Evaluation of convolutional neural networks for search in 1/f2.8 filtered noise and digital breast tomosynthesis phantoms

Aditya Jonnalagadda; Miguel A. Lago; Bruno Barufaldi; Predrag R. Bakic; Craig K. Abbey; Andrew D. Maidment; Miguel P. Eckstein

doi:10.1117/12.2549362

16 March 2020 Evaluation of convolutional neural networks for search in 1/f ^2.8 filtered noise and digital breast tomosynthesis phantoms

Aditya Jonnalagadda, Miguel A. Lago, Bruno Barufaldi, Predrag R. Bakic, Craig K. Abbey, Andrew D. Maidment, Miguel P. Eckstein

Author Affiliations +

Proceedings Volume 11316, Medical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment; 1131617 (2020) https://doi.org/10.1117/12.2549362
Event: SPIE Medical Imaging, 2020, Houston, Texas, United States

Abstract

With the advent of powerful convolutional neural networks (CNNs), recent studies have extended early applications of neural networks to imaging tasks thus making CNNs a potential new tool for assessing medical image quality. Here, we compare a CNN to model observers in a search task for two possible signals (a simulated mass and a smaller simulated micro-calcification) embedded in filtered noise and single slices of Digital Breast Tomosynthesis (DBT) virtual phantoms. For the case of the filtered noise, we show how a CNN can approximate the ideal observer for a search task, achieving a statistical efficiency of 0.77 for the microcalcification and 0.78 for the mass. For search in single slices of DBT phantoms, we show that a Channelized Hotelling Observer (CHO) performance is affected detrimentally by false positives related to anatomic variations and results in detection accuracy below human observer performance. In contrast, the CNN learns to identify and discount the backgrounds, and achieves performance comparable to that of human observer and superior to model observers (Proportion Correct for the microcalcification: CNN = 0.96; Humans = 0.98; CHO = 0.84; Proportion Correct for the mass: CNN = 0.98; Humans = 0.83; CHO = 0.51). Together, our results provide an important evaluation of CNN methods by benchmarking their performance against human and model observers in complex search tasks.

Citation Download Citation

Aditya Jonnalagadda, Miguel A. Lago, Bruno Barufaldi, Predrag R. Bakic, Craig K. Abbey, Andrew D. Maidment, and Miguel P. Eckstein "Evaluation of convolutional neural networks for search in 1/f ^2.8 filtered noise and digital breast tomosynthesis phantoms", Proc. SPIE 11316, Medical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment, 1131617 (16 March 2020); https://doi.org/10.1117/12.2549362

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Digital breast tomosynthesis

Performance modeling

Visual process modeling

Convolutional neural networks

Image filtering

Mathematical modeling

Spatial frequencies

Keywords/Phrases

Search In:

Publication Years