Share Email Print

Proceedings Paper

Evaluation of convolutional neural networks for search in 1/f2.8 filtered noise and digital breast tomosynthesis phantoms
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 16 March 2020
PDF: 8 pages
Proc. SPIE 11316, Medical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment, 1131617 (16 March 2020); doi: 10.1117/12.2549362
Show Author Affiliations
Aditya Jonnalagadda, Univ. of California, Santa Barbara (United States)
Miguel A. Lago, Univ. of California, Santa Barbara (United States)
Bruno Barufaldi, Univ. of Pennsylvania (United States)
Predrag R. Bakic, Univ. of Pennsylvania (United States)
Craig K. Abbey, Univ. of California, Santa Barbara (United States)
Andrew D. Maidment, Univ. of Pennsylvania (United States)
Miguel P. Eckstein, Univ. of California, Santa Barbara (United States)

Published in SPIE Proceedings Vol. 11316:
Medical Imaging 2020: Image Perception, Observer Performance, and Technology Assessment
Frank W. Samuelson; Sian Taylor-Phillips, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?