deep learning based pulmonary intelligent assistant diagnosis system
Principal Investigator
Name
xiaohua liu
Degrees
Ph.D
Institution
LinkDoc Technology (Beijing) Co.,Ltd.
Position Title
Research Scientist
Email
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-513
Initial CDAS Request Approval
Jun 13, 2019
Title
deep learning based pulmonary intelligent assistant diagnosis system
Summary
Lung cancer is the most common cause of cancer-related death in men. Low-dose lung computed tomography(LDCT) screening provides an effective way for early diagnosis and can sharply reduce the lung cancer mortality rate. As LDCT becomes a standard for lung cancer screening in practice, millions of chest CT images need to be examined by professionals on a daily basis. The volume and necessity of the task highlight the need for computer-aided diagnosis (CAD) systems to assist radiologists comprehensively. Recently, driven by the blooming success of deep learning in computer vision, much effort has been made on lung nodule detection, malignancy diagnosis, characteristics assessment and more, and we also have developed a comprehensive lung cancer assessment system to assist radiologists. However, the system is not perfect and it needs for gradual improvement in practice. In this proposal, we aim to validate and improve our system's function in lung nodule detection, localization, segmentation, characterization and nodule progression tracking over multiple scans. With the extensive collection of CT images and clinical datasets from NLST, we believe the recent advancements in artificial intelligence, especially deep learning techniques, will significantly contribute to both the lung cancer research and clinical practices. And such a system will assist radiologist with clinical decision making, in a comprehensive and truly intelligent way.
Aims
Aim #1: To validate and improve our system's function in lung nodule detection, localization, segmentation and characterization simultaneously.
Aim #2: To automatically track and quantify nodule progression from multiple CT scans.
Aim #3: To extend the capability of the proposed model to detect non-nodule related abnormalities, based on available expert diagnosis as ground truth.
Collaborators
Guangming Gao, M.E, Researcher, Linkdoc, Inc.
Ding Ma, M.E, Algorithm Engineer, Linkdoc, Inc.
Weihao Xie, M.E, Algorithm Engineer, Linkdoc, Inc.