Integrating spatial gene expression and breast tumour morphology via deep learning

By Bryan He, L. Bergenstråhle, L. Stenbeck, Abubakar Abid, Alma Andersson, Å. Borg, J. Maaskola, J. Lundeberg, James Y. Zou. Nature Biomedical Engineering, 2020

496 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biophysics, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/49ca6e8fda7abf2b0bcc48506433d9bfab1a8c68

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biophysics

In Molecular Biology

Citations in the corpus

Best practices for single-cell analysis across modalities (2023, background): “Tangram 224 , GridNet 230 and eggplant 231 generate common coordinate frameworks across samples to mitigate this issue 232 .”
Multimodal biomedical AI (2022, background): “…have utilized deep learning to leverage histopathology images to predict spatial gene expression from these images alone, pointing to morphological features in these images not captured by human experts that could potentially enhance the utility and lower the costs of this technology 25,26 .”
Robust mapping of spatiotemporal trajectories and cell–cell interactions in healthy and diseased tissues (2023, unknown): “…is based on the quantitative link between cellular morphology (e.g. cell size, nuclei size, granularity, density, or distribution) and molecular gene expression pro ﬁ les 16,19,55,55 – 57 , with the innovative aspect being that imaging data is used to correct and/or impute the sequencing data.”
Deep learning in cancer diagnosis, prognosis and treatment selection (2021, methodology): “demonstrated by ST-Net, a neural network capable of predicting expressions of clinically relevant genes in breast cancer using tissue spots from H&E slides [73].”
Artificial intelligence for digital and computational pathology (2023, background): “5) and translational considerations for clinical deployment (Box 3).”
Spatial components of molecular tissue biology (2022, unknown): “These can help improve performances on different tasks such as cancer cell classification 152,153 and mapping molecular counts at higher resolution 154 .”
From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment. (2023, background): “49 Saltz et al. develop a deep learning-based computational stain that identiﬁes tumor-inﬁltrating lymphocytes whose spatial patterns are correlated with survival.”