Over the last decade, artificial intelligence (AI) has become a popular research theme in medicine, aiming at improving health care service quality and efficiency for individuals and populations. Simultaneously, the roles of the medical specialties, radiology and radiation oncology, have also become more important, but their existing workforces appear unable to match the increased demand. Hence, various AI-based solutions developed by multi-disciplinary teams of computer scientists and engineers, radiologists, radiographers, radiation oncologists, radiation therapists, medical physicists, and dosimetrists have emerged to address this issue with reported performances similar to, or even better than, gold standards. Examples of these solutions include automatic image segmentation, computer aided diagnosis, automated structured reporting, radiation dose optimization, clinical decision support, and image quality enhancement. However, these promising results were mainly based on retrospective studies and/or those with relatively small sample sizes. Also, ethical issues in AI in radiology and radiation oncology, e.g., automation bias, commission errors, responsibility for medical errors, etc. have been raised by influential bodies.
This Research Topic encourages researchers, academics, and clinicians to publish their high-quality research articles on the development and/or use of AI in different aspects of radiology and radiation oncology workflows that have public health benefits. Examples include examination/treatment scheduling, radiation dose optimization, image quality enhancement, image segmentation, computer aided diagnosis, structured reporting, and clinical decision support with robust methodology. Also, research articles on investigation or review of ethical issues in AI in radiology and radiation oncology are welcome. In this way, the existing evidence base of AI in radiology and radiation oncology can be broadened and strengthened for better management of health for individuals and populations. Hence, this would address concerns of policy makers, influential bodies, research, academic, and clinical communities, and the public.
This Research Topic welcomes the submission of Original Research and Systematic Review articles about AI in radiology/radiation oncology addressing at least one of the following themes:
• Automated Structured Reporting
• Automatic Image Segmentation
• Clinical Decision Support
• Computer Aided Diagnosis
• Disease Prediction and Prognosis
• Ethics of Algorithms and Trained Models
• Ethics of Data
• Ethics of Practice
• Image Feature Extraction
• Image Quality Enhancement
• Image Reconstruction
• Image Registration
• Image Synthesis
• Image Translation
• Imaging Biobanks
• Optimization of Examination / Treatment Scheduling
• Public Health Benefits
• Radiation Dose Optimization
• Radiomics
Papers outside of the themes and/or article types listed above are considered on a case-by-case basis. Please submit a manuscript summary for the Topic Editor team to determine article suitability prior to full manuscript submission.
Keywords:
Radiation Oncology, Artificial Intelligence, Artificial Neural Network, Convolutional Neural Network, Deep Learning, Ethics, Generative Adversarial Network, Generative Artificial Intelligence, Machine Learning, Medical Imaging, Medical Radiation Science, Natural Language Processing, Nuclear Medicine, Radiation Therapy, Radiography, Radiology
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.
Over the last decade, artificial intelligence (AI) has become a popular research theme in medicine, aiming at improving health care service quality and efficiency for individuals and populations. Simultaneously, the roles of the medical specialties, radiology and radiation oncology, have also become more important, but their existing workforces appear unable to match the increased demand. Hence, various AI-based solutions developed by multi-disciplinary teams of computer scientists and engineers, radiologists, radiographers, radiation oncologists, radiation therapists, medical physicists, and dosimetrists have emerged to address this issue with reported performances similar to, or even better than, gold standards. Examples of these solutions include automatic image segmentation, computer aided diagnosis, automated structured reporting, radiation dose optimization, clinical decision support, and image quality enhancement. However, these promising results were mainly based on retrospective studies and/or those with relatively small sample sizes. Also, ethical issues in AI in radiology and radiation oncology, e.g., automation bias, commission errors, responsibility for medical errors, etc. have been raised by influential bodies.
This Research Topic encourages researchers, academics, and clinicians to publish their high-quality research articles on the development and/or use of AI in different aspects of radiology and radiation oncology workflows that have public health benefits. Examples include examination/treatment scheduling, radiation dose optimization, image quality enhancement, image segmentation, computer aided diagnosis, structured reporting, and clinical decision support with robust methodology. Also, research articles on investigation or review of ethical issues in AI in radiology and radiation oncology are welcome. In this way, the existing evidence base of AI in radiology and radiation oncology can be broadened and strengthened for better management of health for individuals and populations. Hence, this would address concerns of policy makers, influential bodies, research, academic, and clinical communities, and the public.
This Research Topic welcomes the submission of Original Research and Systematic Review articles about AI in radiology/radiation oncology addressing at least one of the following themes:
• Automated Structured Reporting
• Automatic Image Segmentation
• Clinical Decision Support
• Computer Aided Diagnosis
• Disease Prediction and Prognosis
• Ethics of Algorithms and Trained Models
• Ethics of Data
• Ethics of Practice
• Image Feature Extraction
• Image Quality Enhancement
• Image Reconstruction
• Image Registration
• Image Synthesis
• Image Translation
• Imaging Biobanks
• Optimization of Examination / Treatment Scheduling
• Public Health Benefits
• Radiation Dose Optimization
• Radiomics
Papers outside of the themes and/or article types listed above are considered on a case-by-case basis. Please submit a manuscript summary for the Topic Editor team to determine article suitability prior to full manuscript submission.
Keywords:
Radiation Oncology, Artificial Intelligence, Artificial Neural Network, Convolutional Neural Network, Deep Learning, Ethics, Generative Adversarial Network, Generative Artificial Intelligence, Machine Learning, Medical Imaging, Medical Radiation Science, Natural Language Processing, Nuclear Medicine, Radiation Therapy, Radiography, Radiology
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.