HCC lesions treated with Y-90 RE and imaged with post-therapy Y-90 PET/CT were selected for retrospective analysis. Three radiologists contoured 20 lesions manually on baseline multiphase contrast-enhanced MRIs, and two of the radiologists re-contoured at two additional sessions. Contours were transferred to co-registered PET/CT-based Y-90 dose maps. Volume-dependent recovery coefficients were applied for partial volume correction (PVC) when reporting mean absorbed dose. To understand how uncertainty varies with tumor size, we fit power models regressing relative uncertainty in volume and in mean absorbed dose on contour volume. Finally, we determined effects of segmentation uncertainty on tumor control probability (TCP), as calculated using logistic models developed in a previous RE study. Results The average lesion volume ranged from 1.8 to 194.5 mL, and the mean absorbed dose ranged from 23.4 to 1629.0 Gy. The mean inter-observer Dice coefficient for lesion contours was significantly less than the mean intra-observer Dice coefficient (0.79 vs. 0.85, p < 0.001). Uncertainty in segmented volume, as measured by the Coefficient of Variation (CV), ranged from 4.2 to 34.7% with an average of 17.2%. The CV in mean absorbed dose had an average value of 5.4% (range 1.2–13.1%) without PVC while it was 15.1% (range 1.5–55.2%) with PVC. Using the fitted models for uncertainty as a function of volume on our prior data, the mean change in TCP due to segmentation uncertainty alone was estimated as 16.2% (maximum 48.5%). Conclusions Though we find relatively high inter- and intra-observer reliability overall, uncertainty in tumor contouring propagates into non-negligible uncertainty in dose metrics and outcome prediction for individual cases that should be considered in dosimetry-guided treatment.

Purpose Metastatic neuroendocrine tumors (NETs) overexpressing type 2 somatostatin receptors are the target for peptide receptor radionuclide therapy (PRRT) through the theragnostic pair of 68 Ga/ 177 Lu-DOTATATE. The main purpose of this study was to develop machine learning models to predict therapeutic tumor dose using pre therapy 68 Ga -PET and clinicopathological biomarkers. Methods We retrospectively analyzed 90 segmented metastaticNETs from 25 patients (M14/F11, age 63.7 ± 9.5, range 38-76) treated by 177 Lu-DOTATATE at our institute. Patients underwent both pretherapy [ 68 Ga]Ga-DOTA-TATE PET/CT and four timepoints SPECT/CT at ~ 4, 24, 96, and 168 h post-177 Lu-DOTATATE infusion. Tumors were segmented by a radiologist on baseline CT or MRI and transferred to co-registered PET/CT and SPECT/CT, and normal organs were segmented by deep learning-based method on CT of the PET and SPECT. The SUV metrics and tumor-to-normal tissue SUV ratios (SUV_TNRs) were calculated from 68 Ga -PET at the contour-level. Posttherapy dosimetry was performed based on the co-registration of SPECT/ CTs to generate time-integrated-activity, followed by an in-house Monte Carlo-based absorbed dose estimation. The correlation between delivered 177 Lu Tumor absorbed dose and PET-derived metrics along with baseline clinicopathological biomarkers (such as Creatinine, Chromogranin A and prior therapies) were evaluated. Multiple interpretable machine-learning algorithms were developed to predict tumor dose using these pretherapy information. Model performance on a nested tenfold cross-validation was evaluated in terms of coefficient of determination (R 2 ), mean-absolute-error (MAE), and mean-relative-absolute-error (MRAE). Results SUV mean showed a significant correlation (q-value < 0.05) with absorbed dose (Spearman ρ = 0.64), followed by TLSUV mean (SUV mean of total-lesion-burden) and SUV peak (ρ = 0.45 and 0.41, respectively). The predictive value of PET-SUV mean in estimation of posttherapy absorbed dose was stronger compared to PET-SUV peak , and SUV_TNRs in terms of univariate analysis (R 2 = 0.28 vs. R 2 ≤ 0.12). An optimal trivariate random forest model composed of SUV mean , TLSUV mean , and total liver SUV mean (normal and tumoral liver) provided the best performance in tumor dose prediction with R 2 = 0.64, MAE = 0.73 Gy/GBq, and MRAE = 0.2. Conclusion Our preliminary results demonstrate the feasibility of using baseline PET images for prediction of absorbed dose prior to 177 Lu-PRRT. Machine learning models combining multiple PET-based metrics performed better than using a single SUV value and using other investigated clinicopathological biomarkers. Developing such quantitative models forms the groundwork for the role of 68 Ga -PET not only for the implementation of personalized treatment planning but also for patient stratification in the era of precision medicine.

Purpose The aim was to quantify inter- and intra-observer variability in manually delineated lesion contours and the resulting impact on radionuclide therapy dosimetry. Methods Ten patients with hepatocellular carcinoma lesions treated with 90Y radioembolization (RE) and imaged with post-therapy 90Y PET/CT were selected for retrospective analysis. Three radiologists contoured 20 lesions manually on baseline multiphase contrast-enhanced MRIs and two of the radiologists re-contoured at two additional sessions. Contours were transferred to co-registered PET/CT-based 90Y dose-maps. Volume-dependent recovery-coefficients (RCs) were applied for partial volume correction when reporting mean absorbed dose. To understand how uncertainty varies with tumor size, we fit power models regressing relative uncertainty in volume and in mean absorbed dose on contour volume. Finally, we determined effects of uncertainty on tumor control probability (TCP), as calculated using logistic models developed in a previous report for lesions treated with RE. Results The average lesion volume ranged from 1.8 mL to 194.5 mL and the mean absorbed dose ranged from 23.4 to 1,629.0 Gy. The mean inter-observer Dice coefficient for lesion contours was significantly less than the mean intra-observer Dice coefficient (0.79 vs. 0.85, p < 0.001). Uncertainty in volume, as measured by the Coefficient of Variation (CV) ranged from 4.2% to 34.7% with a mean of 17.2%. For lesions > 8 mL, the CV in mean absorbed dose had an average value of 7.2% (range 1.5% to 12.6%) while for smaller lesions it was 21.7% (range 8.4 to 55.2%). The fitted uncertainty curves as a function of volume, v (in mL), were: %CV (volume) = 23.0* v-0.17 and %CV (mean dose) = 32.4* v-0.44. With this model for uncertainty, the mean change in TCP was 16.2% (maximum 48.5%). Conclusion Though we find relatively high inter- and intra-observer reliability overall, uncertainty in tumor contouring propagates into non-negligible uncertainty in dose metrics and outcome prediction for individual cases that should be considered in dosimetry-guided treatment.