The tumor microenvironment (TME) has been increasingly recognized as an ecosystem where tumor cells evolve and interact with the host tissue and defense system. In Pathology, this translates into the need to assess intratumoral heterogeneity of histology features and biomarker expression, as well as spatial properties of immune response and collagen framework within the TME. Advances related to targeted and immunotherapy for cancer increase the demand for precision analytics and quantification of these TME parameters, where pathologists' visual assessment is often limited. Research and developments in digital pathology have enabled discoveries of image-based computational biomarkers that, in turn, are being leveraged to serve as diagnostic and predictive tools in precision medicine.
Although many computational methods have been proposed, they are often fragmented and dependent on limited internal data sets for discovery and validation. Generalizability for widespread adoption of these computational imaging techniques, as well as their interlaboratory variation, present challenges for translation into clinical practice. With this endeavor, we aim to promote research and the development of trustworthy computational tools for the assessment of the TME.
To address this innovative topic, we will focus on computational applications to assess TME features that could be potentially implemented in routine clinical practice. We welcome submissions of Original Research papers and Reviews focusing on, but not limited to:
- Computational models to assess the TME such as spatial features
- Deep learning-generated features of the TME with evidence to explain and validate their pathobiology significance
- Virtual staining and imaging techniques to facilitate computational pathology TME feature extraction
- Computational pathology models integrated with radiology and multi-omics data
- Implementation of AI-based methods regarding the TME validated for clinical practice
Please note: 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 any of the sections of Frontiers in Oncology.
The tumor microenvironment (TME) has been increasingly recognized as an ecosystem where tumor cells evolve and interact with the host tissue and defense system. In Pathology, this translates into the need to assess intratumoral heterogeneity of histology features and biomarker expression, as well as spatial properties of immune response and collagen framework within the TME. Advances related to targeted and immunotherapy for cancer increase the demand for precision analytics and quantification of these TME parameters, where pathologists' visual assessment is often limited. Research and developments in digital pathology have enabled discoveries of image-based computational biomarkers that, in turn, are being leveraged to serve as diagnostic and predictive tools in precision medicine.
Although many computational methods have been proposed, they are often fragmented and dependent on limited internal data sets for discovery and validation. Generalizability for widespread adoption of these computational imaging techniques, as well as their interlaboratory variation, present challenges for translation into clinical practice. With this endeavor, we aim to promote research and the development of trustworthy computational tools for the assessment of the TME.
To address this innovative topic, we will focus on computational applications to assess TME features that could be potentially implemented in routine clinical practice. We welcome submissions of Original Research papers and Reviews focusing on, but not limited to:
- Computational models to assess the TME such as spatial features
- Deep learning-generated features of the TME with evidence to explain and validate their pathobiology significance
- Virtual staining and imaging techniques to facilitate computational pathology TME feature extraction
- Computational pathology models integrated with radiology and multi-omics data
- Implementation of AI-based methods regarding the TME validated for clinical practice
Please note: 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 any of the sections of Frontiers in Oncology.
