Deep Learning for Discovering and Visualising Biomarkers
Principal Investigator
Name
Gustavo Carneiro
Degrees
B.Sc.,M.Sc.,,Ph.D.
Institution
University of Adelaide
Position Title
Professor
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-723
Initial CDAS Request Approval
Nov 4, 2020
Title
Deep Learning for Discovering and Visualising Biomarkers
Summary
This bioengineering project will develop novel methods for discovering and visualising optimal biomarkers from chest computed tomography images based on extensions of recently developed deep learning techniques. The extensions proposed in this project will advance the state of the art in medical image analysis given that it will allow an efficient analysis of large dimensionality inputs in their original high resolution. In addition, our project will be the first approach capable of discovering previously unknown biomarkers associated with important clinical outcomes. We will validate the approach on a real-world case study dataset concerning the prediction of patient survival from lung cancer screening images.
Aims
1- Design and implement a system that can predict patient survival from lung cancer screening images.
2- Design and implement a system that uses patient survival label to automatically find visual biomarkers from lung cancer screening images.
3- Design and implement a system that uses lung cancer screening images and predicted visual biomarkers to provide a precise estimation of patient survival.
Collaborators
Renato Hermoza Aragones (University of Adelaide, Adelaide, Australia)
Gabriel Maicas (University of Adelaide, Adelaide, Australia)
Michael Mogford (University of Adelaide, Adelaide, Australia)
Chong Wang (University of Adelaide, Adelaide, Australia)
Yuanhong Chen (University of Adelaide, Adelaide, Australia)
Yu Tian (University of Adelaide, Adelaide, Australia)
Jacinto Nascimento (Assistant Professor at the Instituto Superior Tecnico, Lisbon, Portugal)
Related Publications
-
Weakly-supervised preclinical tumor localization associated with survival prediction from lung cancer screening Chest X-ray images.
Hermoza R, Nascimento JC, Carneiro G
Comput Med Imaging Graph. 2024 May 7; Volume 115: Pages 102395 PUBMED