Autoencoder embedding of task-specific information

Jason L. Granstedt; Weimin Zhou; Mark A. Anastasio

doi:10.1117/12.2513120

4 March 2019 Autoencoder embedding of task-specific information

Jason L. Granstedt, Weimin Zhou, Mark A. Anastasio

Proceedings Volume 10952, Medical Imaging 2019: Image Perception, Observer Performance, and Technology Assessment; 1095207 (2019) https://doi.org/10.1117/12.2513120
Event: SPIE Medical Imaging, 2019, San Diego, California, United States

Abstract

Task-based measures of image quality (IQ) quantify the ability of an observer to perform a specific task. Such measures are employed for assessing and optimizing medical imaging systems. Although the Bayesian ideal observer is optimal by definition, it is frequently both non-linear and intractable. In such cases, linear observers are commonly employed. However, the optimal linear observer, the Hotelling observer (HO), becomes intractable when considering large images. Channelized methods have become popular for reducing the dimensionality of image data. In this work, we propose a novel method for determining efficient channels by learning them with autoencoders (AEs). Autoencoders are neural networks that can be employed to learn concise representations of data, frequently for the purposes of reducing dimensionality. We trained several AEs to encode task-specific information by modifying the standard loss function and examined the effect of hidden layer size and the use of tied/untied weights on the resulting representation accuracy. Subsequently, HOs were applied to both the original images and the dimensionality-reduced versions of them produced by the AEs. It was demonstrated that, for a suitable specification of the AE, the performance of the HO was relatively unaffected by the encoding of the image. However, the computational cost of inverting the covariance matrix was greatly reduced when the HO was applied with the encoded data due to its reduced dimensionality. Our findings suggest that AEs may represent an attractive alternative to the use of heuristic channels for reducing the dimensionality of image data when seeking to accurately approximate the performance of the HO on signal detection tasks.

Conference Presentation

Citation Download Citation

Jason L. Granstedt, Weimin Zhou, and Mark A. Anastasio "Autoencoder embedding of task-specific information", Proc. SPIE 10952, Medical Imaging 2019: Image Perception, Observer Performance, and Technology Assessment, 1095207 (4 March 2019); https://doi.org/10.1117/12.2513120

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