lung nodule classification with interpretable deep learning models
Principal Investigator
Name
Wang Yizhou
Degrees
Ph.D
Institution
Peking University
Position Title
Professor
Email
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-749
Initial CDAS Request Approval
Jan 8, 2021
Title
lung nodule classification with interpretable deep learning models
Summary
Our project is focused on building an interpretable deep learning based computer-aided diagnostic (CAD) system to evaluating the malignancy of lung nodules. Specificly, we plans to explore how to embed clinical prior knowledges like context information, structure symmetry, follow-ups, relationship betwween malignancy and symptom into deep learning models. we are also interested in modeling the uncertainty of the decision made by deep learning models.
Aims
(1) Build a deep learning based computer-aided diagnostic (CAD) system for lung nodule classification.
(2) Based on (1), try to design methods to embed clinical prior knowledges into deep learning models to improve their interpretability.
(3) Based on (2), develop methods to model the the uncertainty of the decision made by deep learning algorithms.
(4) Evaluate our CAD system on pathologicall proven low-dose CT.
Collaborators
Mingzhou Liu, Peking University