Digital pathology
BostonGene's AI-based digital pathology platform identifies distinct characteristics of the tumor and microenvironment, significantly reducing the need for manual analysis and minimizing variability across various types of pathology data.
H&E (hematoxylin and eosin)
BostonGene’s AI-based pathology platform detects and characterizes tissue composition, including tumor, stroma, fibrosis, fat, necrosis and other features. It enables high-throughput analysis, characterizing 100 slides in just 20 minutes.
The clusterization approach significantly improves the efficiency and accuracy of tissue slide analysis, including classification and segmentation, aiding in faster diagnosis and disease subtyping.
The clusterization approach significantly improves the efficiency and accuracy of tissue slide analysis, including classification and segmentation, aiding in faster diagnosis and disease subtyping.
IHC (immunohistochemistry)
BostonGene’s AI-based algorithm accurately detects the expression of target biomarkers in both tumor and immune cells. The automated workflow can be applied to various markers, including:
- Nuclear markers (AR, PR, FOXP3, etc.)
- Cytoplasm/membrane markers (HER2, TROP2, HLA-DR, CD4/8, etc.)
- Complex membrane staining (0, 1+, 2+, and 3+ cells for HER2)
- Targets for novel antibody-drug conjugates (ADC)
MxIF (Multiplex Immunofluorescence)
BostonGene's advanced ML/AI-based pipeline for whole-slide images (WSI) provides single-cell resolution insights into tissue biology and spatial dynamics
Explore BostonGene’s publications that
demonstrate the utility of digital pathology
demonstrate the utility of digital pathology
Cancer Cell • March 11, 2024
Multi-omic Profiling of Follicular Lymphoma Tumors Reveals Changes in Tissue Architecture and Enhanced Stromal Remodeling in High-Risk Patients
Article
Blood • December 28, 2023
Spatial Mapping of Human Hematopoiesis at Single Cell Resolution Reveals Aging-Associated Topographic Remodeling
Article
Cell Reports • August 1, 2022
Multiregional single-cell proteogenomic analysis of ccRCC reveals cytokine drivers of intratumor spatial heterogeneity
Article