RESUMO
PURPOSE: Design and evaluate a knowledge-based model using commercially available artificial intelligence tools for automated treatment planning to efficiently generate clinically acceptable hippocampal avoidance prophylactic cranial irradiation (HA-PCI) plans in patients with small-cell lung cancer. MATERIALS AND METHODS: Data from 44 patients with different grades of head flexion (range 45°) were used as the training datasets. A Rapid Plan knowledge-based planning (KB) routine was applied for a prescription of 25 Gy in 10 fractions using two volumetric modulated arc therapy (VMAT) arcs. The 9 plans used to validate the initial model were added to generate a second version of the RP model (Hippo-MARv2). Automated plans (AP) were compared with manual plans (MP) according to the dose-volume objectives of the PREMER trial. Optimization time and model quality were assessed using 10 patients who were not included in the first 44 datasets. RESULTS: A 55% reduction in average optimization time was observed for AP compared to MP. (15 vs 33 min; p = 0.001).Statistically significant differences in favor of AP were found for D98% (22.6 vs 20.9 Gy), Homogeneity Index (17.6 vs 23.0) and Hippocampus D mean (11.0 vs 11.7 Gy). The AP met the proposed objectives without significant deviations, while in the case of the MP, significant deviations from the proposed target values were found in 2 cases. CONCLUSION: The KB model allows automated planning for HA-PCI. Automation of radiotherapy planning improves efficiency, safety, and quality and could facilitate access to new techniques.
Assuntos
Intervenção Coronária Percutânea , Radioterapia de Intensidade Modulada , Humanos , Dosagem Radioterapêutica , Inteligência Artificial , Planejamento da Radioterapia Assistida por Computador/métodos , Irradiação Craniana/métodos , Radioterapia de Intensidade Modulada/métodos , Hipocampo , Aprendizado de Máquina , Órgãos em Risco/efeitos da radiaçãoRESUMO
AIMS AND BACKGROUND: To evaluate the predictive factors of recurrence in cervical cancer treated with radical radiochemotherapy. METHODS: A retrospective analysis of 56 women was performed. Response was assessed using the RECIST response. Overall survival and disease-free survival curves were estimated by the Kaplan-Meier method and the Cox proportional hazards model was used to analyse predictors of recurrence. RESULTS: Local recurrence was documented in 16 patients and distant metastases in 15. The Kaplan-Meier survival probabilities were 95.1 ± 6.4% at 3 years and 80.4 ± 13.1% at 5 years and the Kaplan-Meier curve values for disease-free survival were 60.3 ± 14.3% at 3 years and 53.0 ± 15.7% at 5 years. Thirty-five patients were alive and 21 patients died, 19 from metastatic disease and 2 from other causes. Complete response after chemoradiation therapy, squamous cell carcinoma and tumour size ≤ 4 cm were significantly associated with outcome. In the Cox regression model, tumour size > 4 cm (hazard ratio 7.48; 95% CI 2.71-20.6; p < 0.001) and partial response (hazard ratio 7.09; 95% CI 2.82-17.8; p < 0.001) were predictive factors for disease-free survival and partial response (hazard ratio 3.7; 95% CI 1.3-10.1; p < 0.001) and non-squamous cell carcinoma (hazard ratio 3.5; 95% CI 1.2-9.7; p < 0.001) were predictive factors for overall survival. CONCLUSIONS: Non-squamous histology and partial response were independent prognostic factors for overall survival and tumour size and partial response were independent prognostic variables for 5-year disease survival.