Radiation therapy aims to cure malignant tumors while preserving surrounding health tissues. Standard courses of radiation therapy last up to six weeks, during which time anatomical changes are often anticipated due to tumor shrinkage and the day-to-day variations of organ filling and patient positioning. Historically clinicians have compensated for these variations with planning target volumes that have generous margins; however, the tradeoff is increased dose to healthy tissues. One alternative is adaptive therapy where the patient receives customized treatment based on the "anatomy-of-the-day." This approach reduces inter-fraction treatment quality variations and better spares healthy tissues. Adaptive therapy has been an active research area for some time and finally has been implemented in some radiotherapy clinics, due in large part to machine learning-driven image registration, segmentation, planning, and treatment delivery.
Adaptive radiotherapy treatments that have long been dreamed of by clinicians are now gradually becoming a clinical reality due to advancements in machine learning and the recent technological breakthroughs powered by AI. Adaptive therapy is in a crucial phase, transitioning from the bench top to the bedside. With the first generation of commercial adaptive treatment machines and solutions already in some radiation oncology centers, there is emerging expertise on the clinical implementation of adaptive planning workflows. This invaluable clinical knowledge from incorporating adaptive therapy into routine clinical practice will undoubtedly encourage related research activities to enhance accuracy and efficiency, which further promotes the clinical implementation of adaptive therapy. In parallel, researchers are making strides in developing advanced adaptive treatment technologies based on information from various imaging modalities. The goal of this Research Topic is to provide a platform for radiation therapy clinicians and researchers to share practical aspects of clinical applications of AI-driven modern adaptive therapy workflows and also to promote cutting-edge technological advancements in this domain.
We welcome manuscripts that include but are not limited to AI-driven image segmentation, treatment planning, online/offline plan adaptation, and prescription adaptations. Both Original Research of novel adaptive therapy solutions and practical knowledge from clinical implementation are welcome. Authors are also encouraged to submit topical reviews that focus on a specific aspect of adaptive radiation therapy, or on the adaptive treatment workflow of a specific disease site.
Please note: manuscripts consisting solely of bioinformatics, computational analysis, or predictions of public databases which are not accompanied by validation (independent cohort or biological validation in vitro or in vivo) will not be accepted in any of the sections of Frontiers in Oncology.
Radiation therapy aims to cure malignant tumors while preserving surrounding health tissues. Standard courses of radiation therapy last up to six weeks, during which time anatomical changes are often anticipated due to tumor shrinkage and the day-to-day variations of organ filling and patient positioning. Historically clinicians have compensated for these variations with planning target volumes that have generous margins; however, the tradeoff is increased dose to healthy tissues. One alternative is adaptive therapy where the patient receives customized treatment based on the "anatomy-of-the-day." This approach reduces inter-fraction treatment quality variations and better spares healthy tissues. Adaptive therapy has been an active research area for some time and finally has been implemented in some radiotherapy clinics, due in large part to machine learning-driven image registration, segmentation, planning, and treatment delivery.
Adaptive radiotherapy treatments that have long been dreamed of by clinicians are now gradually becoming a clinical reality due to advancements in machine learning and the recent technological breakthroughs powered by AI. Adaptive therapy is in a crucial phase, transitioning from the bench top to the bedside. With the first generation of commercial adaptive treatment machines and solutions already in some radiation oncology centers, there is emerging expertise on the clinical implementation of adaptive planning workflows. This invaluable clinical knowledge from incorporating adaptive therapy into routine clinical practice will undoubtedly encourage related research activities to enhance accuracy and efficiency, which further promotes the clinical implementation of adaptive therapy. In parallel, researchers are making strides in developing advanced adaptive treatment technologies based on information from various imaging modalities. The goal of this Research Topic is to provide a platform for radiation therapy clinicians and researchers to share practical aspects of clinical applications of AI-driven modern adaptive therapy workflows and also to promote cutting-edge technological advancements in this domain.
We welcome manuscripts that include but are not limited to AI-driven image segmentation, treatment planning, online/offline plan adaptation, and prescription adaptations. Both Original Research of novel adaptive therapy solutions and practical knowledge from clinical implementation are welcome. Authors are also encouraged to submit topical reviews that focus on a specific aspect of adaptive radiation therapy, or on the adaptive treatment workflow of a specific disease site.
Please note: manuscripts consisting solely of bioinformatics, computational analysis, or predictions of public databases which are not accompanied by validation (independent cohort or biological validation in vitro or in vivo) will not be accepted in any of the sections of Frontiers in Oncology.
