Résumé
IntroductionFor patients with unresectable pancreatic tumors, stereotactic magnetic resonance guided adaptive radiation therapy (SMART) increases survival by delivering a high biologically effective dose in few fractions, although many patients still experience early metastatic or local recurrence [1, 2]. To address this challenge, radiomics leverages mathematical analysis to extract and quantify textural information from medical images, thereby providing additional insights to predict such outcomes. Meanwhile, delta-radiomics assesses the variation in features captured at treatment times and has demonstrated potential in predicting radiotherapy outcomes when combined with machine learning [3]. However, in the case of pancreatic cancer, these studies lack both internal and external validation, which we aim to address here by rigorously showing the performance of such models.MethodsWe included all patients treated with SMART for unresectable pancreatic ductal adenocarcinoma from Montpellier Cancer Institute (France) and from University Hospital La Milagrosa, Madrid (Spain). For all these patients, 0.35T T1-w TrueFISP simulation (simu) and fraction (Fn) MRI were acquired. Radiomics features were extracted following IBSI guidelines [4] on the manually annotated gross tumor volume (GTV) ROI. Delta-radiomics features were calculated between different Fn and simu, and reliable features, as identified in a previous study [5], were analyzed. Various feature selection algorithms and predictive machine learning models were evaluated to predict local recurrence at 1 year (LR1y) and metastatic recurrence at 9 months (MR9m) using radiomics or delta-radiomics data from a single time-point. Prediction models were trained on 70% of the Montpellier dataset after feature selection and first evaluated with an internal validation cohort of 25 patients. A subsequent evaluation was performed using an external validation cohort of 37 patients from Madrid, where radiomics features were harmonized using the ComBat method [6]. Both evaluations were performed using bootstrapping (n=200) to compute the 95% confidence intervals for the area under the curve (AUC) and the Brier score. Results85 patients were recruited from Montpellier Cancer Institute (France) and 37 from University Hospital La Milagrosa, Madrid (Spain). In the first cohort, 14 presented LR1y and 44 MR9m status while they were 5 and 15 respectively in the second cohort. In the internal validation group, the Random Forest (RF)+RF model using F3 radiomics data achieved the highest AUC of 0.96 (95% CI: 0.87-1.00) for predicting LR1y, with a Brier score of 0.08 (95% CI: 0.03-0.14), 84% sensitivity, and 100% specificity. For MR9m, the RF+ADABOOST model with F1/F3 delta-radiomics data yielded an AUC of 0.83 (95% CI: 0.66-0.97), a Brier score of 0.22 (95% CI: 0.20-0.24), 91% sensitivity, and 75% specificity.In the external validation cohort, these models demonstrated an AUC of 0.71 (95% CI: 0.54-0.84) for LR1y and 0.51 (95% CI: 0.28-0.75) for MR9m, with Brier scores of 0.19 (95% CI: 0.11-0.27) and 0.25 (95% CI: 0.22-0.29), respectively. Sensitivity and specificity were 40% and 78% for LR1y, and 40% and 68% for MR9m.In the external validation cohort, the ANOVA K BEST+PSVM model using Simu radiomics data achieved the highest AUC of 0.80 (95% CI: 0.50-0.99) for LR1y, with a Brier score of 0.25 (95% CI: 0.23-0.27), 80% sensitivity, and 56% specificity. For MR9m, the ANOVA K BEST+RF model using F1/F3 delta-radiomics data achieved an AUC of 0.85 (95% CI: 0.71-0.96), a Brier score of 0.23 (95% CI: 0.22-0.24), 73% sensitivity, and 82% specificity.DiscussionThis study demonstrates the potential of delta-radiomics data combined with machine learning models to predict radiotherapy outcomes for patients with pancreatic tumors. Rigorous internal and external validation was crucial for assessing model reliability and generalizability. While LR1y predictions showed strong performance in internal validation, they significantly declined in the external cohort due to the low incidence of local recurrence, which highlighted the need for recalibration [7]. In contrast, MR9m predictions, although not as strong as LR1y, maintained robust performance with F1/F3 delta-radiomics models. This is particularly encouraging, as metastatic recurrence was the primary cause of mortality in the Montpellier dataset (23 out of 34). Finally, the application of the ComBat method for harmonizing radiomics features was limited by small subgroup sample sizes (n<20), preventing its full utilization. ConclusionThis study highlights the potential of delta-radiomics combined with machine learning to predict radiotherapy outcomes in unresectable pancreatic tumors, demonstrating the importance of rigorous validation. Future work should prioritize the inclusion of additional cases and the enhancement of model calibration. Incorporating clinical and dosimetric features could further augment predictive power and address the challenges observed in the external validation.Data and Code Availability StatementNo data is available for this abstract. Code is available online at https://github.com/ftach/delta-rad.References[1] Chuong MD, Lee P, Low DA, et al. (2024) Stereotactic MR-guided on-table adaptive radiation therapy (SMART) for borderline resectable and locally advanced pancreatic cancer: A multi-center, open-label phase 2 study. Radiother Oncol 191:110064.[2] Bordeau K, Michalet M, Keskes A, et al. (2022) Stereotactic MR-guided adaptive radiotherapy for pancreatic tumors: Updated results of the Montpellier prospective registry study. Cancers (Basel) 15:7.[3] Nardone V, Reginelli A, Rubini D, Gagliardi F, Del Tufo S, Belfiore MP, Boldrini L, Desideri I, Cappabianca S (2024) Delta Radiomics: An Updated Systematic Review. La Radiologia Medica 129(8):1197-1214.[4] Zwanenburg A, Leger S, Vallières M, Löck S (2016) Image biomarker standardisation initiative. arXiv preprint arXiv:1612.07003.[5] Michalet M, Valenzuela G, Debuire P, Riou O, Azria D, Nougaret S, Tardieu M (2024) Robustness of Radiomics Features on 0.35 T Magnetic Resonance Imaging for Magnetic Resonance-Guided Radiotherapy. Physics and Imaging in Radiation Oncology 31.[6] Orlhac F, Eertink JJ, Cottereau A-S, Zijlstra JM, Thieblemont C, Meignan M, Boellaard R, Buvat I (2022) A Guide to ComBat Harmonization of Imaging Biomarkers in Multicenter Studies. Journal of Nuclear Medicine 63(2):172-179.[7] Van Calster B, McLernon DJ, van Smeden M, Wynants L, Steyerberg EW, Bossuyt P, Collins GS, et al. (2019) Calibration: The Achilles Heel of Predictive Analytics. BMC Medicine 17(1):230.