About this Research Topic
Precision medicine has been introduced into routine clinical care with an increasing number of treatments being tailored to patient-specific characteristics. Medical imaging and radiomics can further contribute to precision oncology applications, for example by implementing image-based phenotyping.
Radiomics is a high-throughput quantitative analysis of radiologic images, which noninvasively describes oncologic tissues and tumor phenotypes. The target of radiomics - the imaging phenotype - provides important information including genotype, pathology, the tumor environment, and treatment outcome. It relies on semantic and radiomic features and further combines radiologic features to classify and predict automated analysis methods, like machine learning and deep learning. The application of radiomics in image-based phenotyping holds great promise for improving the discrimination of different imaging phenotypes in cancer, forecasting the response to of possible treatments, and optimizing clinical decisions.
To successfully introduce these methods into clinical care, we should determine how underlying biology-driven patterns are related to the image-based tumor phenotypes. This Research Topic aims to collect new discoveries in the field of radiomics and machine learning in medical imaging of cancer. The Original Research and Review articles should focus on the following subtopics:
1) Precision diagnosis. Original Research articles that use radiomics to preoperatively diagnose the stage, pathologic type, and gene mutation in cancers.
2) Therapeutic effect evaluation. Original Research articles that use radiomics to predict or evaluate the therapeutic effect of specific treatment in cancers.
3) Prognostic prediction. Original Research articles that use radiomics to predict the survival of cancer patients.
4) Novel radiomic methods. Original Research articles that develop novel radiomic methods such as deep learning, multi-habitat, and multi-modality fusion.
5) Review or meta-analysis articles about methods and applications of radiomics.
Radiomics is a high-throughput quantitative analysis of radiologic images, which noninvasively describes oncologic tissues and tumor phenotypes. The target of radiomics - the imaging phenotype - provides important information including genotype, pathology, the tumor environment, and treatment outcome. It relies on semantic and radiomic features and further combines radiologic features to classify and predict automated analysis methods, like machine learning and deep learning. The application of radiomics in image-based phenotyping holds great promise for improving the discrimination of different imaging phenotypes in cancer, forecasting the response to of possible treatments, and optimizing clinical decisions.
To successfully introduce these methods into clinical care, we should determine how underlying biology-driven patterns are related to the image-based tumor phenotypes. This Research Topic aims to collect new discoveries in the field of radiomics and machine learning in medical imaging of cancer. The Original Research and Review articles should focus on the following subtopics:
1) Precision diagnosis. Original Research articles that use radiomics to preoperatively diagnose the stage, pathologic type, and gene mutation in cancers.
2) Therapeutic effect evaluation. Original Research articles that use radiomics to predict or evaluate the therapeutic effect of specific treatment in cancers.
3) Prognostic prediction. Original Research articles that use radiomics to predict the survival of cancer patients.
4) Novel radiomic methods. Original Research articles that develop novel radiomic methods such as deep learning, multi-habitat, and multi-modality fusion.
5) Review or meta-analysis articles about methods and applications of radiomics.
Keywords: Cancer, Phenotyping, Radiomics, Precision Medicine, Machine Learning
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.
