In recent years, we have seen the development and introduction of integrated Magnetic Resonance Imaging (MRI) linear accelerators within the radiotherapy community. With MRI-guided radiotherapy (MRIgRT) high soft tissue contrast images can be acquired at several time points during the treatment. This enables daily online adaptation to anatomical changes between treatment fractions and monitoring of anatomical changes. By using delineations of the anatomy on images acquired just prior to the treatment, MRIgRT allows for reduction of geometrical uncertainties due to interfraction motion. As a result, treatment margins can be reduced, allowing a reduction of radiation induced toxicity.
However, MRIgRT adaptive radiotherapy comes at a cost. Online delineation, treatment planning, quality assurance are all time-consuming and operator dependent steps, making treatment slots considerably longer and hampering staff and departmental efficiency.
Automation, and specifically the use of machine learning and artificial intelligence, has shown great potential to streamline these tasks. However, the impact of these tools in daily practice is still very much undeveloped and they represent a great potential for improvements in the management of common cancers.
In this Research Topic we focus on abdominal and pelvic cancers. Our goal is to gather knowledge on the current state of the art of applications of AI for MRI guided online adaptive radiotherapy.
We welcome manuscripts that focus on AI applications to the tasks that happen ‘in the treatment room, during adaptation’. In particular, how AI can further enhance the online adaptive radiotherapy guided by MRI in the treatment of abdominal and pelvic cancers. Examples of applications include (but are not limited to): synthetic CT generation, segmentation, quantitative image, dose prediction, treatment planning, quality assurance, gating and tracking, etc.
Please note: manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by validation (clinical cohort or biological validation in vitro or in vivo) are out of scope for this section and will not be accepted as part of this Research Topic.
In recent years, we have seen the development and introduction of integrated Magnetic Resonance Imaging (MRI) linear accelerators within the radiotherapy community. With MRI-guided radiotherapy (MRIgRT) high soft tissue contrast images can be acquired at several time points during the treatment. This enables daily online adaptation to anatomical changes between treatment fractions and monitoring of anatomical changes. By using delineations of the anatomy on images acquired just prior to the treatment, MRIgRT allows for reduction of geometrical uncertainties due to interfraction motion. As a result, treatment margins can be reduced, allowing a reduction of radiation induced toxicity.
However, MRIgRT adaptive radiotherapy comes at a cost. Online delineation, treatment planning, quality assurance are all time-consuming and operator dependent steps, making treatment slots considerably longer and hampering staff and departmental efficiency.
Automation, and specifically the use of machine learning and artificial intelligence, has shown great potential to streamline these tasks. However, the impact of these tools in daily practice is still very much undeveloped and they represent a great potential for improvements in the management of common cancers.
In this Research Topic we focus on abdominal and pelvic cancers. Our goal is to gather knowledge on the current state of the art of applications of AI for MRI guided online adaptive radiotherapy.
We welcome manuscripts that focus on AI applications to the tasks that happen ‘in the treatment room, during adaptation’. In particular, how AI can further enhance the online adaptive radiotherapy guided by MRI in the treatment of abdominal and pelvic cancers. Examples of applications include (but are not limited to): synthetic CT generation, segmentation, quantitative image, dose prediction, treatment planning, quality assurance, gating and tracking, etc.
Please note: manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by validation (clinical cohort or biological validation in vitro or in vivo) are out of scope for this section and will not be accepted as part of this Research Topic.
