Journal
NPJ PRECISION ONCOLOGY
Volume 5, Issue 1, Pages -Publisher
NATURE PORTFOLIO
DOI: 10.1038/s41698-021-00225-9
Keywords
-
Categories
Funding
- National Science Foundation [IIS-1703883, CNS-1747778, CCF-1733843, IIS-1763523, IIS-1849238-825536, ARO MURI-Z8424104-440149]
- Centre on Perceptual and Interactive Intelligence (CPII) Limited
- National Institute of Dental & Craniofacial Research (NIDCR) [U01 DE025188]
- National Institute of Biomedical Imaging and Bioengineering [R56 EB020527]
- National Cancer Institute [U01 CA217851]
Ask authors/readers for more resources
This study developed a deep-learning model to predict genetic mutations and biological pathway activities directly from whole-slide images. By using histopathology images, the model could predict point mutations and copy number alterations of genes, as well as activities of canonical pathways. The visualization of weight maps in tumor tiles helped understand the decision-making process of deep-learning models.
Breast carcinoma is the most common cancer among women worldwide that consists of a heterogeneous group of subtype diseases. The whole-slide images (WSIs) can capture the cell-level heterogeneity, and are routinely used for cancer diagnosis by pathologists. However, key driver genetic mutations related to targeted therapies are identified by genomic analysis like high-throughput molecular profiling. In this study, we develop a deep-learning model to predict the genetic mutations and biological pathway activities directly from WSIs. Our study offers unique insights into WSI visual interactions between mutation and its related pathway, enabling a head-to-head comparison to reinforce our major findings. Using the histopathology images from the Genomic Data Commons Database, our model can predict the point mutations of six important genes (AUC 0.68-0.85) and copy number alteration of another six genes (AUC 0.69-0.79). Additionally, the trained models can predict the activities of three out of ten canonical pathways (AUC 0.65-0.79). Next, we visualized the weight maps of tumor tiles in WSI to understand the decision-making process of deep-learning models via a self-attention mechanism. We further validated our models on liver and lung cancers that are related to metastatic breast cancer. Our results provide insights into the association between pathological image features, molecular outcomes, and targeted therapies for breast cancer patients.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available