Validation of AI Transformer model using Pan-cancer histology
Principal Investigator
Name
QianXue Wu
Degrees
M.D.
Institution
Chongqing Medical University
Position Title
Phd student
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCOI-1638
Initial CDAS Request Approval
Aug 15, 2024
Title
Validation of AI Transformer model using Pan-cancer histology
Summary
We have built a AI framework based on spatial transcriptomics and the digital image from the same sample. We will get output of spatial transcriptomics (cancer gene expression) of PLCO digital slide from our AI framework. In addition, whole slide images (WSIs), tumor characteristics, staging, prognosis, and lifestyle factors of breast cancer are collected. Accordingly, we will apply meta-annotation methods (annotation-free) and self-learning algorithms, to extract specific pathologic characteristics. Finally, we will test the predicted cancer gene expression in a multivariable Cox regression model.
Aims
1. Predict transcriptomic landscape of PLCO dataset by cancer type.
3. Enhance early detection and prognostic assessment, ultimately improving patient outcomes.
Collaborators
NA