About this Research Topic
In current radiotherapy (RT) practices, each patient within a specific tumor type and stage is prescribed a common dose, even though tumors of different patients are known to respond differently to the same dose. Moreover, subvolumes of a given tumor often respond differently to the same radiation dose, revealing remarkably heterogeneous underlying tumor biology. The current RT paradigm largely ignores the wide per-patient and per-tumor-sub-volume dose-response variations and misses the opportunity to dynamically modify the dose distribution based on tumor response, such as providing a localized high boost dose to poorly-responding tumor sub-volumes that would not be possible to be delivered to the entire tumor due to limited critical structure tolerance. With more and more advanced image acquisition techniques and powerful image analysis tools becoming available, it is time for us to explore ways to bring meaningful personalized RT into clinical practice.
Radiation therapy (RT) efficacy is crippled by the lack of patient-specific tumor response and an effective method is needed to differentiate well-responding from poorly-responding tumors well before the RT course is complete to allow for response-prediction based adaptation. Among all the treatment response monitoring methods, imaging plays a very important role. In addition to conventional CT, MRI, and PET, more and more new imaging technologies have been introduced into the RT field, such as: MR guided RT, MR simulator, CT guided RT and PET/MR. In combination with the capabilities to acquire a large amount of image data, artificial intelligence (AI) and radiomics have also been heavily studied to understand these data and bring the results to guide clinical RT treatments in a more personalized manner. AI is supporting the modern radiotherapy technologies also in the perspective to make the online adaptive treatments more reliable and faster, which potentially represents the most promising strategy to address the impact of inter-fraction variability in dose distribution.
The goal of this Research Topic is to provide a source for colleagues who are interested in pushing personalized RT into routine practice using currently available image acquisition and analysis tools. New experiences related to personalized radiation therapy guided with imaging technologies will be collected, in the perspective of investigating the impact that these technologies and the AI are bringing onto new oncological treatment solutions.
This Research Topic welcomes manuscripts that cover all aspects of RT-oriented image technologies. This involves:
-functional imaging
-treatment response monitoring with on-board imaging
-treatment response estimation with radiomics and other AI tools
-AI-based adaptive radiotherapy experiences
-Reviews of the literature upon invitation
Please note: manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by validation (independent 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.
Radiation therapy (RT) efficacy is crippled by the lack of patient-specific tumor response and an effective method is needed to differentiate well-responding from poorly-responding tumors well before the RT course is complete to allow for response-prediction based adaptation. Among all the treatment response monitoring methods, imaging plays a very important role. In addition to conventional CT, MRI, and PET, more and more new imaging technologies have been introduced into the RT field, such as: MR guided RT, MR simulator, CT guided RT and PET/MR. In combination with the capabilities to acquire a large amount of image data, artificial intelligence (AI) and radiomics have also been heavily studied to understand these data and bring the results to guide clinical RT treatments in a more personalized manner. AI is supporting the modern radiotherapy technologies also in the perspective to make the online adaptive treatments more reliable and faster, which potentially represents the most promising strategy to address the impact of inter-fraction variability in dose distribution.
The goal of this Research Topic is to provide a source for colleagues who are interested in pushing personalized RT into routine practice using currently available image acquisition and analysis tools. New experiences related to personalized radiation therapy guided with imaging technologies will be collected, in the perspective of investigating the impact that these technologies and the AI are bringing onto new oncological treatment solutions.
This Research Topic welcomes manuscripts that cover all aspects of RT-oriented image technologies. This involves:
-functional imaging
-treatment response monitoring with on-board imaging
-treatment response estimation with radiomics and other AI tools
-AI-based adaptive radiotherapy experiences
-Reviews of the literature upon invitation
Please note: manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by validation (independent 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.
Keywords: Radiation therapy, medical imaging, personalized treatment, artificial intelligence, radiomics, adaptive, predictive modelling, dose painting
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
