Adaptive learning approach to improve generalization performance of a domain-aware CNN-based ideal model observer

Nebojsa Bogdanovic; Craig K. Abbey; Yongyi Yang; Jovan G. Brankov

doi:10.1117/12.3006257

29 March 2024 Adaptive learning approach to improve generalization performance of a domain-aware CNN-based ideal model observer

Nebojsa Bogdanovic, Craig K. Abbey, Yongyi Yang, Jovan G. Brankov

Author Affiliations +

Proceedings Volume 12929, Medical Imaging 2024: Image Perception, Observer Performance, and Technology Assessment; 129290C (2024) https://doi.org/10.1117/12.3006257
Event: SPIE Medical Imaging, 2024, San Diego, California, United States

Abstract

Convolutional neural networks (CNNs) have been previously used as model observers (MO) for the purpose of defect detection in medical images. Due to their limited generalizability, such CNN observers do not possess the ability to recognize whether an input image comes from the same distribution as the data it was trained on, i.e., the ability of having domain awareness. In this paper we propose an adaptive learning approach for training a domain-aware CNN ideal observer (IO). In our approach we use a variant of U-Net CNN which is trained simultaneously for defect localization prediction and for reconstruction of the input image. We demonstrate that the reconstruction mean-squared-error (MSE) by the network can serve as an indicator of how well the observer performs in the defect localization task, which is an important step towards developing a domain-aware MO. Furthermore we propose an adaptive learning approach by automatically selecting datasets on which the model in training has poor reconstruction MSE. Our results show that this adaptive training approach can improve the model performance both in generalization and defect localization compared to a non-adaptive approach, particularly for out-of-distribution images - images that were not seen during the training of the algorithm.

Conference Presentation

Citation Download Citation

Nebojsa Bogdanovic, Craig K. Abbey, Yongyi Yang, and Jovan G. Brankov "Adaptive learning approach to improve generalization performance of a domain-aware CNN-based ideal model observer", Proc. SPIE 12929, Medical Imaging 2024: Image Perception, Observer Performance, and Technology Assessment, 129290C (29 March 2024); https://doi.org/10.1117/12.3006257

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