Deep learning based model observer by U-Net

Iris Lorente; Craig K. Abbey; Jovan G. Brankov

doi:10.1117/12.2549687

16 March 2020 Deep learning based model observer by U-Net

Iris Lorente, Craig K. Abbey, Jovan G. Brankov

Proceedings Volume 11316, Medical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment; 113160F (2020) https://doi.org/10.1117/12.2549687
Event: SPIE Medical Imaging, 2020, Houston, Texas, United States

Abstract

Model Observers (MO) are algorithms designed to evaluate and optimize the parameters of new medical imaging reconstruction methodologies by providing a measure of human accuracy for a diagnostic task. In contrast with a computer-aided diagnosis system, MOs are not designed to outperform human diagnosis but only to find a defect if a radiologist would be able to detect it. These algorithms can economize and expedite the finding of optimal reconstruction parameters by reducing the number of sessions with expert radiologists, which are costly and prolonged. Convolutional Neural Networks (CNN or ConvNet) have been successfully used in the computer vision field for image classification, segmentation and video analytics. In this paper, we propose and test several U-Net configurations as MO for a defect localization task on synthetic images with different levels of correlated noisy backgrounds. Preliminary results show that the CNN based MO has potential and its accuracy correlates well with that of the human.

Conference Presentation

Citation Download Citation

Iris Lorente, Craig K. Abbey, and Jovan G. Brankov "Deep learning based model observer by U-Net", Proc. SPIE 11316, Medical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment, 113160F (16 March 2020); https://doi.org/10.1117/12.2549687

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available