Cancer characterization is still the main obstacle to cancer treatment. Generally, patients with the same clinical stage have significant differences in survival and prognosis due to different biological behaviors of tumor, making it challenging to individualized treatment according to the unified treatment model for tumor stages. Recent data suggest that advanced post-treatment anatomical imaging with post-processing and registration can be used to characterize the likelihood and location of potential failures to optimize treatment strategies and improve quality of life. Therefore, "radiomics" has been extensively studied for non-invasive acquisition of quantitative texture information from anatomical structures as the gold standard for pre-treatment staging and post-treatment tumor control assessment. In addition, emerging radiomics technologies further leverage existing image data, using "big data" analytics to provide hitherto unimaginable predictive capabilities. Mass data processing methods have been refined with powerful big data/machine learning techniques to identify clinically applicable non-invasive methods to extract oncology outcomes and toxicity prevention data from large scale data. This approach offers exceptional scalability, clinical applicability, cost-effectiveness, ease of implementation, and an unmatched value proposition.
These studies remain complex for clinicians to accept thoroughly. Therefore, we hope that clinicians with experience in radiomics research will contribute relevant research results to address the issues of treatment selection in clinical practice. The primary goal of this Research Topic is to develop a comprehensive predictive model that can provide standard recommendations for the multidisciplinary management of multiple cancer etiologies. The long-term goal is to reduce mortality and improve quality of life for cancer patients, thereby increasing cost efficiency.
We welcome submissions of Original Research and Review articles focusing on, but not limited to, the following aspects:
• Determination of the predictive utility of serial CT/MRI/PET-based 3-D quantitative image assessment for disease control.
• Identification of the imaging-based radiomics parameters associated with survival and prognosis.
• Categorization of the biological behaviors in cancer with radiomics.
• Validation of the accuracy of personalized therapy based on clinical radiomics models.
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.
Cancer characterization is still the main obstacle to cancer treatment. Generally, patients with the same clinical stage have significant differences in survival and prognosis due to different biological behaviors of tumor, making it challenging to individualized treatment according to the unified treatment model for tumor stages. Recent data suggest that advanced post-treatment anatomical imaging with post-processing and registration can be used to characterize the likelihood and location of potential failures to optimize treatment strategies and improve quality of life. Therefore, "radiomics" has been extensively studied for non-invasive acquisition of quantitative texture information from anatomical structures as the gold standard for pre-treatment staging and post-treatment tumor control assessment. In addition, emerging radiomics technologies further leverage existing image data, using "big data" analytics to provide hitherto unimaginable predictive capabilities. Mass data processing methods have been refined with powerful big data/machine learning techniques to identify clinically applicable non-invasive methods to extract oncology outcomes and toxicity prevention data from large scale data. This approach offers exceptional scalability, clinical applicability, cost-effectiveness, ease of implementation, and an unmatched value proposition.
These studies remain complex for clinicians to accept thoroughly. Therefore, we hope that clinicians with experience in radiomics research will contribute relevant research results to address the issues of treatment selection in clinical practice. The primary goal of this Research Topic is to develop a comprehensive predictive model that can provide standard recommendations for the multidisciplinary management of multiple cancer etiologies. The long-term goal is to reduce mortality and improve quality of life for cancer patients, thereby increasing cost efficiency.
We welcome submissions of Original Research and Review articles focusing on, but not limited to, the following aspects:
• Determination of the predictive utility of serial CT/MRI/PET-based 3-D quantitative image assessment for disease control.
• Identification of the imaging-based radiomics parameters associated with survival and prognosis.
• Categorization of the biological behaviors in cancer with radiomics.
• Validation of the accuracy of personalized therapy based on clinical radiomics models.
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.