Background Local response prediction for brain metastases (BM) after stereotactic radiosurgery (SRS) is challenging, particularly for smaller BM, as existing criteria are based solely on unidimensional measurements. This investigation sought to determine whether radiomic features provide additional value to routinely available clinical and dosimetric variables to predict local recurrence following SRS. Methods Analyzed were 408 BM in 87 patients treated with SRS. A total of 440 radiomic features were extracted from the tumor core and the peritumoral regions, using the baseline pretreatment volumetric post-contrast T1 (T1c) and volumetric T2 fluid-attenuated inversion recovery (FLAIR) MRI sequences. Local tumor progression was determined based on Response Assessment in Neuro-Oncology‒BM criteria, with a maximum axial diameter growth of >20% on the follow-up T1c indicating local failure. The top radiomic features were determined based on resampled random forest (RF) feature importance. An RF classifier was trained using each set of features and evaluated using the area under the receiver operating characteristic curve (AUC). Results The addition of any one of the top 10 radiomic features to the set of clinical features resulted in a statistically significant (P < 0.001) increase in the AUC. An optimized combination of radiomic and clinical features resulted in a 19% higher resampled AUC (mean = 0.793; 95% CI = 0.792–0.795) than clinical features alone (0.669, 0.668–0.671). Conclusions The increase in AUC of the RF classifier, after incorporating radiomic features, suggests that quantitative characterization of tumor appearance on pretreatment T1c and FLAIR adds value to known clinical and dosimetric variables for predicting local failure.

IMPORTANCEThe optimal approach for treatment deescalation in human papillomavirus (HPV)-related oropharyngeal squamous cell carcinomas (OPSCCs) is unknown.OBJECTIVE To assess a primary radiotherapy (RT) approach vs a primary transoral surgical (TOS) approach in treatment deescalation for HPV-related OPSCC. DESIGN, SETTING, AND PARTICIPANTSThis international, multicenter, open-label parallel-group phase 2 randomized clinical trial was conducted at 9 tertiary academic cancer centers in Canada and Australia and enrolled patients with T1-T2N0-2 p16-positive OPSCC between February 13, 2018, and November 17, 2020. Patients had up to 3 years of follow-up.INTERVENTIONS Primary RT (consisting of 60 Gy of RT with concurrent weekly cisplatin in node-positive patients) vs TOS and neck dissection (ND) (with adjuvant reduced-dose RT depending on pathologic findings). MAIN OUTCOMES AND MEASURESThe primary end point was overall survival (OS) compared with a historical control. Secondary end points included progression-free survival (PFS), quality of life, and toxic effects. RESULTSOverall, 61 patients were randomized (30 [49.2%] in the RT arm and 31 [50.8%] in the TOS and ND arm; median [IQR] age, 61.9 [57.2-67.9] years; 8 women [13.6%] and 51 men [86.4%]; 31 [50.8%] never smoked). The trial began in February 2018, and accrual was halted in November 2020 because of excessive toxic effects in the TOS and ND arm. Median follow-up was 17 months (IQR, 15-20 months). For the OS end point, there were 3 death events, all in the TOS and ND arm, including the 2 treatment-related deaths (0.7 and 4.3 months after randomization, respectively) and 1 of myocardial infarction at 8.5 months. There were 4 events for the PFS end point, also all in the TOS and ND arm, which included the 3 mortality events and 1 local recurrence. Thus, the OS and PFS data remained immature. Grade 2 to 5 toxic effects occurred in 20 patients (67%) in the RT arm and 22 (71%) in the TOS and ND arm. Mean (SD) MD Anderson Dysphagia Inventory scores at 1 year were similar between arms (85.7 [15.6] and 84.7 [14.5], respectively). CONCLUSIONS AND RELEVANCEIn this randomized clinical trial, TOS was associated with an unacceptable risk of grade 5 toxic effects, but patients in both trial arms achieved good swallowing outcomes at 1 year. Long-term follow-up is required to assess OS and PFS outcomes.

A prophylactic GT approach results in exposing higher number of patients to GT complications. The higher rate of hospitalizations using a therapeutic approach suggests that patients are sicker when GTs are required. Given the similar weight loss and survival, a therapeutic approach at an earlier stage of need may be a preferable approach, when access to prompt GT placement is available.