Mapping cell types in the tumor microenvironment from tissue images via deep learning trained by spatial transcriptomics of lung adenocarcinoma
Na, K. J.; Koh, J.; Choi, H.; Kim, Y. T.
Show abstract
Profiling heterogeneous cell types in the tumor microenvironment (TME) is important for cancer immunotherapy. Here, we propose a method and validate in independent samples for mapping cell types in the TME from only hematoxylin and eosin (H&E)-stained tumor tissue images using spatial transcriptomic data of lung adenocarcinoma. We obtained spatial transcriptomic data of lung adenocarcinoma from 22 samples. The cell types of each spot were estimated using cell type inference based on a domain adaptation algorithm with single-cell RNA-sequencing data. They were used to train a convolutional neural network with a corresponding H&E image patch as an input. Consequently, the five predicted cell types estimated from the H&E images were significantly correlated with those derived from the RNA-sequencing data. We validated our model using immunohistochemical staining results with marker proteins from independent lung adenocarcinoma samples. Our resource of spatial transcriptomics of lung adenocarcinoma and proposed method with independent validation can provide an annotation-free and precise profiling method of tumor microenvironment using H&E images.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Efficient prediction of a spatial transcriptomics profile better characterizes breast cancer tissue sections without costly experimentation 95%
- Meta-analysis reveals consistent immune response patterns in COVID-19 infected patients at single-cell resolution 93%
- Proteogenomic Characterization of Triple-Negative Apocrine Carcinoma Reveals Molecular Features of Progression and Chemotherapy Response 93%
Similar papers in this journal
- Generalizing AI-driven Assessment of Immunohistochemistry across Immunostains and Cancer Types: A Universal Immunohistochemistry Analyzer 95%
- A Deep Learning Model for Molecular Label Transfer that Enables Cancer Cell Identification from Histopathology Images 94%
- Multimodal single-cell profiling reveals cancer crosstalk between macrophages and stromal cells in poor prognostic cholangiocarcinoma patients. 94%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- Uncovering disease-related multicellular pathway modules on large-scale single-cell transcriptomes with scPAFA 94%
- Comprehensive multimodal and multiomic profiling reveals epigenetic and transcriptional reprogramming in lung tumors 94%
- Multi-sample Full-length Transcriptome Analysis of 22 Breast Cancer Clinical Specimens with Long-Read Sequencing 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.