About this Research Topic
Various Computer-Aided Diagnosis (CAD) systems for brain tumors, utilizing Deep Learning and radiomics methods, have been extensively employed for the early diagnosis of conditions such as Glioblastomas, lymphoma, brain metastases, and related radiomics tasks. However, the real-world clinical application of these CAD and radiomics systems still faces significant challenges in terms of generalization and effectiveness. Two primary challenges need to be addressed: Firstly, the scarcity of high-quality labeled paired images from multiple clinical centers, encompassing complete pathology and gene information. Secondly, the inadequacy of pathologies and genes, such as ki-67, IDH1, and TERTI, in routine clinical practice.
This Research Topic is dedicated to exploring the potential of artificial intelligence approaches in elucidating the relationship between medical images and pathology/gene data in the analysis of brain tumors. The objective is to expand the scope of research from single-center to multi-center, multi-imaging model settings and from single-laboratory medical imaging studies to practical clinical applications. Furthermore, it encourages the development of new imaging technologies such as innovative MRI sequences, PET, SPECT, and optical molecular imaging. To achieve these objectives, we invite researchers to contribute original and unique submissions on Multi-center radiomics and Multi-task Learning theory, algorithms, and applications for brain tumor imaging, pathology, and genetic analysis.
This Research Topic welcomes submissions focused on, but not limited to, the following topics:
● Creation of novel datasets for brain tumor imaging, pathology, and genetic analysis.
● Innovative imaging technologies aimed at discovering new applications in brain tumor radiomics. Encourage the development of new imaging technologies such as innovative MRI sequences, PET, SPECT, and optical molecular imaging.
● Novel approaches for training and testing using multi-canter images or multi-imaging modelling environments, expanding from single laboratory medical imaging studies to practical clinical applications.
● Explore the potential of artificial intelligence approaches in elucidating the relationship between medical images and pathology/gene data in the analysis of brain tumors, such as clinical diagnosis, therapeutic development and the prediction of post-operative mortality.
This Research Topic is dedicated to exploring the potential of artificial intelligence approaches in elucidating the relationship between medical images and pathology/gene data in the analysis of brain tumors. The objective is to expand the scope of research from single-center to multi-center, multi-imaging model settings and from single-laboratory medical imaging studies to practical clinical applications. Furthermore, it encourages the development of new imaging technologies such as innovative MRI sequences, PET, SPECT, and optical molecular imaging. To achieve these objectives, we invite researchers to contribute original and unique submissions on Multi-center radiomics and Multi-task Learning theory, algorithms, and applications for brain tumor imaging, pathology, and genetic analysis.
This Research Topic welcomes submissions focused on, but not limited to, the following topics:
● Creation of novel datasets for brain tumor imaging, pathology, and genetic analysis.
● Innovative imaging technologies aimed at discovering new applications in brain tumor radiomics. Encourage the development of new imaging technologies such as innovative MRI sequences, PET, SPECT, and optical molecular imaging.
● Novel approaches for training and testing using multi-canter images or multi-imaging modelling environments, expanding from single laboratory medical imaging studies to practical clinical applications.
● Explore the potential of artificial intelligence approaches in elucidating the relationship between medical images and pathology/gene data in the analysis of brain tumors, such as clinical diagnosis, therapeutic development and the prediction of post-operative mortality.
Keywords: Pathology, Artificial Intelligence, Brain Tumor
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.
