ABSTRACT
Purpose: The study's purpose was to compare the performance of artificial intelligence (AI) in auto-contouring compared with a human practitioner in terms of precision, differences in dose distribution, and time consumption. Methods and Materials: Datasets of previously irradiated patients in 3 different segments (head and neck, breast, and prostate cancer) were retrospectively collected. An experienced radiation oncologist (MD) performed organs-at-risk (OARs) and standard clinical target volume delineations as baseline structures for comparison. AI-based autocontours were generated in 2 additional CT copies; therefore, 3 groups were assessed: MD alone, AI alone, and AI plus MD corrections (AI+C). Differences in Dice similarity coefficient (DSC) and person-hour burden were assessed. Furthermore, changes in clinically relevant dose-volume parameters were evaluated and compared. Results: Seventy-five previously treated cases were collected (25 per segment) for the analysis. Compared with MD contours, the mean DSC scores were higher than 0.7 for 74% and 80% of AI and AI+C, respectively. After corrections, 17.1% structures presented DSC score deviations higher than 0.1 and 10.4% dose-volume parameters significantly changed in AI-contoured structures. The time consumption assessment yielded mean person-hour reductions of 68%, 51%, and 71% for breast, prostate, and head and neck cancer, respectively. Conclusions: In great extent, AI yielded clinically acceptable OARs and certain clinical target volumes in the explored anatomic segments. Sparse correction and assessment requirements place AI+C as a standard workflow. Minimal clinically relevant differences in OAR exposure were identified. A substantial amount of person-hours could be repurposed with this technology.
ABSTRACT
BACKGROUND: Over the years, radiotherapy has been established as a tool to improve local control for high-grade sarcomas. Although the European Society for Medical Oncology guidelines has taken notice of a shift toward a neoadjuvant radiotherapy approach, the American Society for Radiation Oncology guidelines clearly favor a neoadjuvant approach, citing debilitating long-term adverse effects when radiotherapy is applied postoperatively. In this study, we examined these irradiation-associated adverse events for adjuvant radiotherapy and focused on the prognostic factors for disease outcome, including local control. METHODS: In this retrospective study, data for 106 patients with extremity soft-tissue sarcomas diagnosed between 1997 and 2021, of which 40 received adjuvant radiotherapy, were collected from the clinical and radiological information systems of a high-volume sarcoma treatment center. These data were then analyzed for radiation-associated side effects as well as predictive factors for overall survival, disease-free survival, local control, and surgical complications. RESULTS: Radiotherapy was beneficial to patients improving local control, especially for high-grade sarcomas, even when those were resected with negative margins. Side effects due to radiotherapy occurred in 87.5% of the patients, and these effects primarily included radiation dermatitis in 67.5%; however, only 40.0% had any adverse event of ≥ grade 2 according to Common Terminology Criteria for Adverse Events. Long-term function-limiting side effects occurred in 45.0% of the patients; 10% exhibited ≥ grade 2 function-limiting adverse events. Greater time between surgery and adjuvant radiotherapy was beneficial for the patients, whereas joint infiltrating sarcomas were associated with more severe long term, function-limiting adverse events. 28.3% of the patients experienced a recurrence at any location (median time 18.35 months) and in 16% the recurrence was local (median time 16.11 months), resulting in 1, 3, and 5 year disease-free survival rates of 74.1, 58.9, and 38.5% and local control rates of 78.7, 61.6, and 42.8% were observed, respectively. CONCLUSION: Recurrences may be avoided with high-dose radiation, especially for high-grade G2 and G3 sarcomas, even after complete R0 resection. This resulted in a low rate of severe long-term function-limiting adverse events. Thus, adjuvant radiotherapy should be seriously considered when planning patient treatment, especially when treating patients that present with high-grade sarcomas.
