RESUMO
While initial therapy of mantle cell lymphoma (MCL) is not standardized, bendamustine-rituximab (BR) is commonly used in older patients. Rituximab (R) maintenance following induction is often utilized. Thus, the open-label, randomized phase II ECOG-ACRIN Cancer Research Group E1411 trial was designed to test two questions: 1) Does addition of bortezomib to BR induction (BVR) and/or 2) addition of lenalidomide to rituximab (LR) maintenance improve progression-free survival (PFS) in patients with treatment-naïve MCL? From 2012-2016, 373 previously untreated patients, 87% ≥ 60 years old, were enrolled in this trial. At a median follow up of 7.5 years, there is no difference in the median PFS of BR compared to BVR (5.5 yrs vs. 6.4 yrs, HR 0.90, 90% CI 0.70, 1.16). There were no unexpected additional toxicities with BVR treatment compared to BR, with no impact on total dose/duration of treatment received. Independent of the induction treatment, addition of lenalidomide to rituximab did not significantly improve PFS, with median PFS in R vs LR (5.9 yrs vs 7.2 yrs, HR 0.84 90% CI 0.62, 1.15). The majority of patients completed the planned 24 cycles of LR at the scheduled dose. In summary, adding bortezomib to BR induction does not prolong PFS in treatment-naïve MCL, and LR maintenance was not associated with longer PFS compared with rituximab alone following BR. Nonetheless, the > 5 year median PFS outcomes in this prospective cooperative group trial indicate the efficacy of BR followed by rituximab maintenance as highly effective initial therapy for older MCL patients. (NCT01415752).
RESUMO
PURPOSE: Artificial intelligence can reduce the time used by physicians on radiological assessments. For 18F-fluorodeoxyglucose-avid lymphomas, obtaining complete metabolic response (CMR) by end of treatment is prognostic. METHODS: Here, we present a deep learning-based algorithm for fully automated treatment response assessments according to the Lugano 2014 classification. The proposed four-stage method, trained on a multicountry clinical trial (ClinicalTrials.gov identifier: NCT01287741) and tested in three independent multicenter and multicountry test sets on different non-Hodgkin lymphoma subtypes and different lines of treatment (ClinicalTrials.gov identifiers: NCT02257567, NCT02500407, 20% holdout in ClinicalTrials.gov identifier: NCT01287741), outputs the detected lesions at baseline and follow-up to enable focused radiologist review. RESULTS: The method's response assessment achieved high agreement with the adjudicated radiologic responses (eg, agreement for overall response assessment of 93%, 87%, and 85% in ClinicalTrials.gov identifiers: NCT01287741, NCT02500407, and NCT02257567, respectively) similar to inter-radiologist agreement and was strongly prognostic of outcomes with a trend toward higher accuracy for death risk than adjudicated radiologic responses (hazard ratio for end of treatment by-model CMR of 0.123, 0.054, and 0.205 in ClinicalTrials.gov identifiers: NCT01287741, NCT02500407, and NCT02257567, compared with, respectively, 0.226, 0.292, and 0.272 for CMR by the adjudicated responses). Furthermore, a radiologist review of the algorithm's assessments was conducted. The radiologist median review time was 1.38 minutes/assessment, and no statistically significant differences were observed in the level of agreement of the radiologist with the model's response compared with the level of agreement of the radiologist with the adjudicated responses. CONCLUSION: These results suggest that the proposed method can be incorporated into radiologic response assessment workflows in cancer imaging for significant time savings and with performance similar to trained medical experts.