⚡ Quick Summary
This study evaluates a new x-ray-based adaptive radiotherapy (ART) treatment planning system (TPS) version 2.0 for head and neck cancer (HNC), highlighting the effectiveness of knowledge-based planning (KBP) and artificial intelligence (AI) in enhancing dosimetric outcomes. The findings indicate that AI-guided planning goals significantly improve organ-at-risk (OAR) sparing compared to traditional methods.
🔍 Key Details
- 📊 Patient Sample: 20 definitive and post-operative HNC patients
- ⚙️ Technology: Varian Ethos2.0 TPS emulator
- 🧩 Planning Strategies: Population-based, KBP-guided, AI-guided
- 🏆 Key Metrics: Average contralateral parotid gland mean dose: 20.0 ± 6.1 Gy (population-based) vs. 15.0 ± 6.1 Gy (KBP with human intervention)
🔑 Key Takeaways
- 📊 All planning strategies produced acceptable plan quality.
- 💡 KBP and AI-guided goals provided enhanced dosimetric sparing for OAR.
- 🏆 KBP strategy showed higher modulation and faster optimization time.
- 🌍 Results are applicable to other treatment sites beyond HNC.
- 🤖 AI-guided planning demonstrated the most effective OAR sparing.
- 📈 Study supports the transition to x-ray-based online adaptive radiotherapy.
📚 Background
Head and neck cancer (HNC) treatment is notoriously complex, requiring precise planning to meet dosimetric constraints while ensuring patient safety. The introduction of advanced technologies such as AI and KBP aims to enhance the planning process, making it more efficient and effective. The Varian Ethos2.0 TPS emulator represents a significant step forward in this domain, promising to improve treatment outcomes for patients.
🗒️ Study
The study involved a retrospective analysis of 20 HNC patients treated at the authors’ institution. Utilizing the Varian Ethos2.0 TPS emulator, the researchers compared various planning strategies, including traditional population-based methods and newer AI and KBP-guided approaches. The goal was to assess the performance of these strategies in terms of dosimetric quality and plan deliverability.
📈 Results
The results indicated that all planning strategies yielded acceptable plan quality. Notably, the KBP and AI-guided approaches resulted in a significant reduction in the mean dose to the contralateral parotid gland, with the population-based strategy averaging 20.0 ± 6.1 Gy compared to 15.0 ± 6.1 Gy for KBP with human intervention. Furthermore, the KBP strategy demonstrated superior modulation and faster optimization times, underscoring its potential advantages in clinical practice.
🌍 Impact and Implications
The implications of this study are profound, as it highlights the potential of integrating AI and KBP into routine clinical practice for HNC treatment. By lowering the barriers to effective treatment planning, these technologies can enhance patient outcomes and streamline the planning process. The findings suggest that similar approaches could be beneficial across various treatment sites, paving the way for broader applications of adaptive radiotherapy.
🔮 Conclusion
This study underscores the transformative potential of AI and KBP in head and neck adaptive radiotherapy. By demonstrating that these advanced planning strategies can produce dosimetrically compliant plans with improved OAR sparing, the research advocates for their adoption in clinical settings. As we move forward, continued exploration of these technologies will be crucial in enhancing the quality of cancer care.
💬 Your comments
What are your thoughts on the integration of AI and KBP in radiotherapy planning? We invite you to share your insights and engage in a discussion! 💬 Leave your comments below or connect with us on social media:
Assessing population-based to personalized planning strategies for head and neck adaptive radiotherapy.
Abstract
PURPOSE: Optimal head-and-neck cancer (HNC) treatment planning requires accurate and feasible planning goals to meet dosimetric constraints and generate robust online adaptive treatment plans. A new x-ray-based adaptive radiotherapy (ART) treatment planning system (TPS) version 2.0 emulator includes novel methods to drive the planning process including the revised intelligent optimization engine algorithm (IOE2). HNC is among the most challenging and complex sites and heavily depends on planner skill and experience to successfully generate a reference plan. Therefore, we evaluate the new TPS performance via conventionally accepted planning strategies with/without artificial intelligence (AI) and knowledge-based planning (KBP).
METHODS: Our institution has a pre-clinical release of the Varian Ethos2.0 TPS emulator which includes several changes that may affect current planning strategies. Twenty definitive and post-operative HNC patients were retrospectively selected with a two or three-level simultaneous integrated boost (SIB) dosing scheme. Patients were replanned in the emulator using population-based, KBP-guided with/without human intervention and AI-guided planning goals. These planning strategies were compared both dosimetrically and for plan deliverability.
RESULTS: All strategies generally demonstrated acceptable plan quality with KBP- and AI-guided goals offering enhanced dosimetric sparing in organs-at-risk (OAR). The average contralateral parotid gland mean dose was 20.0 ± 6.1 Gy (p < 0.001) for population-based and 15.0 ± 6.1 Gy (p = n.s.) for KBP-with human intervention versus 15.1 ± 7.4 Gy for clinical plans. Target coverage, minimum dose, and plan hotspot were acceptable in all cases. KBP-enabled strategy demonstrated higher modulation and faster optimization time than both population-based and AI-guided strategies.
CONCLUSION: Simply entering population, automatic KBP-enabled or AI-generated planning goals into the new Ethos2.0 TPS produced dosimetrically compliant plans, with AI-guided goals demonstrating the most OAR sparing. Several of these approaches are easy to translate to other treatment sites and will help lower the barrier to entry for x-ray-based online-ART.
Author: [‘Visak J’, ‘Liao CY’, ‘Zhong X’, ‘Wang B’, ‘Domal S’, ‘Wang HJ’, ‘Maniscalco A’, ‘Pompos A’, ‘Nyguen D’, ‘Parsons D’, ‘Godley A’, ‘Lu W’, ‘Jiang S’, ‘Moon D’, ‘Sher D’, ‘Lin MH’]
Journal: J Appl Clin Med Phys
Citation: Visak J, et al. Assessing population-based to personalized planning strategies for head and neck adaptive radiotherapy. Assessing population-based to personalized planning strategies for head and neck adaptive radiotherapy. 2024; (unknown volume):e14576. doi: 10.1002/acm2.14576