About this Research Topic
Quantitative multimodality imaging is an emerging field which enables simultaneous quantification of physiological parameters from multiple images of a target area, such as tumor or organ of interest. The newly obtained information could enhance the ability to perform a number of tasks, including image segmentation, image fusion, classification, and risk stratification. Recent advancement in machine and deep learning methods have gained interest in medical imaging and can play an important role in quantitative multimodality imaging. Although some progress in this area has been made, the field is still in its infancy and there is a need for reliable quantitative multimodality imaging using state-of-the-art artificial intelligence tools such as machine and deep learning to provide reliable information from images for oncological applications.
The goals of articles presented in this Research topic are, firstly, to identify and present oncological applications which could be impacted from using quantitative multimodality imaging techniques as well as state-of-the-art artificial intelligence tools; secondly, to develop novel methodologies as well as translational research results which demonstrate the synergy between quantitative multimodality imaging and machine and deep learning tools to provide synergistic information as compared to conventional tools.
1. Identify prognostic and predictive imaging biomarkers using combined multimodality imaging and machine and deep learning methods
2. Develop clinical decision support tools using combined multimodal imaging and machine and deep learning methods
3. Develop multimodality medical image fusion techniques using deep learning methods
4. Develop novel medical image classification, segmentation, object detection and tracking tasks methods using deep learning architecture.
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 Frontiers in Oncology.
The goals of articles presented in this Research topic are, firstly, to identify and present oncological applications which could be impacted from using quantitative multimodality imaging techniques as well as state-of-the-art artificial intelligence tools; secondly, to develop novel methodologies as well as translational research results which demonstrate the synergy between quantitative multimodality imaging and machine and deep learning tools to provide synergistic information as compared to conventional tools.
1. Identify prognostic and predictive imaging biomarkers using combined multimodality imaging and machine and deep learning methods
2. Develop clinical decision support tools using combined multimodal imaging and machine and deep learning methods
3. Develop multimodality medical image fusion techniques using deep learning methods
4. Develop novel medical image classification, segmentation, object detection and tracking tasks methods using deep learning architecture.
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 Frontiers in Oncology.
Keywords: Artificial Intelligence, Quantitative Imaging, Oncology, Deep Learning, Multimodal Imaging
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.
