The predictive value of pretherapy [68Ga]Ga-DOTA-TATE PET and biomarkers in [177Lu]Lu-PRRT tumor dosimetry

Abstract

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.

Radiomics and Artificial Intelligence in Radiotheranostics: A Review of Applications for Radioligands Targeting Somatostatin Receptors and Prostate-Specific Membrane Antigens

“…Recently, Akhavanallaf et al [75] developed ML models to predict therapeutic tumor dose using pre-therapy 68 Ga PET and clinicopathological biomarkers for patients with metastatic NETs treated with PRRT. This study retrospectively analyzed 90 segmented metastatic NETs from 25 patients who underwent pre-therapy [ 68 Ga]Ga-DOTA-TATE PET/CT and SPECT/CT at four time points after 177 Lu-DOTA-TATE administration.…”

Theranostic digital twins: Concept, framework and roadmap towards personalized radiopharmaceutical therapies

“…Protein abundance in the blood can influence metabolism and elimination processes. Advancements in on-chip technology, such as microfluidic chips or organoids, offer promising avenues for enhancing physiological data acquisition 71 , 72 , providing detailed insights into physiological processes and facilitating refinement of RPT modeling and dosing strategies.…”

“…Deep learning algorithms, for instance, play a crucial role in analyzing medical images, identifying tumor regions, and optimizing treatment planning and delivery 70 . Machine learning extends its application to predict dose distribution based on PET imaging 71 , 72 . Complementary to mathematical and AI-based techniques, computational tools like Monte Carlo simulations simulate radiation behavior at the atomic level, aiding in predicting the biological effects of radiation 73 .…”