Predicting lung cancer prognosis with deep learning
Principal Investigator
Name
Francesco Ciompi
Institution
Radboud University Medical Center
Position Title
Postdoc
Email
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-325
Initial CDAS Request Approval
Jun 30, 2017
Title
Predicting lung cancer prognosis with deep learning
Summary
In this project, we aim at designing a computer model based on deep learning able to automatically predict the prognosis of lung cancer patients. NLST histopathology images and NLST chest CT images will be used to train the computer model by combining information extracted from nodule growth and appearance, assessed in chest CT images, and from tissue architecture, analyzed in histopathology slides.
Aims
The automatic assessment of prognosis based on both nodule temporal evolution and tissue architecture in HE-stained histopathology slides.
Collaborators
Jeroen van der Laak, Computational Pathology Group, Radboud University Medical Center Nijmegen, Netherlands
Katrien Grunberg, Pathology Department, Radboud University Medical Center Nijmegen, Netherlands
Geert Litjens, Computational Pathology Group, Radboud University Medical Center Nijmegen, Netherlands
Bram van Ginneken, Diagnostic Image Analysis Group, Radboud University Medical Center Nijmegen, Netherlands
Colin Jacobs, Diagnostic Image Analysis Group, Radboud University Medical Center Nijmegen, Netherlands