About this Research Topic
Digital pathology is the process of digitizing histological images and analyzing them using deep learning techniques, often in conjunction with genomics and clinical data. Traditional pathology is manual, subjective, and slow, while AI-guided digital pathology has the potential to accelerate routine clinical workflows, enhance diagnostic accuracy, and deliver personalized medicine at lower costs for cancer patients.
Digital pathology is able to build or utilize computational pathology methods to identify the presence or absence of targetable genomic signatures. It can also quantify the amount of cancer cells expressing the target, map the spatial distribution of not only the target expressing cancer cells but also geo-characterize the tumor microenvironment, to better predict response to therapy.
This Research Topic is interested in research that can leverage artificial intelligence algorithms trained on next-generation sequencing data in conjunction with histological imaging to generate insights on translational, clinical research or clinical trial design, routine clinical use, with an aim of improving outcomes for patients with cancer. Histological data can include but is not limited to data from immunohistochemistry (IHC), H&E (Hematoxylin and eosin), Fluorescence in-situ hybridization (FISH), immunofluorescence etc. Next-generation sequencing data can include but not limited to data from whole-genome sequencing (WGS), whole-exome sequencing (WES), targeted-exome panel sequencing, RNA-
Bioinformatic studies are welcome, however, these should not be based solely on analysis of publicly available datasets such as TCGA. It is essential to have an independent validation cohort for statistically significant confirmation of the findings communicated.
Digital pathology is able to build or utilize computational pathology methods to identify the presence or absence of targetable genomic signatures. It can also quantify the amount of cancer cells expressing the target, map the spatial distribution of not only the target expressing cancer cells but also geo-characterize the tumor microenvironment, to better predict response to therapy.
This Research Topic is interested in research that can leverage artificial intelligence algorithms trained on next-generation sequencing data in conjunction with histological imaging to generate insights on translational, clinical research or clinical trial design, routine clinical use, with an aim of improving outcomes for patients with cancer. Histological data can include but is not limited to data from immunohistochemistry (IHC), H&E (Hematoxylin and eosin), Fluorescence in-situ hybridization (FISH), immunofluorescence etc. Next-generation sequencing data can include but not limited to data from whole-genome sequencing (WGS), whole-exome sequencing (WES), targeted-exome panel sequencing, RNA-
Bioinformatic studies are welcome, however, these should not be based solely on analysis of publicly available datasets such as TCGA. It is essential to have an independent validation cohort for statistically significant confirmation of the findings communicated.
Keywords: Digital Pathology, Genomics, Deep 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.
