RESUMO
PURPOSE: We present a large real-world multicentric dataset of ovarian, uterine and cervical oligometastatic lesions treated with SBRT exploring efficacy and clinical outcomes. In addition, an exploratory machine learning analysis was performed. METHODS: A pooled analysis of gynecological oligometastases in terms of efficacy and clinical outcomes as well an exploratory machine learning model to predict the CR to SBRT were carried out. The CR rate following radiotherapy (RT) was the study main endpoint. The secondary endpoints included the 2-year actuarial LC, DMFS, PFS, and OS. RESULTS: 501 patients from 21 radiation oncology institutions with 846 gynecological metastases were analyzed, mainly ovarian (53.1%) and uterine metastases(32.1%).Multiple fraction radiotherapy was used in 762 metastases(90.1%).The most frequent schedule was 24 Gy in 3 fractions(13.4%). CR was observed in 538(63.7%) lesions. The Machine learning analysis showed a poor ability to find covariates strong enough to predict CR in the whole series. Analyzing them separately, in uterine cancer, if RT dose≥78.3Gy, the CR probability was 75.4%; if volume was <13.7 cc, the CR probability became 85.1%. In ovarian cancer, if the lesion was a lymph node, the CR probability was 71.4%; if volume was <17 cc, the CR probability rose to 78.4%. No covariate predicted the CR for cervical lesions. The overall 2-year actuarial LC was 79.2%, however it was 91.5% for CR and 52.5% for not CR lesions(p < 0.001). The overall 2-year DMFS, PFS and OS rate were 27.3%, 24.8% and 71.0%, with significant differences between CR and not CR. CONCLUSIONS: CR was substantially associated to patient outcomes in our series of gynecological cancer oligometastatic lesions. The ability to predict a CR through artificial intelligence could also drive treatment choices in the context of personalized oncology.
Assuntos
Inteligência Artificial , Radiocirurgia , Humanos , Feminino , Pessoa de Meia-Idade , Radiocirurgia/métodos , Idoso , Adulto , Idoso de 80 Anos ou mais , Neoplasias Uterinas/patologia , Neoplasias Uterinas/radioterapia , Neoplasias Uterinas/cirurgia , Aprendizado de Máquina , Neoplasias do Colo do Útero/patologia , Neoplasias do Colo do Útero/radioterapia , Neoplasias Ovarianas/patologia , Neoplasias Ovarianas/radioterapia , Neoplasias dos Genitais Femininos/patologia , Neoplasias dos Genitais Femininos/radioterapia , Adulto Jovem , Resultado do Tratamento , Estudos RetrospectivosRESUMO
BACKGROUND AND PURPOSE: We aimed to develop and validate different machine-learning (ML) prediction models for the complete response of oligometastatic gynecological cancer after SBRT. MATERIAL AND METHODS: One hundred fifty-seven patients with 272 lesions from 14 different institutions and treated with SBRT with radical intent were included. Thirteen datasets including 222 lesions were combined for model training and internal validation purposes, with an 80:20 ratio. The external testing dataset was selected as the fourteenth Institution with 50 lesions. Lesions that achieved complete response (CR) were defined as responders. Prognostic clinical and dosimetric variables were selected using the LASSO algorithm. Six supervised ML models, including logistic regression (LR), classification and regression tree analysis (CART) and support vector machine (SVM) using four different kernels, were trained and tested to predict the complete response of uterine lesions after SBRT. The performance of models was assessed by receiver operating characteristic curves (ROC), area under the curve (AUC) and calibration curves. An explainable approach based on SHapley Additive exPlanations (SHAP) method was deployed to generate individual explanations of the model's decisions. RESULTS: 63.6% of lesions had a complete response and were used as ground truth for the supervised models. LASSO strongly associated complete response with three variables, namely the lesion volume (PTV), the type of lesions (lymph-nodal versus parenchymal), and the biological effective dose (BED10), that were used as input for ML modeling. In the training set, the AUCs for complete response were 0.751 (95% CI: 0.716-0.786), 0.766 (95% CI: 0.729-0.802) and 0.800 (95% CI: 0.742-0.857) for the LR, CART and SVM with a radial basis function kernel, respectively. These models achieve AUC values of 0.727 (95% CI: 0.669-0.795), 0.734 (95% CI: 0.649-0.815) and 0.771 (95% CI: 0.717-0.824) in the external testing set, demonstrating excellent generalizability. CONCLUSION: ML models enable a reliable prediction of the treatment response of oligometastatic lesions receiving SBRT. This approach may assist radiation oncologists to tailor more individualized treatment plans for oligometastatic patients.
Assuntos
Neoplasias , Radiocirurgia , Humanos , Aprendizado de Máquina , Algoritmos , Área Sob a Curva , Resposta Patológica CompletaRESUMO
OBJECTIVE: This retrospective, multicenter study analyzes the efficacy and safety of stereotactic body radiotherapy in a large cohort of patients with oligometastatic/persistent/recurrent cervical cancer. METHODS: A standardized data collection from several radiotherapy centers that treated patients by stereotactic body radiotherapy between March 2006 and February 2021 was set up. Clinical and stereotactic body radiotherapy parameters were collected. Objective response rate was defined as a composite of complete and partial response, while clinical benefit included objective response rate plus stable disease. Radiation Therapy Oncology Group/European Organization for Research and Treatment of Cancer and Common Terminology Criteria for Adverse Events scales were used to grade toxicities. The primary endpoints were the rate of complete response to stereotactic body radiotherapy, and the 2 year actuarial local control rate on a 'per lesion' basis. The secondary end points were progression-free survival and overall survival, as well as toxicity. RESULTS: A total of 83 patients with oligometastatic/persistent/recurrent cervical cancer bearing 125 lesions treated by stereotactic body radiotherapy at 15 different centers were selected for analysis. Of the sites of metastatic disease, lymph node metastases were most common (55.2%), followed by parenchyma lesions (44.8%). Median total dose was 35 Gy (range 10-60), in five fractions (range 1-10), with a median dose/fraction of 7 Gy (range 4-26). Complete, partial, and stable response were found in 73 (58.4%), 29 (23.2%), and 16 (12.8%) lesions, respectively, reaching 94.4% of the clinical benefit rate. Forty-six (55.4%) patients had a complete response. Patients achieving complete response on a 'per lesion' basis experienced a 2 year actuarial local control rate of 89.0% versus 22.1% in lesions not achieving complete response (p<0.001). The 2 year actuarial progression-free survival rate was 42.5% in patients with complete response versus 7.8% in patients with partial response or stable or progressive disease (p=0.001). The 2 year actuarial overall survival rate was 68.9% in patients with complete response versus 44.3% in patients with partial response or stable or progressive disease (p=0.015). Fifteen patients (18.1%) had mild acute toxicity, totaling 29 side events. Late toxicity was documented in four patients (4.8%) totaling seven adverse events. CONCLUSION: Our analysis confirmed the efficacy of stereotactic body radiotherapy in oligometastatic/persistent/recurrent cervical cancer patients. The low toxicity profile encourages the wider use of stereotactic body radiotherapy in this setting.
Assuntos
Mangifera , Radiocirurgia , Neoplasias do Colo do Útero , Feminino , Humanos , Recidiva Local de Neoplasia/cirurgia , Radiocirurgia/efeitos adversos , Estudos Retrospectivos , Resultado do Tratamento , Neoplasias do Colo do Útero/etiologia , Neoplasias do Colo do Útero/radioterapiaRESUMO
UNLABELLED: Temozolomide (TMZ) is the first line drug in the care of high grade gliomas. The combined treatment of TMZ plus radiotherapy is more effective in the care of brain gliomas then radiotherapy alone. Aim of this report is a survival comparison, on a long time (>10 years) span, of glioma patients treated with radiotherapy alone and with radiotherapy + TMZ. MATERIALS AND METHODS: In this report we retrospectively reviewed the outcome of 128 consecutive pts with diagnosis of high grade gliomas referred to our institutions from April 1994 to November 2001. The first 64 pts were treated with RT alone and the other 64 with a combination of RT and adjuvant or concomitant TMZ. RESULTS: Grade 3 (G3) haematological toxicity was recorded in 6 (9%) of 64 pts treated with RT and TMZ. No G4 haematological toxicity was observed. Age, histology, and administration of TMZ were statistically significant prognostic factors associated with 2 years overall survival (OS). PFS was for GBM 9 months, for AA 11. CONCLUSIONS: The combination of RT and TMZ improves long term survival in glioma patients. Our results confirm the superiority of the combination on a long time basis.
Assuntos
Neoplasias Encefálicas/tratamento farmacológico , Neoplasias Encefálicas/radioterapia , Glioma/tratamento farmacológico , Glioma/radioterapia , Adulto , Idoso , Neoplasias Encefálicas/patologia , Terapia Combinada , Dacarbazina/administração & dosagem , Dacarbazina/análogos & derivados , Feminino , Glioma/patologia , Humanos , Masculino , Pessoa de Meia-Idade , Estudos Retrospectivos , TemozolomidaRESUMO
AIMS AND BACKGROUND: Temozolomide, a novel alkylating agent, has shown promising results in the treatment of patients with high-grade gliomas, when used as single agent as well as in combination with radiation therapy. MATERIALS AND METHODS: In this report we retrospectively reviewed the clinical outcome of 128 consecutive patients with a diagnosis of high-grade gliomas referred to our Institutions from April 1994 to November 2001. The first 64 patients were treated with radiotherapy alone and the other 64 with a combination of radiotherapy and temozolomide (31 with radiotherapy and adjuvant temozolomide and 33 with radiotherapy and concomitant temozolomide followed by adjuvant temozolomide). RESULTS: Grade 3 hematological toxicity was scored in 9% of 64 patients treated with radiotherapy and temozolomide. No grade 4 hematological toxicity was reported, and the other acute side effects observed were mild or easily controlled with medications. Age, histology and administration of temozolomide were statistically significant prognostic factors associated with better 2-year overall survival. In contrast, we did not observe a significant difference in overall survival between adjuvant and concomitant/adjuvant temozolomide administration. CONCLUSIONS: We report the favorable results of a schedule combining radiotherapy and temozolomide in the treatment of patients with high-grade gliomas. The literature data and above all the findings of the phase III EORTC-NCIC 26981 trial suggest that actually the schedule can be used routinely in clinical practice. Further clinical studies, using temozolomide in combination with other agents, are required.