Automated Lung Cancer Assessment with Explainable AI and Uncertainty Estimation
Principal Investigator
Name
Laura Brattain
Degrees
Ph.D.
Institution
University of Central Florida
Position Title
Associate Professor
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCOI-1619
Initial CDAS Request Approval
Jul 15, 2024
Title
Automated Lung Cancer Assessment with Explainable AI and Uncertainty Estimation
Summary
Lung cancer remains a leading cause of cancer-related mortality globally. Accurate early detection, characterization, and prognosis are crucial for improving patient outcomes. While deep learning (DL) techniques have shown promise in automating these tasks, there is a growing need for models that not only provide accurate predictions but also offer explainability and uncertainty estimation. Explainable AI (XAI) can help clinicians understand and trust model predictions, while uncertainty estimation can highlight cases that require further review. This proposal aims to develop an automated lung cancer assessment system incorporating explainable AI and uncertainty estimation.
Aims
The specific objectives are:
Automated detection of lung nodules in CT scans with uncertainty estimation.
Characterization and classification of lung nodules with explainability.
Prognostic modeling for patient survival prediction with integrated uncertainty estimation and explainability.
Collaborators
UCF Center for Research in Computer Vision