Neoadjuvant image-guided helical intensity modulated radiotherapy of extremity sarcomas - a single center experience.

BACKGROUND: Advanced radiotherapy (RT) techniques allow normal tissue to be spared in patients with extremity soft tissue sarcoma (STS). This work aims to evaluate toxicity and outcome after neoadjuvant image-guided radiotherapy (IGRT) as helical intensity modulated radiotherapy (IMRT) with reduced margins based on MRI-based target definition in patients with STS. METHODS: Between 2010 to 2014, 41 patients with extremity STS were treated with IGRT delivered as helical IMRT on a tomotherapy machine. The tumor site was in the upper extremity in 6 patients (15%) and lower extremity in 35 patients (85%). Reduced margins of 2.5 cm in longitudinal direction and 1.0 cm in axial direction were used to expand the MRI-defined gross tumor volume, including peritumoral edema, to the clinical target volume. An additional margin of 5 mm was added to receive the planning target volume. The full total dose of 50 Gy in 2 Gy fractions was sucessfully applied in 40 patients. Two patients received chemotherapy instead of surgery due to systemic progression. All patients were included into a strict follow-up program and were seen interdisciplinarily by the Departments of Orthopaedic Surgery and Radiation Oncology. RESULTS: Thirty eight patients that received total RT total dose and subsequent resection were analyzed for outcome. After a median follow-up of 38.5 months cumulative OS, local PFS and systemic PFS at 2 years were determined at 78.2, 85.2 and 54.5%, respectively. Two of 6 local recurrences were proximal marginal misses. Negative resection margins were achieved in 84% of patients. The rate of major wound complications was comparable to previous IMRT studies with 36.8%. RT was overall tolerable with low toxicity rates. CONCLUSIONS: IMRT-IGRT offers neoadjuvant treatment for extremity STS with reduced safety margins and thus low toxicity rates. Wound complication rates were comparable to previously reported frequencies. Two reported marginal misses suggest a word of caution for reduction of longitudinal safety margins.

Treatment-related features improve machine learning prediction of prognosis in soft tissue sarcoma patients.

BACKGROUND AND PURPOSE: Current prognostic models for soft tissue sarcoma (STS) patients are solely based on staging information. Treatment-related data have not been included to date. Including such information, however, could help to improve these models. MATERIALS AND METHODS: A single-center retrospective cohort of 136 STS patients treated with radiotherapy (RT) was analyzed for patients' characteristics, staging information, and treatment-related data. Therapeutic imaging studies and pathology reports of neoadjuvantly treated patients were analyzed for signs of response. Random forest machine learning-based models were used to predict patients' death and disease progression at 2 years. Pre-treatment and treatment models were compared. RESULTS: The prognostic models achieved high performances. Using treatment features improved the overall performance for all three classification types: prediction of death, and of local and systemic progression (area under the receiver operatoring characteristic curve (AUC) of 0.87, 0.88, and 0.84, respectively). Overall, RT-related features, such as the planning target volume and total dose, had preeminent importance for prognostic performance. Therapy response features were selected for prediction of disease progression. CONCLUSIONS: A machine learning-based prognostic model combining known prognostic factors with treatment- and response-related information showed high accuracy for individualized risk assessment. This model could be used for adjustments of follow-up procedures.