Machine learning (ML) is a part of artificial intelligence and it has the potential to fundamentally augment the routine practice of radiation therapy. ML algorithms excel in learning complex relationships and incorporating existing knowledge into an inference model. The model is able to recognize complex patterns in medical data using either human-engineered features or deep neural network-based representations and provide a quantitative assessment of clinical diagnosis, modelling, treatment and prognosis for radiation therapy. Particularly, given the nature of heavy data involvement and the large amount of existing data, radiation oncology is one of the best fields for ML algorithms and they are having transformative ML-based applications in clinical practice. Indeed, ML has the potential to improve the overall quality of radiation therapy in terms of the accuracy, precision, and efficiency. The improvements benefit the whole workflow: from patient modeling, image segmentation, and treatment planning to patient setup, beam delivery, and prognosis analysis.
In this special issue collection, we aim to focus on the ML applications in radiation oncology daily practice. Specifically, topics involved in the whole workflow of radiation oncology including initial treatment decision-making, treatment planning and preparation, quality assurance, delivery of radiation therapy and follow-up care will be covered. We target studies that apply ML algorithms in each step of the workflow and discuss the implications of ML on the whole process, with a high-level overview of the ML-based radiation therapy. We plan to include studies that review the most recent advances of this rapidly evolving field and discuss the challenges associated with developing clinically relevant ML algorithms and implementing these algorithms in radiation therapy routine practice. The impact of the applications of ML algorithms on the roles of radiotherapy medical professionals will also be included.
Toward above goals, we welcome coordinated efforts in either original research and review articles from academy, industry, and hospitals. Since this field is at its infancy, we are open to innovative ideas and clinical relevant applications in the area of machine learning in radiation oncology. The topics include but are not limited to:
- Initial treatment decision-making (such as patient evaluation, dose prescription)
- Treatment planning and preparation (such as image segmentation, dosimetric treatment planning, image registration)
- Treatment setup and delivery (such as image guidance, motion management, and adaptive treatment)
- Response assessment and follow-up care
- Toxicity prediction and management
- Challenges to clinical implementation
- Regulation and clinical evaluation
Important 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.
Machine learning (ML) is a part of artificial intelligence and it has the potential to fundamentally augment the routine practice of radiation therapy. ML algorithms excel in learning complex relationships and incorporating existing knowledge into an inference model. The model is able to recognize complex patterns in medical data using either human-engineered features or deep neural network-based representations and provide a quantitative assessment of clinical diagnosis, modelling, treatment and prognosis for radiation therapy. Particularly, given the nature of heavy data involvement and the large amount of existing data, radiation oncology is one of the best fields for ML algorithms and they are having transformative ML-based applications in clinical practice. Indeed, ML has the potential to improve the overall quality of radiation therapy in terms of the accuracy, precision, and efficiency. The improvements benefit the whole workflow: from patient modeling, image segmentation, and treatment planning to patient setup, beam delivery, and prognosis analysis.
In this special issue collection, we aim to focus on the ML applications in radiation oncology daily practice. Specifically, topics involved in the whole workflow of radiation oncology including initial treatment decision-making, treatment planning and preparation, quality assurance, delivery of radiation therapy and follow-up care will be covered. We target studies that apply ML algorithms in each step of the workflow and discuss the implications of ML on the whole process, with a high-level overview of the ML-based radiation therapy. We plan to include studies that review the most recent advances of this rapidly evolving field and discuss the challenges associated with developing clinically relevant ML algorithms and implementing these algorithms in radiation therapy routine practice. The impact of the applications of ML algorithms on the roles of radiotherapy medical professionals will also be included.
Toward above goals, we welcome coordinated efforts in either original research and review articles from academy, industry, and hospitals. Since this field is at its infancy, we are open to innovative ideas and clinical relevant applications in the area of machine learning in radiation oncology. The topics include but are not limited to:
- Initial treatment decision-making (such as patient evaluation, dose prescription)
- Treatment planning and preparation (such as image segmentation, dosimetric treatment planning, image registration)
- Treatment setup and delivery (such as image guidance, motion management, and adaptive treatment)
- Response assessment and follow-up care
- Toxicity prediction and management
- Challenges to clinical implementation
- Regulation and clinical evaluation
Important 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.
