Radiation oncology is uniquely positioned to harness the power of big data as vast amounts of data are generated at an unprecedented pace for individual patients in imaging studies and radiation treatments worldwide. The big data encountered in the radiotherapy clinic may include patient demographics stored in the electronic medical record (EMR) systems, plan settings and dose volumetric information of the tumors and normal tissues generated by treatment planning systems (TPS), anatomical and functional information from diagnostic and therapeutic imaging modalities (e.g., CT, PET, MRI and kVCBCT) stored in picture archiving and communication systems (PACS), as well as the genomics, proteomics and metabolomics information derived from blood and tissue specimens. Yet, the great potential of big data in radiation oncology has not been fully exploited for the benefits of cancer patients due to a variety of technical hurdles and hardware limitations.
With recent development in computer technology, there have been increasing and promising applications of machine learning algorithms involving the big data in radiation oncology. This research topic is intended to present novel technological breakthroughs and state-of-the-art developments in machine learning and data mining in radiation oncology in recent years. Eventually, greater exploitation of radiation oncology big data could lead to more personalized radiotherapy worldwide. Potential topics include, but are not limited to:
? Radiomics and quantitative imaging
? Knowledge-based treatment planning
? Treatment response prediction via machine learning
? Clinical decision support via machine learning
? Comparative effectiveness research in radiation oncology
? Bioinformatics for improved quality of care
? Motion compensation and correction via machine learning
? Automated image registration and contouring
? Radiogenomics
? TCP and NTCP modeling
? Cancer registries and classification
? Tracking big organ dose data for patient safety in radiation therapy
? Machine learning models for early cancer prediction and prevention
? Natural language processing of EMR data
Radiation oncology is uniquely positioned to harness the power of big data as vast amounts of data are generated at an unprecedented pace for individual patients in imaging studies and radiation treatments worldwide. The big data encountered in the radiotherapy clinic may include patient demographics stored in the electronic medical record (EMR) systems, plan settings and dose volumetric information of the tumors and normal tissues generated by treatment planning systems (TPS), anatomical and functional information from diagnostic and therapeutic imaging modalities (e.g., CT, PET, MRI and kVCBCT) stored in picture archiving and communication systems (PACS), as well as the genomics, proteomics and metabolomics information derived from blood and tissue specimens. Yet, the great potential of big data in radiation oncology has not been fully exploited for the benefits of cancer patients due to a variety of technical hurdles and hardware limitations.
With recent development in computer technology, there have been increasing and promising applications of machine learning algorithms involving the big data in radiation oncology. This research topic is intended to present novel technological breakthroughs and state-of-the-art developments in machine learning and data mining in radiation oncology in recent years. Eventually, greater exploitation of radiation oncology big data could lead to more personalized radiotherapy worldwide. Potential topics include, but are not limited to:
? Radiomics and quantitative imaging
? Knowledge-based treatment planning
? Treatment response prediction via machine learning
? Clinical decision support via machine learning
? Comparative effectiveness research in radiation oncology
? Bioinformatics for improved quality of care
? Motion compensation and correction via machine learning
? Automated image registration and contouring
? Radiogenomics
? TCP and NTCP modeling
? Cancer registries and classification
? Tracking big organ dose data for patient safety in radiation therapy
? Machine learning models for early cancer prediction and prevention
? Natural language processing of EMR data
