Expanding the reach: Integrating AI-generated auto contours via deep learning segmentation into diverse treatment planning systems

Aim: Contouring in treatment planning systems for radiation oncology plays a crucial role in ensuring accurate and effective treatment. The integration of AI-generated auto-contouring with other planning systems, particularly in remote areas, is essential for achieving optimal contouring. This study explores the incorporation of deep learning-based auto-contouring into various treatment planning systems to enhance precision and accessibility. Methods: The study utilized the Ray Station planning system 12A (Ray Search Laboratories, Sweden), renowned for its GPU-powered algorithm capable of generating AI-generated contours through deep learning segmentation. The research encompassed a group of hospitals distributed across various locations in India. Results: The OAR contours generated through deep learning segmentation in Ray Station were seamlessly transferred to both Monaco and Eclipse TPS via cloud connectivity. The average time required for any auto contour was less than two minutes and the maximum time it took to implement auto contour and exporting and start planning through other planning systems at any remote site is less than one hour. Conclusion: By Integrating, we could able to come down the contour time three days to one hour even for remotest areas where there is no contour expert available. This method not only translates to significant time savings to start planning and treatment but also ensure uniformity of contours across all our units. This consistency fosters enhanced quality in treatment planning, facilitates research endeavour, and ultimately contributes to improved patient care especially in developing countries where the budget for dedicated treatment planning systems are not adequate.